Update spacy pipeline to 3.8.0

README.md

@@ -14,112 +14,60 @@ model-index:
     metrics:
     - name: NER Precision
       type: precision
-      value: 0.8441212981
+      value: 0.8499734936
     - name: NER Recall
       type: recall
-      value: 0.8368495077
+      value: 0.8456399437
     - name: NER F Score
       type: f_score
-      value: 0.8404696742
+      value: 0.8478011809
   - task:
       name: TAG
       type: token-classification
     metrics:
     - name: TAG (XPOS) Accuracy
       type: accuracy
-      value: 0.9696128631
+      value: 0.9710512465
   - task:
       name: POS
       type: token-classification
     metrics:
     - name: POS (UPOS) Accuracy
       type: accuracy
-      value: 0.9688965451
+      value: 0.9685137334
   - task:
       name: MORPH
       type: token-classification
     metrics:
     - name: Morph (UFeats) Accuracy
       type: accuracy
-      value: 0.9451117385
+      value: 0.9431524548
   - task:
       name: LEMMA
       type: token-classification
     metrics:
     - name: Lemma Accuracy
       type: accuracy
-      value: 0.9745478902
+      value: 0.974069467
   - task:
       name: UNLABELED_DEPENDENCIES
       type: token-classification
     metrics:
     - name: Unlabeled Attachment Score (UAS)
       type: f_score
-      value: 0.8089662094
+      value: 0.818445411
   - task:
       name: LABELED_DEPENDENCIES
       type: token-classification
     metrics:
     - name: Labeled Attachment Score (LAS)
       type: f_score
-      value: 0.7368831893
+      value: 0.7425002788
   - task:
       name: SENTS
       type: token-classification
     metrics:
     - name: Sentences F-Score
       type: f_score
-      value: 0.9721913237
+      value: 0.98
 ---
-Core Hungarian model for HuSpaCy. Components: tok2vec, senter, tagger, morphologizer, lemmatizer, parser, ner
-
-| Feature | Description |
-| --- | --- |
-| **Name** | `hu_core_news_md` |
-| **Version** | `3.7.0` |
-| **spaCy** | `>=3.7.0,<3.8.0` |
-| **Default Pipeline** | `tok2vec`, `senter`, `tagger`, `morphologizer`, `lookup_lemmatizer`, `trainable_lemmatizer`, `parser`, `ner` |
-| **Components** | `tok2vec`, `senter`, `tagger`, `morphologizer`, `lookup_lemmatizer`, `trainable_lemmatizer`, `parser`, `ner` |
-| **Vectors** | -1 keys, 200000 unique vectors (100 dimensions) |
-| **Sources** | [UD Hungarian Szeged](https://universaldependencies.org/treebanks/hu_szeged/index.html) (Richárd Farkas, Katalin Simkó, Zsolt Szántó, Viktor Varga, Veronika Vincze (MTA-SZTE Research Group on Artificial Intelligence))<br>[NYTK-NerKor Corpus](https://github.com/nytud/NYTK-NerKor) (Eszter Simon, Noémi Vadász (Department of Language Technology and Applied Linguistics))<br>[Szeged NER Corpus](https://rgai.inf.u-szeged.hu/node/130) (György Szarvas, Richárd Farkas, László Felföldi, András Kocsor, János Csirik (MTA-SZTE Research Group on Artificial Intelligence))<br>[Hungarian lg Floret vectors](https://huggingface.co/huspacy/hu_vectors_web_lg) (Szeged AI) |
-| **License** | `cc-by-sa-4.0` |
-| **Author** | [SzegedAI, MILAB](https://github.com/huspacy/huspacy) |
-
-### Label Scheme
-
-<details>
-
-<summary>View label scheme (1209 labels for 4 components)</summary>
-
-| Component | Labels |
-| --- | --- |
-| **`tagger`** | `ADJ`, `ADP`, `ADV`, `AUX`, `CCONJ`, `DET`, `INTJ`, `NOUN`, `NUM`, `PART`, `PRON`, `PROPN`, `PUNCT`, `SCONJ`, `SYM`, `VERB`, `X` |
-| **`morphologizer`** | `Definite=Def\|POS=DET\|PronType=Art`, `Case=Ine\|Number=Sing\|POS=NOUN`, `POS=ADV`, `Case=Nom\|NumType=Card\|Number=Sing\|POS=NUM`, `Case=Nom\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Nom\|Number=Sing\|POS=ADJ\|VerbForm=PartPres`, `Case=Nom\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Case=Nom\|Number=Sing\|POS=NOUN`, `Definite=Ind\|POS=DET\|PronType=Tot`, `Case=Ade\|Number=Sing\|POS=NOUN`, `Case=Nom\|Degree=Cmp\|Number=Sing\|POS=ADJ`, `POS=PUNCT`, `Case=Nom\|Number=Sing\|POS=DET\|Person=3\|PronType=Dem`, `Case=Acc\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Definite=Ind\|POS=DET\|PronType=Ind`, `Definite=Def\|Mood=Ind\|Number=Sing\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `POS=ADP`, `POS=CCONJ`, `Case=Del\|Number=Sing\|POS=NOUN`, `Case=Gen\|Number=Sing\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Sbl\|Number=Sing\|POS=NOUN`, `Case=Nom\|Number=Sing\|POS=ADJ\|VerbForm=PartPast`, `Case=Del\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Nom\|Number=Sing\|POS=PROPN`, `Definite=Ind\|Mood=Ind\|Number=Sing\|POS=VERB\|Person=3\|Tense=Past\|VerbForm=Fin\|Voice=Act`, `Case=Acc\|Number=Sing\|POS=NOUN`, `Case=Sup\|Number=Sing\|POS=PROPN`, `Case=Ess\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Case=Ine\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Sup\|Number=Plur\|POS=NOUN`, `Degree=Pos\|POS=ADV`, `Case=Sup\|Number=Sing\|POS=NOUN`, `Definite=Ind\|Mood=Ind\|Number=Sing\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Cau\|Number=Plur\|POS=NOUN`, `Case=Cau\|Number=Sing\|POS=NOUN`, `Case=Gen\|Number=Sing\|POS=NOUN`, `Definite=Ind\|Mood=Ind\|Number=Plur\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Nom\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Definite=Def\|Mood=Ind\|Number=Sing\|POS=VERB\|Person=3\|Tense=Past\|VerbForm=Fin\|Voice=Act`, `Case=Tra\|Number=Sing\|POS=ADJ\|VerbForm=PartPres`, `Case=Nom\|Number=Plur\|POS=NOUN`, `Case=Cau\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Definite=Def\|Mood=Pot\|Number=Plur\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Ins\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Ins\|Number=Sing\|POS=NOUN`, `POS=ADV\|PronType=Neg`, `Case=Ine\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Case=Gen\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `POS=SCONJ`, `Case=Acc\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Definite=Def\|Mood=Ind\|Number=Plur\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Nom\|NumType=Frac\|Number=Sing\|POS=NUM`, `Case=Sbl\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Abl\|Number=Sing\|POS=NOUN`, `Case=Dat\|Number=Sing\|POS=NOUN`, `Definite=Ind\|Mood=Ind\|Number=Sing\|POS=AUX\|Person=3\|Tense=Pres\|Voice=Act`, `POS=VERB\|VerbForm=Inf\|Voice=Act`, `Case=Nom\|Number=Sing\|POS=PRON\|Person=3\|PronType=Dem`, `Definite=Ind\|Mood=Ind\|Number=Plur\|POS=VERB\|Person=3\|Tense=Past\|VerbForm=Fin\|Voice=Act`, `Case=Acc\|Number=Sing\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Nom\|Degree=Sup\|Number=Sing\|POS=ADJ`, `POS=ADV\|PronType=Dem`, `Case=Ins\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Ins\|Number=Sing\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Ade\|Degree=Pos\|Number=Sing\|POS=ADJ`, `POS=ADV\|PronType=Int`, `Case=Tra\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Definite=Ind\|Mood=Pot\|Number=Sing\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Sbl\|Number=Sing\|POS=PROPN`, `Case=Sbl\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Case=All\|Number=Sing\|POS=PRON\|Person=3\|PronType=Dem`, `Definite=Ind\|Mood=Imp\|Number=Sing\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `POS=PART`, `Case=Sup\|Number=Sing\|POS=DET\|Person=3\|PronType=Dem`, `POS=ADV\|PronType=Tot`, `Case=Ill\|Definite=Ind\|POS=DET\|PronType=Ind`, `Number=Sing\|POS=VERB\|Person=3\|VerbForm=Inf\|Voice=Act`, `Case=Ill\|Number=Sing\|POS=NOUN`, `Definite=Ind\|Mood=Ind\|Number=Sing\|POS=AUX\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Sbl\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rel`, `Case=Dat\|Number=Sing\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Nom\|NumType=Ord\|Number=Sing\|POS=ADJ`, `Case=Nom\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rel`, `Definite=Def\|Mood=Ind\|Number=Sing\|POS=AUX\|Person=3\|Tense=Pres\|Voice=Act`, `Definite=Ind\|Mood=Cnd\|Number=Sing\|POS=AUX\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Acc\|Number=Sing\|POS=DET\|Person=3\|PronType=Dem`, `Definite=Def\|Mood=Ind\|Number=Plur\|POS=VERB\|Person=3\|Tense=Past\|VerbForm=Fin\|Voice=Act`, `Case=Sup\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Definite=Ind\|Mood=Ind\|Number=Sing\|POS=AUX\|Person=3\|Tense=Past\|VerbForm=Fin\|Voice=Act`, `Case=Ade\|Number=Sing\|POS=ADJ\|VerbForm=PartPast`, `Case=Nom\|Number=Plur\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Ess\|Number=Sing\|POS=ADJ\|VerbForm=PartPres`, `Case=Acc\|Number=Sing\|POS=PROPN`, `Case=Nom\|Number=Sing\|POS=ADJ\|VerbForm=PartFut`, `Case=Ine\|NumType=Card\|Number=Sing\|POS=NUM`, `Definite=Ind\|Mood=Pot\|Number=Plur\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Acc\|Number=Plur\|POS=NOUN`, `Case=Del\|Number=Plur\|POS=NOUN`, `Case=Gen\|Number=Plur\|POS=PRON\|Person=3\|PronType=Rel`, `Case=Nom\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Case=Tra\|Number=Sing\|POS=NOUN`, `Case=Sup\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rel`, `Definite=Ind\|Mood=Imp\|Number=Plur\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Definite=Def\|Mood=Imp\|Number=Plur\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Acc\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Case=Acc\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Definite=Ind\|POS=DET\|PronType=Art`, `Case=Dat\|Number=Plur\|POS=NOUN`, `Case=Ins\|Number=Plur\|POS=NOUN`, `Case=Sbl\|Number=Plur\|POS=NOUN`, `Case=Ela\|Number=Sing\|POS=NOUN`, `Definite=Ind\|Mood=Pot\|Number=Plur\|POS=VERB\|Person=3\|Tense=Past\|VerbForm=Fin\|Voice=Act`, `Case=Acc\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Case=All\|Number=Sing\|POS=NOUN`, `Case=Ine\|Number=Plur\|POS=NOUN`, `Case=Dat\|Number=Plur\|POS=ADJ\|VerbForm=PartPres`, `Case=Ela\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Case=Abl\|Number=Sing\|POS=PROPN`, `Case=Cau\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Acc\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs\|Reflex=Yes`, `Case=Ins\|Number=Sing\|POS=PROPN`, `Case=Ess\|Number=Sing\|POS=ADJ\|VerbForm=PartPast`, `Number=Plur\|POS=VERB\|Person=3\|VerbForm=Inf\|Voice=Act`, `Case=Sbl\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Nom\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Case=All\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Abl\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Definite=Def\|Mood=Ind\|Number=Plur\|POS=VERB\|Person=1\|Tense=Past\|VerbForm=Fin\|Voice=Act`, `Case=Dat\|Degree=Pos\|Number=Plur\|POS=ADJ`, `POS=ADV\|PronType=Rel`, `Definite=Def\|Mood=Ind\|Number=Plur\|POS=VERB\|Person=3\|Tense=Past\|VerbForm=Fin\|Voice=Cau`, `Case=Del\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Gen\|Number=Sing\|POS=DET\|Person=3\|PronType=Dem`, `Case=Ill\|Number=Plur\|POS=NOUN`, `Case=Ela\|Number=Plur\|POS=NOUN`, `Case=Ill\|Number=Sing\|POS=PROPN`, `Case=Ela\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Nom\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Acc\|Number=Sing\|POS=PRON\|Person=3\|PronType=Int`, `Definite=Def\|POS=DET\|PronType=Ind`, `Case=Dat\|Number=Sing\|POS=PRON\|Person=3\|PronType=Ind`, `Definite=Ind\|Mood=Ind\|Number=Plur\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Nom\|Number=Plur\|POS=PRON\|Person=1\|PronType=Prs`, `Case=Acc\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rcp`, `Case=Ine\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Case=All\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Ter\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `POS=ADV\|VerbForm=Conv`, `Definite=Def\|Mood=Ind\|Number=Plur\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Sup\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Case=Nom\|Number=Sing\|POS=PRON\|Person=3\|PronType=Tot`, `Aspect=Iter\|Definite=Def\|Mood=Ind\|Number=Plur\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Aspect=Iter\|Definite=Def\|Mood=Ind\|Number=Plur\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Definite=Ind\|Mood=Pot\|Number=Sing\|POS=VERB\|Person=3\|Tense=Past\|VerbForm=Fin\|Voice=Act`, `Definite=Def\|Mood=Imp\|Number=Sing\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Nom\|Number=Plur\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Dis\|Number=Sing\|POS=NOUN`, `Case=Gen\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rel`, `Case=Ade\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Dat\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs\|Reflex=Yes`, `Case=All\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Dat\|Number=Plur\|POS=ADJ\|VerbForm=PartPast`, `Case=Dat\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Nom\|Number=Plur\|POS=PROPN`, `Case=Nom\|Degree=Pos\|Number=Plur\|POS=ADJ`, `Case=Cau\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Dat\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Case=Ine\|Number=Sing\|POS=PROPN`, `Definite=Def\|Mood=Ind\|Number=Sing\|POS=VERB\|Person=3\|Tense=Past\|VerbForm=Fin\|Voice=Cau`, `Case=Acc\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Definite=Ind\|Mood=Ind\|Number=Plur\|POS=VERB\|Person=3\|Tense=Past\|VerbForm=Fin\|Voice=Cau`, `Case=Abs\|Number=Sing\|POS=NOUN`, `Case=Ade\|Number=Sing\|POS=PROPN`, `Case=Ins\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Case=Sup\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Sbl\|Number=Sing\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Abl\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Nom\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Gen\|Number=Sing\|POS=PROPN`, `Case=Del\|Number=Sing\|POS=PROPN`, `Case=Sbl\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Loc\|Number=Sing\|POS=NOUN`, `Case=Acc\|Definite=Ind\|POS=DET\|PronType=Ind`, `Case=Ill\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rcp`, `Case=Acc\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs\|Reflex=Yes`, `Definite=Ind\|Mood=Pot\|Number=Plur\|POS=VERB\|Person=1\|Tense=Past\|VerbForm=Fin\|Voice=Act`, `Case=Del\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rel`, `Definite=Ind\|Mood=Cnd\|Number=Sing\|POS=AUX\|Person=3\|Tense=Pres\|Voice=Act`, `Case=Acc\|Number=Plur\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Ter\|Number=Sing\|POS=NOUN`, `Case=Ela\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rel`, `POS=X`, `Definite=Def\|Mood=Cnd\|Number=Sing\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Gen\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Definite=Ind\|Mood=Imp\|Number=Sing\|POS=AUX\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Del\|NumType=Card\|Number=Sing\|POS=NUM`, `Case=Nom\|Number=Sing\|POS=PRON\|Person=3\|PronType=Neg`, `Case=Tra\|Degree=Cmp\|Number=Sing\|POS=ADJ`, `Definite=Ind\|Mood=Ind\|Number=Plur\|POS=VERB\|Person=1\|Tense=Past\|VerbForm=Fin\|Voice=Act`, `Degree=Pos\|POS=ADV\|PronType=Dem`, `Case=Acc\|Number=Sing\|POS=PRON\|Person=3\|Reflex=Yes`, `Case=Nom\|Number=Sing\|POS=PRON\|Person=3\|PronType=Int`, `Case=Del\|Number=Sing\|POS=PRON\|Person=3\|PronType=Dem`, `Definite=Ind\|Mood=Cnd,Pot\|Number=Sing\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Ade\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Acc\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rel`, `Case=Ill\|Number=Sing\|POS=PRON\|Person=3\|PronType=Neg`, `Definite=Def\|Mood=Imp\|Number=Plur\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Aspect=Iter\|Definite=Def\|Mood=Ind\|Number=Sing\|POS=VERB\|Person=3\|Tense=Past\|VerbForm=Fin\|Voice=Act`, `Case=Nom\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs\|Reflex=Yes`, `Case=Ine\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Definite=Def\|Mood=Cnd,Pot\|Number=Sing\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Ine\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rel`, `Case=Sbl\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Case=Dat\|Number=Plur\|POS=PRON\|Person=3\|PronType=Rel`, `Case=Nom\|Number=Plur\|POS=PRON\|Person=3\|PronType=Rel`, `Definite=Ind\|Mood=Ind\|Number=Plur\|POS=AUX\|Person=3\|Tense=Past\|VerbForm=Fin\|Voice=Act`, `Case=Dat\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Case=All\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Ess\|Degree=Sup\|Number=Sing\|POS=ADJ`, `Definite=Ind\|Mood=Cnd\|Number=Sing\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Dat\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Dat\|Number=Sing\|POS=PROPN`, `Case=Nom\|Number=Sing\|Number[psed]=Sing\|POS=NOUN`, `Case=Ins\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Nom\|Number=Plur\|POS=ADJ\|VerbForm=PartPres`, `Case=Sbl\|Degree=Pos\|Number=Plur\|POS=ADJ`, `Case=Ess\|Degree=Cmp\|Number=Sing\|POS=ADJ`, `Case=Acc\|Number=Plur\|Number[psor]=Sing\|POS=ADJ\|Person[psor]=3\|VerbForm=PartPast`, `Definite=Def\|Mood=Pot\|Number=Plur\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Cau`, `Definite=Ind\|POS=DET\|PronType=Neg`, `Case=Ins\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Nom\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Ter\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Sup\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Definite=Def\|Mood=Pot\|Number=Sing\|POS=VERB\|Person=3\|Tense=Past\|VerbForm=Fin\|Voice=Act`, `Case=Nom\|Number=Sing\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Del\|Number=Sing\|POS=PRON\|Person=3\|PronType=Ind`, `Definite=Def\|Mood=Pot\|Number=Sing\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Acc\|Number=Sing\|Number[psor]=Sing\|POS=PROPN\|Person[psor]=3`, `Case=Nom\|Number=Plur\|POS=ADJ\|VerbForm=PartPast`, `Case=Cau\|Number=Sing\|POS=PRON\|Person=3\|PronType=Ind`, `Definite=Ind\|Mood=Imp\|Number=Sing\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Cau`, `Case=Acc\|Number=Sing\|Number[psed]=Sing\|POS=PRON\|Person=3\|PronType=Prs\|Reflex=Yes`, `Case=Acc\|Number=Plur\|POS=ADJ\|VerbForm=PartPast`, `Case=Dat\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Case=Cau\|Number=Sing\|POS=PROPN`, `Case=Abs\|Number=Sing\|POS=ADJ\|VerbForm=PartPres`, `Case=Acc\|Number=Sing\|POS=PRON\|Person=3\|PronType=Tot`, `Case=Dat\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rcp`, `Case=Ine\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Definite=Def\|Mood=Ind\|Number=Sing\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Cau`, `Case=Nom\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Case=Ess\|Number=Sing\|POS=NOUN`, `Case=Ter\|Number=Plur\|POS=NOUN`, `Case=Tem\|NumType=Card\|Number=Sing\|POS=NUM`, `Case=Acc\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `POS=INTJ`, `Case=Ine\|Number=Plur\|POS=DET\|Person=3\|PronType=Dem`, `Number=Plur\|POS=VERB\|Person=1\|VerbForm=Inf\|Voice=Act`, `Case=Sbl\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs\|Reflex=Yes`, `Definite=Ind\|Mood=Pot\|Number=Sing\|POS=AUX\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=All\|Number=Sing\|POS=PROPN`, `Case=Ter\|Number=Sing\|POS=PROPN`, `Case=Dat\|Number=Sing\|POS=PRON\|Person=3\|PronType=Tot`, `Definite=Ind\|Mood=Ind\|Number=Sing\|POS=VERB\|Person=1\|Tense=Past\|VerbForm=Fin\|Voice=Act`, `Definite=Def\|Mood=Ind\|Number=Sing\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Sbl\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Acc\|Number=Plur\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Dat\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rel`, `Case=Gen\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Ind`, `Case=Ins\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rel`, `Definite=Ind\|Mood=Ind\|Number=Plur\|POS=AUX\|Person=3\|Tense=Pres\|Voice=Act`, `Case=Abl\|Number=Sing\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Sup\|Number=Sing\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Ela\|Number=Sing\|POS=PRON\|Person=3\|PronType=Int`, `Case=Acc\|Number=Sing\|POS=PRON\|Person=3\|PronType=Neg`, `Case=Sbl\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Definite=Ind\|Mood=Imp\|Number=Plur\|POS=AUX\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Definite=Def\|Mood=Ind\|Number=Plur\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Cau`, `Definite=Ind\|Mood=Cnd\|Number=Plur\|POS=AUX\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Acc\|Number=Plur\|POS=PRON\|Person=3\|PronType=Rel`, `Definite=Ind\|Mood=Cnd\|Number=Plur\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Nom\|Degree=Pos\|Number=Sing\|Number[psor]=Sing\|POS=ADJ\|Person[psor]=3`, `Case=Sbl\|Degree=Pos\|Number=Sing\|Number[psor]=Sing\|POS=ADJ\|Person[psor]=3`, `Definite=Def\|POS=DET\|PronType=Prs`, `Case=Ill\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Ine\|Number=Sing\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Ill\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Del\|Number=Sing\|Number[psor]=Sing\|POS=PROPN\|Person[psor]=3`, `Case=Acc\|Number=Plur\|POS=DET\|Person=3\|PronType=Dem`, `Definite=Def\|Mood=Ind\|Number=Sing\|POS=VERB\|Person=1\|Tense=Past\|VerbForm=Fin\|Voice=Act`, `Definite=Ind\|Mood=Ind\|Number=Sing\|POS=AUX\|Person=1\|Tense=Past\|VerbForm=Fin\|Voice=Act`, `Definite=Ind\|Mood=Ind\|Number=Sing\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Ill\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Definite=Ind\|Mood=Ind\|Number=Sing\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Cau`, `Definite=Ind\|Mood=Imp,Pot\|Number=Plur\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Nom\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `Case=Dat\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `Definite=Def\|Mood=Imp\|Number=Sing\|POS=VERB\|Person=2\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Dat\|Number=Sing\|Number[psed]=Sing\|POS=PRON\|Person=3\|PronType=Prs\|Reflex=Yes`, `Case=Sbl\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `Case=Ins\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `Definite=Def\|Mood=Imp\|Number=Sing\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Ine\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Ine\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `Definite=Ind\|Mood=Pot\|Number=Sing\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Definite=Def\|Mood=Pot\|Number=Sing\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Dat\|Degree=Sup\|Number=Sing\|POS=ADJ`, `Case=Acc\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `Case=Cau\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Ins\|Number=Plur\|POS=PRON\|Person=1\|PronType=Prs`, `Case=Ins\|Number=Sing\|POS=DET\|Person=3\|PronType=Dem`, `Case=Ins\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Case=Acc\|Number=Sing\|POS=PRON\|Person=2\|PronType=Prs`, `Definite=2\|Mood=Ind\|Number=Sing\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Definite=Ind\|Mood=Ind\|Number=Sing\|POS=VERB\|Person=2\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Nom\|Number=Plur\|POS=DET\|Person=3\|PronType=Dem`, `Case=Sbl\|Number=Plur\|POS=DET\|Person=3\|PronType=Dem`, `Definite=Ind\|Mood=Pot\|Number=Sing\|POS=VERB\|Person=1\|Tense=Past\|VerbForm=Fin\|Voice=Act`, `Case=Acc\|Number=Sing\|POS=PRON\|Person=3\|PronType=Ind`, `Case=All\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Case=All\|Number=Plur\|POS=NOUN`, `Case=Ela\|Number=Plur\|POS=DET\|Person=3\|PronType=Dem`, `Case=Abs\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Ine\|Number=Sing\|POS=DET\|Person=3\|PronType=Dem`, `Case=Ine\|Number=Plur\|POS=PRON\|Person=3\|PronType=Rel`, `Case=Nom\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs\|Reflex=Yes`, `Case=Ins\|Number=Plur\|POS=DET\|Person=3\|PronType=Dem`, `POS=AUX\|VerbForm=Inf\|Voice=Act`, `Case=Nom\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Definite=Def\|Mood=Cnd\|Number=Sing\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Definite=Def\|Mood=Cnd\|Number=Plur\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Ela\|Number=Sing\|POS=DET\|Person=3\|PronType=Dem`, `Case=Nom\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=All\|Number=Sing\|POS=DET\|Person=3\|PronType=Dem`, `Case=Acc\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Aspect=Iter\|Definite=Ind\|Mood=Ind\|Number=Plur\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Gen\|Number=Sing\|Number[psor]=Sing\|POS=PROPN\|Person[psor]=3`, `Case=Ter\|NumType=Card\|Number=Sing\|POS=NUM`, `Case=Gen\|Number=Plur\|POS=NOUN`, `Case=Tem\|Number=Sing\|POS=NOUN`, `Case=Del\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Acc\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Case=Ade\|Number=Plur\|POS=PRON\|Person=1\|PronType=Prs`, `Case=Ins\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `POS=ADV\|PronType=Ind`, `Definite=Ind\|Mood=Ind\|Number=Sing\|POS=AUX\|Person=1\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Ill\|Number=Sing\|POS=DET\|Person=3\|PronType=Dem`, `Definite=Def\|POS=DET\|PronType=Int`, `Case=Gen\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Case=Dat\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Definite=Ind\|Mood=Imp\|Number=Sing\|POS=VERB\|Person=2\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Definite=Ind\|Mood=Ind\|Number=Plur\|POS=AUX\|Person=1\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Abs\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Case=Nom\|Number=Sing\|Number[psed]=Sing\|POS=PROPN`, `Case=Del\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Acc\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Ela\|Number=Sing\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Ins\|Number=Sing\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Acc\|Number=Plur\|POS=PROPN`, `Case=Abl\|NumType=Card\|Number=Sing\|POS=NUM`, `Definite=Def\|Mood=Pot\|Number=Plur\|POS=VERB\|Person=3\|Tense=Past\|VerbForm=Fin\|Voice=Act`, `Case=Dat\|Number=Sing\|Number[psor]=Sing\|POS=PROPN\|Person[psor]=3`, `Case=Abs\|Number=Sing\|Number[psor]=Sing\|POS=PROPN\|Person[psor]=3`, `Definite=Def\|Mood=Pot\|Number=Plur\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Abl\|Number=Plur\|POS=PRON\|Person=3\|PronType=Rel`, `Case=Ela\|Number=Sing\|POS=PROPN`, `Case=Ade\|Number=Sing\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Ela\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Case=Sbl\|Number=Sing\|POS=DET\|Person=3\|PronType=Dem`, `Definite=Def\|Mood=Imp,Pot\|Number=Sing\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Definite=Def\|POS=DET\|PronType=Tot`, `Definite=Def\|POS=DET\|PronType=Neg`, `Case=Ins\|Degree=Cmp\|Number=Plur\|POS=ADJ`, `Case=Ine\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Ind`, `Case=Nom\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rcp`, `Case=Acc\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Case=Sup\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Case=Sbl\|NumType=Card\|Number=Sing\|POS=NUM`, `Case=Ill\|Number=Sing\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Dat\|Number=Plur\|POS=DET\|Person=3\|PronType=Dem`, `Definite=Def\|Mood=Ind\|Number=Plur\|POS=AUX\|Person=3\|Tense=Pres\|Voice=Act`, `Case=Ins\|Number=Sing\|POS=PRON\|Person=3\|PronType=Tot`, `Case=Abl\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs\|Reflex=Yes`, `Case=Gen\|Number=Plur\|POS=DET\|Person=3\|PronType=Dem`, `Definite=Ind\|Mood=Ind\|Number=Sing\|POS=VERB\|Person=3\|Tense=Past\|VerbForm=Fin\|Voice=Cau`, `Case=Sbl\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Case=Tra\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Abl\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Ill\|Number=Sing\|POS=PRON\|Person=3\|PronType=Tot`, `Case=Del\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs\|Reflex=Yes`, `Case=Ess\|Number=Sing\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Ess\|NumType=Card\|Number=Sing\|POS=NUM`, `Case=Sup\|Number=Plur\|POS=DET\|Person=3\|PronType=Dem`, `Case=Acc\|Degree=Pos\|Number=Plur\|POS=ADJ`, `Case=Nom\|Degree=Pos\|Number=Sing\|POS=ADJ\|VerbForm=PartPres`, `Case=Nom\|Degree=Pos\|Number=Sing\|POS=ADJ\|VerbForm=PartPast`, `Case=Ess\|Degree=Pos\|Number=Sing\|POS=ADJ\|VerbForm=PartPres`, `Case=All\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rel`, `Case=Ins\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs\|Reflex=Yes`, `Degree=Cmp\|POS=ADV`, `Definite=Def\|Mood=Ind\|Number=Plur\|POS=VERB\|Person=2\|Tense=Past\|VerbForm=Fin\|Voice=Act`, `Case=Dat\|Number=Plur\|POS=PRON\|Person=2\|PronType=Prs`, `Case=All\|Number=Plur\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Nom\|Number=Sing\|POS=PRON\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Ela\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Cau\|Number=Sing\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Ins\|NumType=Card\|Number=Sing\|POS=NUM`, `Definite=Ind\|Mood=Ind\|Number=Plur\|POS=AUX\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Nom\|Degree=Pos\|Number=Sing\|POS=ADJ\|VerbForm=PartFut`, `Case=Dat\|Degree=Pos\|Number=Plur\|POS=ADJ\|VerbForm=PartPast`, `Degree=Sup\|POS=ADV`, `Case=Acc\|NumType=Card\|Number=Sing\|POS=NUM`, `Definite=Def\|Mood=Ind\|Number=Sing\|POS=AUX\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Ine\|NumType=Frac\|Number=Sing\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Ade\|Number=Plur\|POS=NOUN`, `Case=Acc\|NumType=Frac\|Number=Sing\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Tra\|Degree=Pos\|Number=Sing\|POS=ADJ\|VerbForm=PartPres`, `Case=Nom\|Degree=Pos\|Number=Plur\|POS=ADJ\|VerbForm=PartPres`, `Number=Sing\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Inf\|Voice=Act`, `Case=All\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Case=Cau\|NumType=Card\|Number=Sing\|POS=NUM`, `Case=Nom\|Degree=Pos\|Number=Sing\|Number[psed]=Sing\|POS=ADJ`, `Case=Nom\|NumType=Frac\|Number=Sing\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Ela\|Number=Plur\|POS=PRON\|Person=3\|PronType=Dem`, `Definite=Def\|Mood=Ind\|Number=Plur\|POS=AUX\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Definite=Ind\|Mood=Ind\|Number=Plur\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Cau`, `Case=Ins\|Number=Sing\|POS=PRON\|Person=3\|PronType=Int`, `Case=Ine\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Mood=Pot\|POS=VERB\|VerbForm=Inf\|Voice=Act`, `Case=Ela\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Ade\|Number=Sing\|Number[psed]=Sing\|POS=NOUN`, `Definite=Def\|Mood=Imp\|Number=Sing\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Cau`, `Number=Plur\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Inf\|Voice=Act`, `Case=Ela\|NumType=Card\|Number=Sing\|POS=NUM`, `Case=Dat\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs\|Reflex=Yes`, `Case=Nom\|NumType=Card\|Number=Plur\|POS=NUM`, `Case=Sbl\|NumType=Frac\|Number=Sing\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Definite=Ind\|Mood=Imp\|Number=Plur\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin\|Voice=Cau`, `Case=Ade\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Case=Dat\|Degree=Pos\|Number=Plur\|POS=ADJ\|VerbForm=PartPres`, `Number=Sing\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Inf\|Voice=Act`, `Case=Ine\|Number=Plur\|POS=PRON\|Person=3\|PronType=Dem`, `Number=Plur\|POS=ADV\|Person=1\|PronType=PrsPron`, `POS=ADV\|PronType=v`, `Definite=Ind\|Mood=Imp\|Number=Plur\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Abl\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Number=Sing\|POS=ADV\|Person=3\|PronType=PrsPron`, `Case=Acc\|Number=Plur\|POS=PRON\|Person=1\|PronType=Prs`, `Case=Nom\|NumType[sem]=Time\|Number=Sing\|POS=NUM`, `Case=Tem\|NumType[sem]=Time\|Number=Sing\|POS=NUM`, `Case=Abl\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Number=Sing\|POS=ADV\|Person=1\|PronType=PrsPron`, `Case=Ter\|NumType[sem]=Time\|Number=Sing\|POS=NUM`, `Case=Ill\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Case=Acc\|Number=Plur\|POS=PRON\|Person=2\|PronType=Prs`, `Number=Sing\|POS=VERB\|Person=1\|VerbForm=Inf\|Voice=Act`, `Case=Ine\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=1\|Poss=Yes\|PronType=Prs`, `Case=Ine\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Number=Plur\|POS=ADV\|Person=3\|PronType=PrsPron`, `Case=Ins\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Case=Ela\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Case=Ins\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Ter\|Number=Sing\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Gen\|Number=Sing\|POS=PRON\|Person=3\|PronType=Tot`, `Case=Sbl\|NumType=Ord\|Number=Sing\|POS=ADJ`, `Cas=6\|Number=Sing\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Acc\|Number=Sing\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Ela\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Sup\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Nom\|Number=Plur\|POS=PRON\|Person=3\|PronType=Tot`, `Case=Ade\|Number=Sing\|POS=PRON\|Person=3\|PronType=Tot`, `Definite=Ind\|Mood=Imp\|Number=Sing\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Sup\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Case=Sbl\|Number=Plur\|POS=PRON\|Person=3\|PronType=Rel`, `Case=Del\|Degree=Sup\|Number=Sing\|POS=ADJ`, `Case=Abl\|Number=Sing\|POS=PRON\|Person=3\|PronType=Int`, `Case=Nom\|NumType=Dist\|Number=Sing\|POS=NUM`, `Case=Sup\|Number=Plur\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Nom\|Number=Sing\|POS=PRON\|Person=1\|Reflexive=Yes`, `Case=Nom\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=2`, `Case=Acc\|Number=Sing\|POS=PRON\|Person=1\|Reflexive=Yes`, `Case=Sbl\|Number=Sing\|POS=PRON\|Person=1\|Reflexive=Yes`, `Case=Abl\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Ins\|Number=Sing\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Sbl\|Number=Sing\|POS=PRON\|Person=3\|Reflexive=Yes`, `Definite=Ind\|Mood=Cnd\|Number=Sing\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Ins\|Number=Plur\|POS=PRON\|Person=3\|PronType=Rel`, `Case=Sbl\|Degree=Cmp\|Number=Sing\|POS=ADJ`, `Definite=Ind\|Mood=Ind\|Number=Sing\|POS=AUX\|Person=1\|Tense=Pres\|Voice=Act`, `Definite=Def\|Mood=Ind\|Number=Sing\|POS=AUX\|Person=1\|Tense=Pres\|Voice=Act`, `Case=Acc\|NumType=Card\|Number=Sing\|Number[psor]=Plur\|POS=NUM\|Person[psor]=1`, `Case=Nom\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=1\|Poss=Yes\|PronType=Prs`, `Case=Abl\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `Number=Plur\|POS=ADV\|Person=2\|PronType=PrsPron`, `Case=Ine\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Definite=Ind\|Mood=Ind\|Number=Plur\|POS=AUX\|Person=1\|Tense=Pres\|Voice=Act`, `Case=Acc\|Number=Plur\|POS=PRON\|Person=1\|Reflexive=Yes`, `Case=All\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Dat\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Ill\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rel`, `Case=Sbl\|Number=Sing\|POS=PRON\|Person=3\|PronType=Ind`, `Definite=Ind\|Mood=Cnd\|Number=Plur\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Sup\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Case=Gen\|Degree=Cmp\|Number=Plur\|POS=ADJ`, `Case=Nom\|Degree=Sup\|Number=Plur\|POS=ADJ`, `Case=Ins\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rcp`, `Case=Del\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Case=Del\|Number=Sing\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Nom\|Number=Sing\|Number[psor]=Plur\|POS=PRON\|Person=3\|Person[psor]=1\|Poss=Yes\|PronType=Prs`, `Case=Ela\|Number=Sing\|POS=PRON\|Person=3\|PronType=Tot`, `Case=Nom\|Degree=Cmp\|Number=Plur\|POS=ADJ`, `Definite=Ind\|Mood=Ind\|Number=Plur\|POS=VERB\|Person=2\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Nom\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=2`, `Case=All\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Case=Abl\|Number=Sing\|POS=PRON\|Person=3\|PronType=Tot`, `Case=All\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Abl\|Number=Plur\|POS=NOUN`, `Case=Dat\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Ade\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Cas=6\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rel`, `Case=Nom\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=3\|Poss=Yes\|PronType=Prs`, `Case=Nom\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=2\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Ess\|Number=Sing\|POS=PRON\|Person=3\|PronType=Tot`, `Case=Abl\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rcp`, `Case=Sbl\|NumType[sem]=Time\|Number=Sing\|POS=NUM`, `Case=All\|Number=Plur\|POS=PROPN`, `Case=Nom\|Number=Sing\|Number[psor]=Plur\|POS=PRON\|Person=3\|Person[psor]=1\|PronType=Ind`, `Case=Ine\|Number=Sing\|POS=PRON\|Person=1\|Reflexive=Yes`, `Case=Acc\|Degree=Cmp\|Number=Plur\|POS=ADJ`, `Case=Dat\|Number=Plur\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Ine\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Nom\|Number=Sing\|Number[psor]=Sing\|POS=PROPN\|Person[psor]=3`, `Case=Ade\|Degree=Cmp\|Number=Sing\|POS=ADJ`, `Case=Nom\|Number=Plur\|POS=PRON\|Person=2\|PronType=Prs`, `Definite=Def\|Mood=Ind\|Number=Plur\|POS=VERB\|Person=2\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Definite=Ind\|Mood=Ind\|Number=Plur\|POS=VERB\|Person=2\|Tense=Past\|VerbForm=Fin\|Voice=Act`, `Case=Dat\|NumType=Ord\|Number=Sing\|POS=ADJ`, `Case=Ins\|Number=Plur\|POS=PROPN`, `Case=Nom\|NumType=Ord\|Number=Plur\|POS=ADJ`, `Case=Dat\|Number=Sing\|POS=PRON\|Person=3\|PronType=Int`, `Case=Ela\|Number=Sing\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Ine\|Number=Sing\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Sup\|Number=Sing\|POS=PRON\|Person=3\|PronType=Tot`, `Definite=Def\|Mood=Cnd\|Number=Plur\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=All\|Number=Sing\|POS=PRON\|Person=1\|Reflexive=Yes`, `Case=Nom\|NumType[sem]=Dot\|Number=Sing\|POS=NUM`, `Case=Sup\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Degree=Pos\|POS=ADV\|PronType=Ind`, `Case=Ela\|Number=Sing\|Number[psed]=Sing\|POS=NOUN`, `Definite=Def\|Mood=Ind\|Number=Plur\|POS=AUX\|Person=1\|Tense=Pres\|Voice=Act`, `Case=Ade\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Ins\|Number=Plur\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Sup\|NumType[sem]=Time\|Number=Sing\|POS=NUM`, `Case=Gen\|Number=Plur\|POS=PROPN`, `Case=All\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rcp`, `Case=Ins\|Number=Sing\|Number[psed]=Sing\|POS=NOUN`, `Case=Ill\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Sbl\|Number=Sing\|POS=PRON\|Person=3\|PronType=Tot`, `Case=Del\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Number=Sing\|POS=ADV\|Person=2\|PronType=PrsPron`, `Case=Sbl\|Number=Sing\|POS=PRON\|Person=3\|PronType=Int`, `Case=Gen\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Case=Ill\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Degree=Cmp\|POS=ADV\|PronType=Dem`, `Case=Ins\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Case=Sup\|Number=Sing\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Ins\|NumType=Card\|Number=Sing\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Ill\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Case=Ill\|Number=Sing\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Dat\|NumType=Card\|Number=Sing\|POS=NUM`, `Case=All\|Number=Sing\|POS=PRON\|Person=3\|PronType=Tot`, `Case=Dat\|Number=Plur\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Abl\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rel`, `Case=All\|Number=Sing\|POS=PRON\|Person=3\|Reflexive=Yes`, `Definite=Def\|Mood=Ind\|Number=Sing\|POS=VERB\|Person=2\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Del\|Number=Sing\|POS=PRON\|Person=1\|Reflexive=Yes`, `Case=Ins\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=2`, `Case=Nom\|Number=Sing\|Number[psor]=Plur\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Ind`, `Case=All\|Number=Sing\|POS=PRON\|Person=3\|PronType=Int`, `Case=Nom\|Number=Plur\|POS=PRON\|Person=1\|PronType=Tot`, `Case=Gen\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Case=Dat\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Case=Acc\|Degree=Sup\|Number=Sing\|POS=ADJ`, `Case=Nom\|Degree=Pos\|Number=Sing\|Number[psor]=Sing\|POS=ADJ\|Person[psor]=1`, `Case=Sbl\|NumType=Frac\|Number=Sing\|POS=NUM`, `Case=Tem\|NumType=Frac\|Number=Sing\|POS=NUM`, `Case=Tem\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Nom\|NumType[sem]=Result\|Number=Sing\|POS=NUM`, `Case=Del\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rcp`, `Case=Gen\|Number=Sing\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Acc\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=2`, `Case=Ins\|Number=Sing\|POS=PRON\|Person=1\|Reflexive=Yes`, `Case=Dat\|Number=Plur\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Acc\|Number=Plur\|Number[psed]=Sing\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Cau\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rel`, `Case=Acc\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=3\|Poss=Yes\|PronType=Prs`, `Case=Nom\|Number=Plur\|POS=PRON\|Person=1\|Reflexive=Yes`, `Case=Ade\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rel`, `Case=Ins\|Number=Plur\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Dat\|Number=Sing\|POS=PRON\|Person=1\|Reflexive=Yes`, `Case=Ine\|Number=Sing\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Dat\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Case=Nom\|Number=Sing\|Number[psor]=Plur\|POS=PRON\|Person=3\|Person[psor]=1\|PronType=Tot`, `Case=Sbl\|Number=Plur\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Ela\|Number=Plur\|POS=PRON\|Person=3\|PronType=Rel`, `Case=Dat\|Number=Plur\|POS=PRON\|Person=1\|Reflexive=Yes`, `Case=Nom\|Number=Sing\|POS=PRON\|Person=2\|PronType=Prs`, `Definite=Ind\|Mood=Ind\|Number=Sing\|POS=VERB\|Person=2\|Tense=Past\|VerbForm=Fin\|Voice=Act`, `Case=Sup\|Number=Sing\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Ind`, `Case=Del\|Number=Plur\|POS=PRON\|Person=1\|Reflexive=Yes`, `Case=Del\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Case=Dat\|Degree=Cmp\|Number=Sing\|POS=ADJ`, `Definite=2\|Mood=Ind\|Number=Sing\|POS=VERB\|Person=1\|Tense=Past\|VerbForm=Fin\|Voice=Act`, `Case=Com\|Number=Sing\|POS=NOUN`, `Case=Tra\|Number=Plur\|POS=NOUN`, `Case=Ins\|Number=Plur\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Acc\|Number=Plur\|POS=PRON\|Person=1\|PronType=Tot`, `Case=Ade\|Number=Plur\|POS=PROPN`, `Case=Ins\|Number=Plur\|POS=PRON\|Person=2\|PronType=Prs`, `Case=Ess\|Number=Sing\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Dat\|Degree=Cmp\|Number=Plur\|POS=ADJ`, `Definite=Def\|Mood=Imp\|Number=Plur\|POS=VERB\|Person=2\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Sbl\|NumType[sem]=Quotient\|Number=Sing\|POS=NUM`, `Case=Nom\|Number=Plur\|POS=PRON\|Person=3\|PronType=Int`, `Case=Del\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Case=Del\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Case=Sup\|Number=Sing\|POS=PRON\|Person=1\|Reflexive=Yes`, `Case=Ade\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Ins\|NumType=Card\|Number=Plur\|POS=NUM`, `Case=Ess\|Number=Sing\|POS=PRON\|Person=3\|PronType=Int`, `Case=Del\|Degree=Cmp\|Number=Sing\|POS=ADJ`, `Case=Cau\|Number=Plur\|POS=PRON\|Person=1\|Reflexive=Yes`, `Case=Sbl\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rcp`, `Case=Tem\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Ill\|NumType=Frac\|Number=Sing\|POS=NUM`, `Case=Ill\|Number=Plur\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Nom\|Degree=Pos\|Number=Sing\|Number[psor]=Plur\|POS=ADJ\|Person[psor]=1`, `Case=Del\|Number=Sing\|POS=PRON\|Person=3\|PronType=Int`, `Case=Del\|Number=Sing\|POS=PRON\|Person=3\|PronType=Tot`, `Case=Gen\|NumType=Card\|Number=Sing\|Number[psor]=Plur\|POS=NUM\|Person[psor]=1`, `Case=Gen\|Number=Sing\|Number[psor]=Plur\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Ind`, `Case=Dat\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Case=Gen\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Case=Nom\|Number=Sing\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Ela\|Number=Sing\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Ins\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Case=Dat\|NumType=Card\|Number=Sing\|Number[psor]=Plur\|POS=NUM\|Person[psor]=1`, `Case=Sbl\|Number=Plur\|POS=PRON\|Person=1\|Reflexive=Yes`, `Case=Ill\|Number=Sing\|POS=PRON\|Person=3\|PronType=Int`, `Case=Acc\|Degree=Cmp\|Number=Sing\|POS=ADJ`, `Case=Cau\|Number=Sing\|POS=PRON\|Person=3\|PronType=Tot`, `Case=Acc\|Number=Plur\|POS=PRON\|Person=3\|PronType=Int`, `Case=Acc\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=2`, `Definite=Def\|Mood=Cnd\|Number=Plur\|POS=VERB\|Person=2\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Ins\|Number=Plur\|POS=PRON\|Person=1\|Reflexive=Yes`, `Case=Sbl\|Degree=Sup\|Number=Sing\|POS=ADJ`, `Case=Sup\|Number=Plur\|POS=PRON\|Person=1\|Reflexive=Yes`, `Case=Tem\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Case=Ins\|Degree=Pos\|Number=Plur\|POS=ADJ`, `Case=Abl\|Number=Sing\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Tra\|Number=Sing\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Abs\|NumType=Ord\|Number=Sing\|POS=ADJ`, `Case=All\|Number=Plur\|POS=PRON\|Person=1\|PronType=Tot`, `Case=Dat\|Number=Sing\|Number[psor]=Plur\|POS=PRON\|Person=3\|Person[psor]=1\|PronType=Ind`, `Case=Ine\|Number=Plur\|POS=PRON\|Person=1\|Reflexive=Yes`, `Case=Sup\|Number=Plur\|POS=PRON\|Person=3\|PronType=Ind`, `Definite=Def\|Mood=Ind\|Number=Sing\|POS=VERB\|Person=2\|Tense=Past\|VerbForm=Fin\|Voice=Act`, `Case=All\|Number=Plur\|POS=PRON\|Person=1\|Reflexive=Yes`, `Cas=1\|Number=Sing\|POS=PROPN`, `Definite=Ind\|Mood=Ind\|Number=Sing\|POS=AUX\|Person=2\|Tense=Pres\|Voice=Act`, `Case=Ela\|Number=Sing\|POS=PRON\|Person=1\|Reflexive=Yes`, `Case=Sbl\|Number=Sing\|POS=PRON\|Person=2\|Reflexive=Yes`, `Case=Nom\|Number=Sing\|POS=PRON\|Person=2\|Reflexive=Yes`, `Case=Nom\|Number=Sing\|Number[psor]=Sing\|POS=PROPN\|Person[psor]=1`, `Case=Acc\|Number=Plur\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Sbl\|NumType[sem]=Result\|Number=Sing\|POS=NUM`, `Case=Nom\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=2`, `Case=Nom\|Number=Sing\|Number[psed]=Sing\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Nom\|Number=Sing\|Number[psed]=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Case=Sbl\|Number=Sing\|Number[psed]=Sing\|POS=NOUN`, `Case=Nom\|Number=Sing\|Number[psed]=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Definite=Ind\|Mood=Ind\|Number=Sing\|POS=AUX\|Person=3\|Tense=Past\|Voice=Act`, `Case=Ill\|Number=Sing\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Ine\|Number=Sing\|POS=PRON\|Person=3\|PronType=Tot`, `Case=Ins\|Number=Sing\|Number[psor]=Sing\|POS=PROPN\|Person[psor]=3`, `Case=Ela\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Case=Gen\|Number=Plur\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Dat\|NumType=Card\|Number=Sing\|Number[psor]=Plur\|POS=NUM\|Person[psor]=3`, `Case=Ine\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rcp`, `Case=Nom\|Number=Sing\|Number[psed]=Sing\|POS=PRON\|Person=3\|PronType=Rel`, `Case=Dat\|Number=Plur\|POS=PRON\|Person=1\|PronType=Tot`, `Definite=Ind\|Mood=Imp\|Number=Plur\|POS=VERB\|Person=2\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Cau\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Case=Acc\|Number=Sing\|Number[psed]=Sing\|POS=PROPN`, `Case=Dat\|Number=Sing\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Nom\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=1\|PronType=Tot`, `Case=Abl\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Tra\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Cau\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Case=Gen\|Number=Sing\|POS=PRON\|Person=3\|PronType=Int`, `Case=Sup\|Number=Plur\|POS=PROPN`, `Case=Ess\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Definite=Def\|Mood=Cnd\|Number=Sing\|POS=VERB\|Person=2\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Dis\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Case=Ill\|Number=Sing\|Number[psor]=Sing\|POS=PROPN\|Person[psor]=3`, `Case=All\|Number=Sing\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Nom\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Tot`, `Case=Nom\|NumType=Card\|Number=Sing\|Number[psor]=Plur\|POS=NUM\|Person[psor]=1`, `Case=Nom\|Number=Plur\|POS=PRON\|Person=3\|Reflexive=Yes`, `Cas=6\|Number=Sing\|POS=PRON\|Person=3\|PronType=Tot`, `Case=Ins\|Number=Plur\|POS=PRON\|Person=3\|PronType=Int`, `Case=Sup\|Number=Plur\|POS=PRON\|Person=3\|PronType=Rel`, `Case=Sbl\|Number=Sing\|Number[psed]=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Sup\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Abl\|Number=Plur\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Gen\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Abs\|Number=Plur\|POS=NOUN`, `Case=Sup\|Number=Sing\|Number[psor]=Plur\|POS=PRON\|Person=3\|Person[psor]=1\|PronType=Tot`, `Case=Ine\|Number=Sing\|Number[psed]=Sing\|POS=NOUN`, `Case=Tra\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Case=Sbl\|Number=Plur\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Ins\|Degree=Cmp\|Number=Sing\|Number[psor]=Sing\|POS=ADJ\|Person[psor]=3`, `Case=Ade\|Number=Sing\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Sbl\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=All\|Number=Sing\|Number[psed]=Sing\|POS=NOUN`, `Case=Abl\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Case=Nom\|Number=Sing\|Number[psor]=Plur\|POS=PROPN\|Person[psor]=1`, `Case=Nom\|Number=Sing\|Number[psed]=Sing\|POS=PRON\|Person=3\|PronType=Int`, `Case=Del\|Number=Plur\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Del\|Number=Plur\|POS=PRON\|Person=3\|PronType=Rel`, `Case=All\|Number=Plur\|POS=PRON\|Person=3\|PronType=Rel`, `Case=Ade\|Number=Plur\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Ter\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Case=Nom\|NumType=Card\|Number=Sing\|Number[psor]=Plur\|POS=NUM\|Person[psor]=3`, `Case=Abl\|Number=Sing\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Dat\|Number=Sing\|POS=PRON\|Person=2\|Reflexive=Yes`, `Case=Dat\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=2`, `Case=Ins\|Number=Plur\|POS=PRON\|Person=3\|PronType=Tot`, `Case=Sup\|Degree=Pos\|Number=Plur\|POS=ADJ`, `Case=Ela\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `Case=Ine\|Number=Plur\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Acc\|Number=Sing\|Number[psed]=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Sbl\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Definite=Ind\|Mood=Cnd\|Number=Sing\|POS=VERB\|Person=2\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Ill\|NumType=Card\|Number=Sing\|POS=NUM`, `Case=Acc\|NumType=Frac\|Number=Sing\|POS=NUM`, `Case=Cau\|Number=Sing\|POS=PRON\|Person=3\|PronType=Int`, `Case=Gen\|NumType=Card\|Number=Sing\|POS=NUM`, `Case=Ade\|Number=Sing\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=All\|NumType=Card\|Number=Sing\|POS=NUM`, `Case=Ill\|Number=Sing\|Number[psor]=Plur\|POS=PRON\|Person=3\|Person[psor]=1\|Poss=Yes\|PronType=Prs`, `Definite=2\|Mood=Cnd\|Number=Sing\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Cas=6\|Number=Sing\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Cau\|Number=Plur\|POS=PRON\|Person=3\|PronType=Tot`, `Case=Abl\|Degree=Pos\|Number=Plur\|POS=ADJ`, `Case=Abs\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Case=Acc\|Number=Plur\|Number[psed]=Sing\|POS=NOUN`, `Case=Nom\|NumType=Card\|Number=Sing\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Cau\|Number=Plur\|POS=PRON\|Person=3\|PronType=Dem`, `Case=All\|Number=Plur\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Acc\|Degree=Sup\|Number=Plur\|POS=ADJ`, `Case=Sup\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rcp`, `Case=Ade\|Number=Plur\|Number[psed]=Sing\|POS=NOUN`, `Case=Nom\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=2`, `Case=Ill\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=2`, `Case=Del\|Degree=Sup\|Number=Plur\|POS=ADJ`, `Case=Nom\|Number=Plur\|Number[psed]=Sing\|POS=NOUN`, `Case=Cau\|Number=Plur\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Cau\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rcp`, `Number=Sing\|POS=VERB\|Person=2\|VerbForm=Inf\|Voice=Act`, `Case=Ine\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=2`, `Case=Acc\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=2`, `Case=Cau\|Degree=Cmp\|Number=Plur\|POS=ADJ`, `Case=Ine\|Number=Sing\|Number[psor]=Plur\|POS=PRON\|Person=3\|Person[psor]=1\|Poss=Yes\|PronType=Prs`, `Case=Ela\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Sup\|Number=Plur\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Cau\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Sbl\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Case=Ter\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Tra\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Cau\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `Definite=Ind\|Mood=Cnd\|Number=Plur\|POS=VERB\|Person=2\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Nom\|Number=Sing\|Number[psor]=Plur\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Tot`, `Case=Acc\|Number=Sing\|Number[psed]=Sing\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Dat\|NumType=Card\|Number=Plur\|POS=NUM`, `Case=Dat\|Number=Sing\|Number[psed]=Sing\|POS=PRON\|Person=1\|Reflexive=Yes`, `Case=Abl\|Number=Plur\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Tem\|Number=Plur\|POS=NOUN`, `Case=Abs\|Number=Sing\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Sbl\|Number=Plur\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Ins\|Number=Sing\|Number[psed]=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=All\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Case=Abl\|Number=Sing\|POS=PRON\|Person=1\|Reflexive=Yes`, `Case=Acc\|NumType=Ord\|Number=Sing\|POS=ADJ`, `Case=All\|NumType=Ord\|Number=Sing\|POS=ADJ`, `Case=Nom\|Number=Plur\|Number[psed]=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Nom\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Ind`, `Case=Ill\|Number=Sing\|POS=PRON\|Person=1\|Reflexive=Yes`, `Case=Ade\|NumType=Card\|Number=Sing\|POS=NUM`, `Case=Ade\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Case=Nom\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=2\|PronType=Tot`, `Case=Abl\|Number=Plur\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Cau\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Del\|Degree=Pos\|Number=Plur\|POS=ADJ`, `Case=Cau\|Number=Plur\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Ill\|Number=Plur\|POS=PRON\|Person=3\|PronType=Rel`, `Case=Ade\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Ine\|Number=Sing\|POS=PRON\|Person=3\|PronType=Int`, `Case=Nom\|Number=Sing\|Number[psed]=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Acc\|Number=Plur\|POS=PRON\|Person=3\|PronType=Tot`, `Case=Ade\|Number=Plur\|POS=PRON\|Person=3\|PronType=Rel`, `Case=Acc\|Number=Sing\|POS=PRON\|Person=2\|Reflexive=Yes`, `Case=Ins\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=2`, `Case=All\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=2`, `Case=Acc\|Number=Sing\|Number[psor]=Plur\|POS=PRON\|Person=3\|Person[psor]=1\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `Case=Ess\|NumType=Ord\|Number=Sing\|POS=ADJ`, `Case=Cau\|Degree=Sup\|Number=Plur\|POS=ADJ`, `Cas=6\|Number=Sing\|POS=PRON\|Person=3\|PronType=Int`, `Case=Tra\|NumType=Card\|Number=Sing\|POS=NUM`, `Number=Plur\|POS=VERB\|Person=2\|VerbForm=Inf\|Voice=Act`, `Case=Nom\|Degree=Pos\|Number=Plur\|Number[psor]=Sing\|POS=ADJ\|Person[psor]=3`, `Cas=6\|Number=Sing\|POS=NOUN`, `Case=Ins\|Number=Sing\|Number[psed]=Sing\|POS=PROPN`, `Case=Ins\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Ind`, `Case=Ela\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=2`, `Case=Sup\|NumType=Card\|Number=Sing\|Number[psor]=Plur\|POS=NUM\|Person[psor]=3`, `Case=Abl\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Case=Nom\|Number=Sing\|Number[psor]=Plur\|POS=PRON\|Person=3\|Person[psor]=1\|PronType=Int`, `Case=Ill\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=2`, `Case=Del\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Case=Tra\|Degree=Pos\|Number=Plur\|POS=ADJ`, `Case=Sbl\|NumType=Card\|Number=Plur\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Acc\|NumType=Card\|Number=Plur\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Nom\|Number=Sing\|Number[psor]=Plur\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Int`, `Case=Nom\|Number=Plur\|Number[psed]=Sing\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Ine\|Number=Sing\|POS=PRON\|Person=2\|Reflexive=Yes`, `Case=Abl\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Case=Gen\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Case=Gen\|NumType=Card\|Number=Plur\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Nom\|Number=Sing\|Number[psor]=Plur\|POS=PRON\|Person=3\|Person[psor]=3\|Poss=Yes\|PronType=Prs`, `Case=Ins\|NumType=Card\|Number=Sing\|Number[psor]=Plur\|POS=NUM\|Person[psor]=3`, `Case=All\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Case=Acc\|NumType=Card\|Number=Sing\|Number[psor]=Plur\|POS=NUM\|Person[psor]=3`, `Case=Tra\|Degree=Sup\|Number=Plur\|POS=ADJ`, `Case=Sbl\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=2`, `Case=Ins\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=2`, `Case=Nom\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=1\|PronType=Dem`, `Case=Nom\|Degree=Cmp\|Number=Plur\|Number[psed]=Sing\|POS=ADJ`, `Case=Acc\|Number=Sing\|Number[psed]=Sing\|POS=NOUN`, `Case=Cau\|Number=Plur\|POS=PRON\|Person=3\|PronType=Rel`, `Case=Nom\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=2\|PronType=Ind`, `Case=All\|Degree=Pos\|Number=Plur\|POS=ADJ`, `Case=All\|Number=Sing\|POS=PRON\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Tem\|Number=Sing\|POS=PRON\|Person=3\|PronType=Int`, `Case=Dat\|Number=Sing\|POS=PRON\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Ill\|Number=Sing\|POS=PRON\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Abl\|Number=Sing\|POS=PRON\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Cau\|Number=Plur\|POS=PROPN`, `Case=Ade\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Gen\|Number=Sing\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Ade\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Ind`, `Case=All\|Number=Plur\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Gen\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Del\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=2`, `Definite=Ind\|Mood=Ind\|Number=Plur\|POS=AUX\|Person=2\|Tense=Pres\|Voice=Act`, `Definite=Def\|Mood=Ind\|Number=Plur\|POS=AUX\|Person=2\|Tense=Pres\|Voice=Act`, `Case=Sup\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=2`, `Case=Tra\|Number=Sing\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Ins\|Number=Sing\|POS=PRON\|Person=2\|PronType=Prs`, `Case=Sup\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Ind`, `Case=Nom\|NumType=Card\|Number=Plur\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Sbl\|Number=Sing\|Number[psed]=Sing\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Nom\|Number=Plur\|Number[psed]=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=All\|Number=Plur\|Number[psed]=Sing\|POS=NOUN`, `Case=Nom\|Number=Sing\|Number[psed]=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Ill\|Number=Plur\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Ela\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Ind`, `Case=Ela\|Degree=Pos\|Number=Plur\|POS=ADJ`, `Case=Del\|Number=Plur\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Sup\|Number=Sing\|POS=PRON\|Person=3\|PronType=Int`, `Case=Tra\|Number=Plur\|Number[psed]=Sing\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Ter\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Nom\|Number=Sing\|Number[psed]=Sing\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Acc\|Number=Sing\|Number[psor]=Plur\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Tot`, `Case=Acc\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Ind`, `Case=All\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=2`, `Case=Acc\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=1\|Poss=Yes\|PronType=Prs`, `Case=Ter\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=2`, `Case=All\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=1\|Poss=Yes\|PronType=Prs`, `Definite=Def\|Mood=Ind\|Number=Sing\|POS=AUX\|Person=2\|Tense=Pres\|Voice=Act`, `Case=Gen\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=2`, `Case=Cau\|Number=Plur\|Number[psed]=Sing\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Ins\|Number=Plur\|Number[psed]=Sing\|POS=NOUN`, `Case=Gen\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=3\|Poss=Yes\|PronType=Prs`, `Case=Del\|Number=Plur\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Tem\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Case=Del\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=2`, `Case=Sup\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=2`, `Case=Ter\|Number=Sing\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Sup\|Number=Sing\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Ine\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Abs\|Number=Sing\|POS=PRON\|Person=3\|PronType=Dem`, `Case=All\|Number=Sing\|Number[psor]=Plur\|POS=PRON\|Person=3\|Person[psor]=1\|Poss=Yes\|PronType=Prs`, `Case=Sup\|NumType=Ord\|Number=Sing\|POS=ADJ`, `Case=Cau\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=2`, `Case=Sup\|NumType=Ord\|Number=Sing\|Number[psor]=Sing\|POS=ADJ\|Person[psor]=3`, `Case=Sup\|Number=Sing\|Number[psor]=Sing\|POS=PROPN\|Person[psor]=3`, `Case=Abl\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Nom\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Int`, `Case=Ela\|Number=Plur\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Dat\|NumType=Ord\|Number=Sing\|Number[psor]=Sing\|POS=ADJ\|Person[psor]=3`, `Case=Ill\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Case=All\|Number=Sing\|Number[psed]=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=1`, `Case=Nom\|Number=Plur\|Number[psor]=Sing\|POS=PROPN\|Person[psor]=1`, `Case=Ine\|NumType=Card\|Number=Sing\|Number[psor]=Plur\|POS=NUM\|Person[psor]=1`, `Case=Abl\|Number=Sing\|Number[psor]=Sing\|POS=PROPN\|Person[psor]=1`, `Case=Ela\|Number=Sing\|Number[psed]=Sing\|POS=PRON\|Person=3\|PronType=Tot`, `Case=Ade\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Case=Ill\|Number=Sing\|Number[psor]=Plur\|POS=PROPN\|Person[psor]=1`, `Case=Ade\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=1\|Poss=Yes\|PronType=Prs`, `Case=All\|Number=Sing\|Number[psed]=Sing\|POS=PROPN`, `Case=Acc\|Degree=Pos\|Number=Plur\|Number[psor]=Plur\|POS=ADJ\|Person[psor]=3`, `Case=Dat\|Degree=Pos\|Number=Sing\|Number[psor]=Sing\|POS=ADJ\|Person[psor]=3`, `Case=Nom\|Number=Sing\|POS=SYM\|Type=w`, `Case=Gen\|Number=Sing\|POS=SYM\|Type=w`, `Case=Abl\|Number=Sing\|POS=SYM\|Type=w`, `Case=Acc\|Number=Sing\|POS=SYM\|Type=w`, `Case=Ade\|Degree=Pos\|Number=Plur\|POS=ADJ`, `Case=All\|Number=Sing\|POS=SYM\|Type=w`, `Case=Tra\|Degree=Sup\|Number=Sing\|POS=ADJ`, `Case=Ins\|Degree=Cmp\|Number=Sing\|POS=ADJ`, `Case=Abl\|Number=Sing\|Number[psed]=Sing\|POS=NOUN`, `Case=Nom\|Degree=Pos\|Number=Plur\|Number[psed]=Sing\|POS=ADJ`, `Case=Sup\|Number=Sing\|Number[psed]=Sing\|POS=NOUN`, `Case=Sup\|Degree=Pos\|Number=Sing\|Number[psor]=Sing\|POS=ADJ\|Person[psor]=3`, `Case=Nom\|NumType[sem]=Quotient\|Number=Sing\|POS=NUM`, `Case=Gen\|Degree=Pos\|Number=Plur\|POS=ADJ`, `Case=Acc\|Number=Sing\|Number[psor]=Plur\|POS=PROPN\|Person[psor]=1`, `Case=Ins\|Number=Sing\|Number[psed]=Plur\|POS=NOUN`, `Case=Gen\|Number=Sing\|Number[psed]=Sing\|POS=NOUN`, `Case=Ine\|Degree=Pos\|Number=Sing\|Number[psor]=Plur\|POS=ADJ\|Person[psor]=3`, `Case=Abs\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Ela\|Degree=Pos\|Number=Sing\|Number[psor]=Sing\|POS=ADJ\|Person[psor]=3`, `Case=Dat\|Number=Sing\|Number[psed]=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Gen\|Number=Plur\|Number[psed]=Sing\|POS=NOUN`, `Case=Nom\|Number=Sing\|POS=SYM\|Type=o`, `Case=Gen\|NumType=Frac\|Number=Sing\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Sup\|NumType=Card\|Number=Sing\|POS=NUM`, `Case=Nom\|NumType[sem]=Signed\|Number=Sing\|POS=NUM`, `Case=Com\|Number=Sing\|POS=PROPN`, `Case=Acc\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Tot`, `Case=Ins\|Number=Sing\|Number[psed]=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Ill\|Number=Plur\|POS=PRON\|Person=1\|Reflexive=Yes`, `Case=Nom\|Number=Plur\|Number[psed]=Sing\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Ins\|Degree=Pos\|Number=Sing\|Number[psor]=Sing\|POS=ADJ\|Person[psor]=3`, `Case=Gen\|NumType=Dist\|Number=Sing\|POS=NUM`, `Case=Nom\|NumType[sem]=Formula\|Number=Sing\|POS=NUM`, `Case=Del\|Number=Sing\|POS=SYM\|Type=w`, `Case=Ade\|Number=Sing\|Number[psor]=Plur\|POS=PRON\|Person=3\|Person[psor]=1\|Poss=Yes\|PronType=Prs`, `Case=Ins\|Degree=Sup\|Number=Sing\|POS=ADJ`, `Case=Nom\|Number=Sing\|Number[psor]=Plur\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Rel`, `Case=Ine\|Number=Plur\|Number[psed]=Sing\|POS=NOUN`, `Case=Nom\|Degree=Pos\|Number=Sing\|Number[psor]=Plur\|POS=ADJ\|Person[psor]=3`, `Case=Ade\|Number=Plur\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Acc\|Number=Sing\|POS=SYM\|Type=o`, `Case=Ins\|NumType=Frac\|Number=Sing\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Ela\|Number=Sing\|POS=SYM\|Type=o`, `Case=Dat\|Degree=Pos\|Number=Plur\|Number[psor]=Sing\|POS=ADJ\|Person[psor]=3`, `Case=All\|Number=Plur\|Number[psed]=Sing\|POS=SYM\|Type=w`, `Case=Ade\|Number=Sing\|POS=SYM\|Type=w`, `Case=Sbl\|Number=Sing\|POS=SYM\|Type=w`, `Case=Ade\|NumType=Card\|Number=Sing\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Ill\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Ind`, `Case=Ine\|Number=Sing\|Number[psor]=Sing\|POS=PROPN\|Person[psor]=3`, `Case=Acc\|NumType=Card\|Number=Plur\|POS=NUM`, `Case=Ill\|Degree=Sup\|Number=Sing\|POS=ADJ`, `Case=Acc\|Degree=Sup\|Number=Sing\|Number[psor]=Sing\|POS=ADJ\|Person[psor]=3`, `Case=Sup\|NumType=Card\|Number=Sing\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Dat\|Number=Sing\|Number[psed]=Sing\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Ine\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Tot`, `Case=Ill\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=3`, `Case=Sup\|Number=Sing\|POS=SYM\|Type=w`, `Case=Ine\|Degree=Pos\|Number=Plur\|POS=ADJ`, `Case=Gen\|Degree=Pos\|Number=Plur\|Number[psor]=Sing\|POS=ADJ\|Person[psor]=3`, `Case=Ins\|NumType=Frac\|Number=Sing\|POS=NUM`, `Case=Ela\|Number=Sing\|POS=SYM\|Type=w`, `Case=Sbl\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Ind`, `Case=Nom\|Number=Sing\|POS=SYM\|Type=p`, `Case=Abl\|Number=Plur\|Number[psed]=Sing\|POS=NOUN`, `Case=Nom\|NumType[sem]=Measure\|Number=Sing\|POS=NUM`, `Case=Abs\|Number=Sing\|POS=PROPN`, `Case=Ins\|Number=Sing\|Number[psor]=Plur\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Ind`, `Case=Nom\|Number=Sing\|Number[psed]=Plur\|POS=NOUN`, `Case=Nom\|Number=Sing\|POS=SYM\|Type=m`, `Case=Acc\|Number=Sing\|POS=SYM\|Type=m`, `Case=Sup\|Number=Sing\|Number[psed]=Sing\|POS=PROPN`, `Case=Ine\|Number=Plur\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Nom\|Number=Sing\|Number[psed]=Sing\|POS=SYM\|Type=o`, `Case=Ins\|Number=Sing\|POS=SYM\|Type=o`, `Case=Ins\|Number=Sing\|POS=SYM\|Type=w`, `Case=Dat\|Number=Plur\|POS=PRON\|Person=3\|PronType=Int`, `Case=Acc\|Number=Sing\|Number[psed]=Plur\|POS=NOUN`, `Case=Gen\|NumType=Ord\|Number=Sing\|POS=ADJ`, `Case=Gen\|Number=Plur\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Sbl\|Number=Plur\|POS=PRON\|Person=3\|PronType=Int`, `Case=Abl\|Number=Sing\|Number[psed]=Sing\|POS=PROPN`, `Case=Acc\|Degree=Pos\|Number=Plur\|Number[psor]=Sing\|POS=ADJ\|Person[psor]=3`, `Case=Abs\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Ind`, `Case=Ill\|Number=Sing\|POS=SYM\|Type=w`, `Case=Ela\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Abl\|NumType[sem]=Time\|Number=Sing\|POS=NUM`, `Case=Gen\|Degree=Sup\|Number=Sing\|Number[psor]=Sing\|POS=ADJ\|Person[psor]=3`, `Case=Abs\|Number=Sing\|Number[psor]=Plur\|POS=PRON\|Person=3\|Person[psor]=3\|Poss=Yes\|PronType=Prs`, `Case=Sup\|Degree=Cmp\|Number=Sing\|POS=ADJ`, `Case=Gen\|Degree=Cmp\|Number=Sing\|POS=ADJ`, `Case=Gen\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Tot`, `Case=Ins\|Number=Sing\|Number[psor]=Plur\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Tot`, `Case=Sup\|NumType=Frac\|Number=Sing\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Abs\|Degree=Pos\|Number=Sing\|Number[psor]=Sing\|POS=ADJ\|Person[psor]=3`, `Case=Acc\|Degree=Pos\|Number=Sing\|Number[psor]=Sing\|POS=ADJ\|Person[psor]=3`, `Case=Acc\|NumType[sem]=Percent\|Number=Sing\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Ter\|NumType[sem]=Percent\|Number=Sing\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Dat\|Number=Sing\|Number[psed]=Sing\|POS=NOUN`, `Case=Nom\|NumType[sem]=Percent\|Number=Sing\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Acc\|NumType[sem]=Percent\|Number=Sing\|POS=NUM`, `Case=Ter\|NumType=Frac\|Number=Sing\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Ade\|NumType[sem]=Percent\|Number=Sing\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Ins\|NumType[sem]=Percent\|Number=Sing\|POS=NUM`, `Case=Ins\|NumType[sem]=Percent\|Number=Sing\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Gen\|NumType[sem]=Percent\|Number=Sing\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Dat\|NumType[sem]=Percent\|Number=Sing\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Sbl\|NumType[sem]=Percent\|Number=Sing\|POS=NUM`, `Case=Ine\|NumType[sem]=Percent\|Number=Sing\|POS=NUM`, `Case=All\|NumType=Frac\|Number=Sing\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Ade\|NumType=Frac\|Number=Sing\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Nom\|NumType[sem]=Percent\|Number=Sing\|POS=NUM`, `Case=All\|NumType[sem]=Percent\|Number=Sing\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Abl\|NumType=Card\|Number=Sing\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Ter\|NumType=Card\|Number=Sing\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Acc\|NumType=Card\|Number=Sing\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Ter\|NumType[sem]=Formula\|Number=Sing\|POS=NUM`, `Case=Sbl\|NumType[sem]=Percent\|Number=Sing\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=All\|Number=Plur\|POS=PRON\|Person=3\|PronType=Int`, `Case=Nom\|Number=Plur\|Number[psor]=Sing\|POS=PROPN\|Person[psor]=3`, `Case=Del\|NumType=Frac\|Number=Sing\|POS=NUM`, `Case=Cau\|NumType=Frac\|Number=Sing\|POS=NUM`, `Case=Gen\|Number=Plur\|Number[psor]=Sing\|POS=PROPN\|Person[psor]=3`, `Case=Ins\|NumType=Ord\|Number=Sing\|Number[psor]=Sing\|POS=ADJ\|Person[psor]=3`, `Case=Ade\|NumType=Frac\|Number=Sing\|Number[psor]=Plur\|POS=NUM\|Person[psor]=3`, `Case=Ine\|NumType=Frac\|Number=Sing\|Number[psor]=Plur\|POS=NUM\|Person[psor]=3`, `Case=Acc\|Number=Sing\|Number[psor]=Plur\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Ind`, `Case=Sup\|NumType=Card\|Number=Plur\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Tra\|Number=Sing\|Number[psed]=Sing\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Ine\|NumType=Card\|Number=Plur\|POS=NUM`, `Case=Gen\|Number=Sing\|Number[psed]=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Tra\|Number=Sing\|Number[psed]=Sing\|POS=NOUN`, `Case=Gen\|Number=Sing\|Number[psed]=Sing\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Nom\|Number=Sing\|Number[psed]=Sing\|Number[psor]=Sing\|POS=PROPN\|Person[psor]=3`, `Case=Gen\|Number=Sing\|Number[psed]=Sing\|POS=PRON\|Person=3\|PronType=Ind`, `Case=Tem\|Degree=Sup\|Number=Sing\|POS=ADJ`, `Case=Dat\|NumType[sem]=Dot\|Number=Sing\|POS=NUM`, `Case=Sbl\|NumType=Card\|Number=Plur\|POS=NUM`, `Case=All\|Number=Sing\|Number[psed]=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Ine\|NumType=Frac\|Number=Sing\|POS=NUM`, `Case=All\|Degree=Cmp\|Number=Sing\|POS=ADJ`, `Case=Sbl\|Number=Plur\|POS=PROPN`, `Case=Tra\|Number=Sing\|POS=PRON\|Person=3\|PronType=Tot`, `Case=Sup\|NumType=Frac\|Number=Sing\|POS=NUM`, `Case=Dat\|Number=Plur\|Number[psed]=Sing\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Dat\|Number=Sing\|POS=SYM\|Type=w`, `Case=Ill\|Number=Plur\|POS=PROPN`, `Case=Loc\|Number=Sing\|POS=PROPN`, `Case=Ess\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rel`, `Case=Acc\|Degree=Pos\|Number=Plur\|Number[psed]=Sing\|POS=ADJ`, `Case=Abl\|Degree=Cmp\|Number=Sing\|POS=ADJ`, `Case=All\|NumType=Frac\|Number=Sing\|POS=NUM`, `Case=Ade\|Degree=Cmp\|Number=Plur\|POS=ADJ`, `Case=Ine\|NumType=Ord\|Number=Sing\|POS=ADJ`, `Case=Ine\|Number=Sing\|POS=SYM\|Type=w`, `Case=Cau\|NumType=Frac\|Number=Sing\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Ela\|Number=Sing\|Number[psor]=Sing\|POS=PROPN\|Person[psor]=3`, `Case=Abs\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rel`, `Case=Sbl\|NumType[sem]=Dot\|Number=Sing\|POS=NUM`, `Case=Tem\|Number=Sing\|POS=PROPN`, `Case=Del\|NumType[sem]=Dot\|Number=Sing\|POS=NUM`, `Case=Ade\|Number=Sing\|Number[psor]=Sing\|POS=PROPN\|Person[psor]=3`, `Case=Ine\|Number=Sing\|Number[psor]=Plur\|POS=PROPN\|Person[psor]=1`, `Case=Nom\|Number=Sing\|Number[psed]=Sing\|POS=PRON\|Person=3\|PronType=Tot`, `Case=Acc\|Degree=Sup\|Number=Plur\|Number[psor]=Sing\|POS=ADJ\|Person[psor]=3`, `Case=Ade\|Number=Plur\|Number[psed]=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=3`, `Case=Ela\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Case=Acc\|Number=Plur\|Number[psed]=Plur\|POS=PRON\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Del\|Number=Plur\|Number[psed]=Sing\|POS=NOUN`, `Case=Nom\|Degree=Sup\|Number=Sing\|Number[psor]=Sing\|POS=ADJ\|Person[psor]=3`, `Case=Dat\|Number=Plur\|POS=PROPN`, `Case=Ill\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Sbl\|NumType=Card\|Number=Sing\|Number[psor]=Plur\|POS=NUM\|Person[psor]=3`, `Case=Ins\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=1\|Poss=Yes\|PronType=Prs`, `Case=Dat\|Number=Plur\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=2`, `Case=Ter\|Number=Plur\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Case=Ess\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=2`, `Case=Sup\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=2`, `Case=Acc\|Number=Sing\|Number[psor]=Plur\|POS=PRON\|Person=3\|Person[psor]=2\|PronType=Tot`, `Case=Gen\|NumType=Card\|Number=Sing\|Number[psor]=Plur\|POS=NUM\|Person[psor]=3`, `Case=Ine\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Int`, `Case=All\|Number=Sing\|Number[psor]=Sing\|POS=PROPN\|Person[psor]=3`, `Case=Dat\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=2`, `Case=Gen\|Number=Sing\|POS=PRON\|Person=3\|PronType=Rcp`, `Definite=Ind\|Mood=Imp\|Number=Sing\|POS=AUX\|Person=3\|Tense=Pres\|Voice=Act`, `Case=Tra\|Number=Sing\|Number[psor]=Plur\|POS=NOUN\|Person[psor]=1`, `Case=Ins\|NumType=Card\|Number=Plur\|Number[psor]=Sing\|POS=NUM\|Person[psor]=3`, `Case=Del\|Number=Sing\|POS=PRON\|Person=2\|Reflexive=Yes`, `Case=Sbl\|NumType=Card\|Number=Sing\|Number[psor]=Plur\|POS=NUM\|Person[psor]=1`, `Case=Dat\|Number=Sing\|Number[psor]=Plur\|POS=PRON\|Person=3\|Person[psor]=2\|PronType=Ind`, `Case=All\|Number=Sing\|POS=PRON\|Person=2\|Poss=Yes\|PronType=Prs`, `Case=Sbl\|Number=Sing\|Number[psed]=Sing\|POS=PROPN`, `Case=Ill\|Number=Sing\|Number[psed]=Sing\|POS=PROPN`, `Case=Ine\|NumType=Card\|Number=Sing\|Number[psor]=Plur\|POS=NUM\|Person[psor]=3`, `Case=Del\|Number=Sing\|POS=PRON\|Person=2\|PronType=Prs`, `Case=Acc\|Number=Sing\|Number[psed]=Sing\|Number[psor]=Plur\|POS=PRON\|Person=3\|Person[psor]=2\|PronType=Tot`, `Case=Abl\|Number=Sing\|Number[psor]=Plur\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Int`, `Case=Ine\|Number=Sing\|Number[psed]=Sing\|POS=PROPN`, `Case=Cau\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=2`, `Case=Del\|Number=Plur\|Number[psed]=Sing\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Cau\|Number=Sing\|POS=PRON\|Person=3\|Reflexive=Yes`, `Case=Nom\|NumType=Card\|Number=Sing\|Number[psor]=Plur\|POS=NUM\|Person[psor]=2`, `Case=Abl\|Number=Sing\|Number[psor]=Sing\|POS=NOUN\|Person[psor]=2`, `Case=Ine\|Degree=Cmp\|Number=Sing\|POS=ADJ`, `Definite=2\|Mood=Imp\|Number=Sing\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `Case=Dat\|Number=Sing\|Number[psor]=Plur\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Tot`, `Case=Ela\|Degree=Cmp\|Number=Sing\|POS=ADJ`, `Case=Acc\|Number=Sing\|POS=SYM\|Type=p`, `Case=Abl\|NumType=Ord\|Number=Sing\|POS=ADJ`, `Case=Acc\|Number=Plur\|Number[psed]=Sing\|POS=PRON\|Person=3\|PronType=Dem`, `Case=Ine\|Number=Plur\|POS=PROPN`, `Case=Sbl\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Person[psor]=3\|PronType=Tot`, `Case=Ins\|Number=Sing\|Number[psor]=Plur\|POS=PRON\|Person=3\|Person[psor]=3\|Poss=Yes\|PronType=Prs`, `Case=Ter\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Case=Dat\|Number=Plur\|POS=PRON\|Person=1\|PronType=Prs`, `Case=Acc\|Number=Plur\|Number[psor]=Sing\|POS=PROPN\|Person[psor]=3`, `Case=All\|Number=Sing\|Number[psed]=Sing\|POS=PRON\|Person=3\|PronType=Tot` |
-| **`parser`** | `ROOT`, `acl`, `advcl`, `advmod`, `advmod:locy`, `advmod:mode`, `advmod:que`, `advmod:tfrom`, `advmod:tlocy`, `advmod:to`, `advmod:tto`, `amod:att`, `appos`, `aux`, `case`, `cc`, `ccomp`, `ccomp:obj`, `ccomp:obl`, `ccomp:pred`, `compound`, `compound:preverb`, `conj`, `cop`, `csubj`, `dep`, `det`, `flat:name`, `iobj`, `list`, `mark`, `nmod`, `nmod:att`, `nmod:obl`, `nsubj`, `nummod`, `obj`, `obj:lvc`, `obl`, `orphan`, `parataxis`, `punct`, `xcomp` |
-| **`ner`** | `LOC`, `MISC`, `ORG`, `PER` |
-
-</details>
-
-### Accuracy
-
-| Type | Score |
-| --- | --- |
-| `TOKEN_ACC` | 99.99 |
-| `TOKEN_P` | 99.86 |
-| `TOKEN_R` | 99.93 |
-| `TOKEN_F` | 99.89 |
-| `SENTS_P` | 97.11 |
-| `SENTS_R` | 97.33 |
-| `SENTS_F` | 97.22 |
-| `TAG_ACC` | 96.96 |
-| `POS_ACC` | 96.89 |
-| `MORPH_ACC` | 94.51 |
-| `MORPH_MICRO_P` | 97.64 |
-| `MORPH_MICRO_R` | 96.84 |
-| `MORPH_MICRO_F` | 97.24 |
-| `LEMMA_ACC` | 97.45 |
-| `DEP_UAS` | 80.90 |
-| `DEP_LAS` | 73.69 |
-| `ENTS_P` | 84.41 |
-| `ENTS_R` | 83.68 |
-| `ENTS_F` | 84.05 |

config.cfg

@@ -1,8 +1,8 @@
 [paths]
-parser_model = "models/hu_core_news_md-parser-3.7.0/model-best"
-ner_model = "models/hu_core_news_md-ner-3.7.0/model-best"
-lemmatizer_lookups = "models/hu_core_news_md-lookup-lemmatizer-3.7.0"
-tagger_model = "models/hu_core_news_md-tagger-3.7.0/model-best"
+parser_model = "models/hu_core_news_md-parser-3.8.0/model-best"
+ner_model = "models/hu_core_news_md-ner-3.8.0/model-best"
+lemmatizer_lookups = "models/hu_core_news_md-lookup-lemmatizer-3.8.0"
+tagger_model = "models/hu_core_news_md-tagger-3.8.0/model-best"
 train = null
 dev = null
 vectors = null

edit_tree_lemmatizer.py

@@ -1,465 +1,465 @@
-from functools import lru_cache
-
-from typing import cast, Any, Callable, Dict, Iterable, List, Optional
-from typing import Sequence, Tuple, Union
-from collections import Counter
-from copy import deepcopy
-from itertools import islice
-import numpy as np
-
-import srsly
-from thinc.api import Config, Model, SequenceCategoricalCrossentropy, NumpyOps
-from thinc.types import Floats2d, Ints2d
-
-from spacy.pipeline._edit_tree_internals.edit_trees import EditTrees
-from spacy.pipeline._edit_tree_internals.schemas import validate_edit_tree
-from spacy.pipeline.lemmatizer import lemmatizer_score
-from spacy.pipeline.trainable_pipe import TrainablePipe
-from spacy.errors import Errors
-from spacy.language import Language
-from spacy.tokens import Doc, Token
-from spacy.training import Example, validate_examples, validate_get_examples
-from spacy.vocab import Vocab
-from spacy import util
-
-
-TOP_K_GUARDRAIL = 20
-
-
-default_model_config = """
-[model]
-@architectures = "spacy.Tagger.v2"
-
-[model.tok2vec]
-@architectures = "spacy.HashEmbedCNN.v2"
-pretrained_vectors = null
-width = 96
-depth = 4
-embed_size = 2000
-window_size = 1
-maxout_pieces = 3
-subword_features = true
-"""
-DEFAULT_EDIT_TREE_LEMMATIZER_MODEL = Config().from_str(default_model_config)["model"]
-
-
-@Language.factory(
-    "trainable_lemmatizer_v2",
-    assigns=["token.lemma"],
-    requires=[],
-    default_config={
-        "model": DEFAULT_EDIT_TREE_LEMMATIZER_MODEL,
-        "backoff": "orth",
-        "min_tree_freq": 3,
-        "overwrite": False,
-        "top_k": 1,
-        "overwrite_labels": True,
-        "scorer": {"@scorers": "spacy.lemmatizer_scorer.v1"},
-    },
-    default_score_weights={"lemma_acc": 1.0},
-)
-def make_edit_tree_lemmatizer(
-    nlp: Language,
-    name: str,
-    model: Model,
-    backoff: Optional[str],
-    min_tree_freq: int,
-    overwrite: bool,
-    top_k: int,
-    overwrite_labels: bool,
-    scorer: Optional[Callable],
-):
-    """Construct an EditTreeLemmatizer component."""
-    return EditTreeLemmatizer(
-        nlp.vocab,
-        model,
-        name,
-        backoff=backoff,
-        min_tree_freq=min_tree_freq,
-        overwrite=overwrite,
-        top_k=top_k,
-        overwrite_labels=overwrite_labels,
-        scorer=scorer,
-    )
-
-
-# _f = open("lemmatizer.log", "w")
-# def debug(*args):
-#     _f.write(" ".join(args) + "\n")
-def debug(*args):
-    pass
-
-
-class EditTreeLemmatizer(TrainablePipe):
-    """
-    Lemmatizer that lemmatizes each word using a predicted edit tree.
-    """
-
-    def __init__(
-        self,
-        vocab: Vocab,
-        model: Model,
-        name: str = "trainable_lemmatizer",
-        *,
-        backoff: Optional[str] = "orth",
-        min_tree_freq: int = 3,
-        overwrite: bool = False,
-        top_k: int = 1,
-        overwrite_labels,
-        scorer: Optional[Callable] = lemmatizer_score,
-    ):
-        """
-        Construct an edit tree lemmatizer.
-
-        backoff (Optional[str]): backoff to use when the predicted edit trees
-            are not applicable. Must be an attribute of Token or None (leave the
-            lemma unset).
-        min_tree_freq (int): prune trees that are applied less than this
-            frequency in the training data.
-        overwrite (bool): overwrite existing lemma annotations.
-        top_k (int): try to apply at most the k most probable edit trees.
-        """
-        self.vocab = vocab
-        self.model = model
-        self.name = name
-        self.backoff = backoff
-        self.min_tree_freq = min_tree_freq
-        self.overwrite = overwrite
-        self.top_k = top_k
-        self.overwrite_labels = overwrite_labels
-
-        self.trees = EditTrees(self.vocab.strings)
-        self.tree2label: Dict[int, int] = {}
-
-        self.cfg: Dict[str, Any] = {"labels": []}
-        self.scorer = scorer
-        self.numpy_ops = NumpyOps()
-
-    def get_loss(
-        self, examples: Iterable[Example], scores: List[Floats2d]
-    ) -> Tuple[float, List[Floats2d]]:
-        validate_examples(examples, "EditTreeLemmatizer.get_loss")
-        loss_func = SequenceCategoricalCrossentropy(normalize=False, missing_value=-1)
-
-        truths = []
-        for eg in examples:
-            eg_truths = []
-            for (predicted, gold_lemma, gold_pos, gold_sent_start) in zip(
-                eg.predicted,
-                eg.get_aligned("LEMMA", as_string=True),
-                eg.get_aligned("POS", as_string=True),
-                eg.get_aligned_sent_starts(),
-            ):
-                if gold_lemma is None:
-                    label = -1
-                else:
-                    form = self._get_true_cased_form(
-                        predicted.text, gold_sent_start, gold_pos
-                    )
-                    tree_id = self.trees.add(form, gold_lemma)
-                    # debug(f"@get_loss: {predicted}/{gold_pos}[{gold_sent_start}]->{form}|{gold_lemma}[{tree_id}]")
-                    label = self.tree2label.get(tree_id, 0)
-                eg_truths.append(label)
-
-            truths.append(eg_truths)
-
-        d_scores, loss = loss_func(scores, truths)
-        if self.model.ops.xp.isnan(loss):
-            raise ValueError(Errors.E910.format(name=self.name))
-
-        return float(loss), d_scores
-
-    def predict(self, docs: Iterable[Doc]) -> List[Ints2d]:
-        if self.top_k == 1:
-            scores2guesses = self._scores2guesses_top_k_equals_1
-        elif self.top_k <= TOP_K_GUARDRAIL:
-            scores2guesses = self._scores2guesses_top_k_greater_1
-        else:
-            scores2guesses = self._scores2guesses_top_k_guardrail
-        # The behaviour of *_scores2guesses_top_k_greater_1()* is efficient for values
-        # of *top_k>1* that are likely to be useful when the edit tree lemmatizer is used
-        # for its principal purpose of lemmatizing tokens. However, the code could also
-        # be used for other purposes, and with very large values of *top_k* the method
-        # becomes inefficient. In such cases, *_scores2guesses_top_k_guardrail()* is used
-        # instead.
-        n_docs = len(list(docs))
-        if not any(len(doc) for doc in docs):
-            # Handle cases where there are no tokens in any docs.
-            n_labels = len(self.cfg["labels"])
-            guesses: List[Ints2d] = [self.model.ops.alloc2i(0, n_labels) for _ in docs]
-            assert len(guesses) == n_docs
-            return guesses
-        scores = self.model.predict(docs)
-        assert len(scores) == n_docs
-        guesses = scores2guesses(docs, scores)
-        assert len(guesses) == n_docs
-        return guesses
-
-    def _scores2guesses_top_k_equals_1(self, docs, scores):
-        guesses = []
-        for doc, doc_scores in zip(docs, scores):
-            doc_guesses = doc_scores.argmax(axis=1)
-            doc_guesses = self.numpy_ops.asarray(doc_guesses)
-
-            doc_compat_guesses = []
-            for i, token in enumerate(doc):
-                tree_id = self.cfg["labels"][doc_guesses[i]]
-                form: str = self._get_true_cased_form_of_token(token)
-                if self.trees.apply(tree_id, form) is not None:
-                    doc_compat_guesses.append(tree_id)
-                else:
-                    doc_compat_guesses.append(-1)
-            guesses.append(np.array(doc_compat_guesses))
-
-        return guesses
-
-    def _scores2guesses_top_k_greater_1(self, docs, scores):
-        guesses = []
-        top_k = min(self.top_k, len(self.labels))
-        for doc, doc_scores in zip(docs, scores):
-            doc_scores = self.numpy_ops.asarray(doc_scores)
-            doc_compat_guesses = []
-            for i, token in enumerate(doc):
-                for _ in range(top_k):
-                    candidate = int(doc_scores[i].argmax())
-                    candidate_tree_id = self.cfg["labels"][candidate]
-                    form: str = self._get_true_cased_form_of_token(token)
-                    if self.trees.apply(candidate_tree_id, form) is not None:
-                        doc_compat_guesses.append(candidate_tree_id)
-                        break
-                    doc_scores[i, candidate] = np.finfo(np.float32).min
-                else:
-                    doc_compat_guesses.append(-1)
-            guesses.append(np.array(doc_compat_guesses))
-
-        return guesses
-
-    def _scores2guesses_top_k_guardrail(self, docs, scores):
-        guesses = []
-        for doc, doc_scores in zip(docs, scores):
-            doc_guesses = np.argsort(doc_scores)[..., : -self.top_k - 1 : -1]
-            doc_guesses = self.numpy_ops.asarray(doc_guesses)
-
-            doc_compat_guesses = []
-            for token, candidates in zip(doc, doc_guesses):
-                tree_id = -1
-                for candidate in candidates:
-                    candidate_tree_id = self.cfg["labels"][candidate]
-
-                    form: str = self._get_true_cased_form_of_token(token)
-
-                    if self.trees.apply(candidate_tree_id, form) is not None:
-                        tree_id = candidate_tree_id
-                        break
-                doc_compat_guesses.append(tree_id)
-
-            guesses.append(np.array(doc_compat_guesses))
-
-        return guesses
-
-    def set_annotations(self, docs: Iterable[Doc], batch_tree_ids):
-        for i, doc in enumerate(docs):
-            doc_tree_ids = batch_tree_ids[i]
-            if hasattr(doc_tree_ids, "get"):
-                doc_tree_ids = doc_tree_ids.get()
-            for j, tree_id in enumerate(doc_tree_ids):
-                if self.overwrite or doc[j].lemma == 0:
-                    # If no applicable tree could be found during prediction,
-                    # the special identifier -1 is used. Otherwise the tree
-                    # is guaranteed to be applicable.
-                    if tree_id == -1:
-                        if self.backoff is not None:
-                            doc[j].lemma = getattr(doc[j], self.backoff)
-                    else:
-                        form = self._get_true_cased_form_of_token(doc[j])
-                        lemma = self.trees.apply(tree_id, form) or form
-                        # debug(f"@set_annotations: {doc[j]}/{doc[j].pos_}[{doc[j].is_sent_start}]->{form}|{lemma}[{tree_id}]")
-                        doc[j].lemma_ = lemma
-
-    @property
-    def labels(self) -> Tuple[int, ...]:
-        """Returns the labels currently added to the component."""
-        return tuple(self.cfg["labels"])
-
-    @property
-    def hide_labels(self) -> bool:
-        return True
-
-    @property
-    def label_data(self) -> Dict:
-        trees = []
-        for tree_id in range(len(self.trees)):
-            tree = self.trees[tree_id]
-            if "orig" in tree:
-                tree["orig"] = self.vocab.strings[tree["orig"]]
-            if "subst" in tree:
-                tree["subst"] = self.vocab.strings[tree["subst"]]
-            trees.append(tree)
-        return dict(trees=trees, labels=tuple(self.cfg["labels"]))
-
-    def initialize(
-        self,
-        get_examples: Callable[[], Iterable[Example]],
-        *,
-        nlp: Optional[Language] = None,
-        labels: Optional[Dict] = None,
-    ):
-        validate_get_examples(get_examples, "EditTreeLemmatizer.initialize")
-
-        if self.overwrite_labels:
-            if labels is None:
-                self._labels_from_data(get_examples)
-            else:
-                self._add_labels(labels)
-
-        # Sample for the model.
-        doc_sample = []
-        label_sample = []
-        for example in islice(get_examples(), 10):
-            doc_sample.append(example.x)
-            gold_labels: List[List[float]] = []
-            for token in example.reference:
-                if token.lemma == 0:
-                    gold_label = None
-                else:
-                    gold_label = self._pair2label(token.text, token.lemma_)
-
-                gold_labels.append(
-                    [
-                        1.0 if label == gold_label else 0.0
-                        for label in self.cfg["labels"]
-                    ]
-                )
-
-            gold_labels = cast(Floats2d, gold_labels)
-            label_sample.append(self.model.ops.asarray(gold_labels, dtype="float32"))
-
-        self._require_labels()
-        assert len(doc_sample) > 0, Errors.E923.format(name=self.name)
-        assert len(label_sample) > 0, Errors.E923.format(name=self.name)
-
-        self.model.initialize(X=doc_sample, Y=label_sample)
-
-    def from_bytes(self, bytes_data, *, exclude=tuple()):
-        deserializers = {
-            "cfg": lambda b: self.cfg.update(srsly.json_loads(b)),
-            "model": lambda b: self.model.from_bytes(b),
-            "vocab": lambda b: self.vocab.from_bytes(b, exclude=exclude),
-            "trees": lambda b: self.trees.from_bytes(b),
-        }
-
-        util.from_bytes(bytes_data, deserializers, exclude)
-
-        return self
-
-    def to_bytes(self, *, exclude=tuple()):
-        serializers = {
-            "cfg": lambda: srsly.json_dumps(self.cfg),
-            "model": lambda: self.model.to_bytes(),
-            "vocab": lambda: self.vocab.to_bytes(exclude=exclude),
-            "trees": lambda: self.trees.to_bytes(),
-        }
-
-        return util.to_bytes(serializers, exclude)
-
-    def to_disk(self, path, exclude=tuple()):
-        path = util.ensure_path(path)
-        serializers = {
-            "cfg": lambda p: srsly.write_json(p, self.cfg),
-            "model": lambda p: self.model.to_disk(p),
-            "vocab": lambda p: self.vocab.to_disk(p, exclude=exclude),
-            "trees": lambda p: self.trees.to_disk(p),
-        }
-        util.to_disk(path, serializers, exclude)
-
-    def from_disk(self, path, exclude=tuple()):
-        def load_model(p):
-            try:
-                with open(p, "rb") as mfile:
-                    self.model.from_bytes(mfile.read())
-            except AttributeError:
-                raise ValueError(Errors.E149) from None
-
-        deserializers = {
-            "cfg": lambda p: self.cfg.update(srsly.read_json(p)),
-            "model": load_model,
-            "vocab": lambda p: self.vocab.from_disk(p, exclude=exclude),
-            "trees": lambda p: self.trees.from_disk(p),
-        }
-
-        util.from_disk(path, deserializers, exclude)
-        return self
-
-    def _add_labels(self, labels: Dict):
-        if "labels" not in labels:
-            raise ValueError(Errors.E857.format(name="labels"))
-        if "trees" not in labels:
-            raise ValueError(Errors.E857.format(name="trees"))
-
-        self.cfg["labels"] = list(labels["labels"])
-        trees = []
-        for tree in labels["trees"]:
-            errors = validate_edit_tree(tree)
-            if errors:
-                raise ValueError(Errors.E1026.format(errors="\n".join(errors)))
-
-            tree = dict(tree)
-            if "orig" in tree:
-                tree["orig"] = self.vocab.strings[tree["orig"]]
-            if "orig" in tree:
-                tree["subst"] = self.vocab.strings[tree["subst"]]
-
-            trees.append(tree)
-
-        self.trees.from_json(trees)
-
-        for label, tree in enumerate(self.labels):
-            self.tree2label[tree] = label
-
-    def _labels_from_data(self, get_examples: Callable[[], Iterable[Example]]):
-        # Count corpus tree frequencies in ad-hoc storage to avoid cluttering
-        # the final pipe/string store.
-        vocab = Vocab()
-        trees = EditTrees(vocab.strings)
-        tree_freqs: Counter = Counter()
-        repr_pairs: Dict = {}
-        for example in get_examples():
-            for token in example.reference:
-                if token.lemma != 0:
-                    form = self._get_true_cased_form_of_token(token)
-                    # debug("_labels_from_data", str(token) + "->" + form, token.lemma_)
-                    tree_id = trees.add(form, token.lemma_)
-                    tree_freqs[tree_id] += 1
-                    repr_pairs[tree_id] = (form, token.lemma_)
-
-        # Construct trees that make the frequency cut-off using representative
-        # form - token pairs.
-        for tree_id, freq in tree_freqs.items():
-            if freq >= self.min_tree_freq:
-                form, lemma = repr_pairs[tree_id]
-                self._pair2label(form, lemma, add_label=True)
-
-    @lru_cache()
-    def _get_true_cased_form(self, token: str, is_sent_start: bool, pos: str) -> str:
-        if is_sent_start and pos != "PROPN":
-            return token.lower()
-        else:
-            return token
-
-    def _get_true_cased_form_of_token(self, token: Token) -> str:
-        return self._get_true_cased_form(token.text, token.is_sent_start, token.pos_)
-
-    def _pair2label(self, form, lemma, add_label=False):
-        """
-        Look up the edit tree identifier for a form/label pair. If the edit
-        tree is unknown and "add_label" is set, the edit tree will be added to
-        the labels.
-        """
-        tree_id = self.trees.add(form, lemma)
-        if tree_id not in self.tree2label:
-            if not add_label:
-                return None
-
-            self.tree2label[tree_id] = len(self.cfg["labels"])
-            self.cfg["labels"].append(tree_id)
-        return self.tree2label[tree_id]
+from functools import lru_cache
+
+from typing import cast, Any, Callable, Dict, Iterable, List, Optional
+from typing import Sequence, Tuple, Union
+from collections import Counter
+from copy import deepcopy
+from itertools import islice
+import numpy as np
+
+import srsly
+from thinc.api import Config, Model, SequenceCategoricalCrossentropy, NumpyOps
+from thinc.types import Floats2d, Ints2d
+
+from spacy.pipeline._edit_tree_internals.edit_trees import EditTrees
+from spacy.pipeline._edit_tree_internals.schemas import validate_edit_tree
+from spacy.pipeline.lemmatizer import lemmatizer_score
+from spacy.pipeline.trainable_pipe import TrainablePipe
+from spacy.errors import Errors
+from spacy.language import Language
+from spacy.tokens import Doc, Token
+from spacy.training import Example, validate_examples, validate_get_examples
+from spacy.vocab import Vocab
+from spacy import util
+
+
+TOP_K_GUARDRAIL = 20
+
+
+default_model_config = """
+[model]
+@architectures = "spacy.Tagger.v2"
+
+[model.tok2vec]
+@architectures = "spacy.HashEmbedCNN.v2"
+pretrained_vectors = null
+width = 96
+depth = 4
+embed_size = 2000
+window_size = 1
+maxout_pieces = 3
+subword_features = true
+"""
+DEFAULT_EDIT_TREE_LEMMATIZER_MODEL = Config().from_str(default_model_config)["model"]
+
+
+@Language.factory(
+    "trainable_lemmatizer_v2",
+    assigns=["token.lemma"],
+    requires=[],
+    default_config={
+        "model": DEFAULT_EDIT_TREE_LEMMATIZER_MODEL,
+        "backoff": "orth",
+        "min_tree_freq": 3,
+        "overwrite": False,
+        "top_k": 1,
+        "overwrite_labels": True,
+        "scorer": {"@scorers": "spacy.lemmatizer_scorer.v1"},
+    },
+    default_score_weights={"lemma_acc": 1.0},
+)
+def make_edit_tree_lemmatizer(
+    nlp: Language,
+    name: str,
+    model: Model,
+    backoff: Optional[str],
+    min_tree_freq: int,
+    overwrite: bool,
+    top_k: int,
+    overwrite_labels: bool,
+    scorer: Optional[Callable],
+):
+    """Construct an EditTreeLemmatizer component."""
+    return EditTreeLemmatizer(
+        nlp.vocab,
+        model,
+        name,
+        backoff=backoff,
+        min_tree_freq=min_tree_freq,
+        overwrite=overwrite,
+        top_k=top_k,
+        overwrite_labels=overwrite_labels,
+        scorer=scorer,
+    )
+
+
+# _f = open("lemmatizer.log", "w")
+# def debug(*args):
+#     _f.write(" ".join(args) + "\n")
+def debug(*args):
+    pass
+
+
+class EditTreeLemmatizer(TrainablePipe):
+    """
+    Lemmatizer that lemmatizes each word using a predicted edit tree.
+    """
+
+    def __init__(
+        self,
+        vocab: Vocab,
+        model: Model,
+        name: str = "trainable_lemmatizer",
+        *,
+        backoff: Optional[str] = "orth",
+        min_tree_freq: int = 3,
+        overwrite: bool = False,
+        top_k: int = 1,
+        overwrite_labels,
+        scorer: Optional[Callable] = lemmatizer_score,
+    ):
+        """
+        Construct an edit tree lemmatizer.
+
+        backoff (Optional[str]): backoff to use when the predicted edit trees
+            are not applicable. Must be an attribute of Token or None (leave the
+            lemma unset).
+        min_tree_freq (int): prune trees that are applied less than this
+            frequency in the training data.
+        overwrite (bool): overwrite existing lemma annotations.
+        top_k (int): try to apply at most the k most probable edit trees.
+        """
+        self.vocab = vocab
+        self.model = model
+        self.name = name
+        self.backoff = backoff
+        self.min_tree_freq = min_tree_freq
+        self.overwrite = overwrite
+        self.top_k = top_k
+        self.overwrite_labels = overwrite_labels
+
+        self.trees = EditTrees(self.vocab.strings)
+        self.tree2label: Dict[int, int] = {}
+
+        self.cfg: Dict[str, Any] = {"labels": []}
+        self.scorer = scorer
+        self.numpy_ops = NumpyOps()
+
+    def get_loss(
+        self, examples: Iterable[Example], scores: List[Floats2d]
+    ) -> Tuple[float, List[Floats2d]]:
+        validate_examples(examples, "EditTreeLemmatizer.get_loss")
+        loss_func = SequenceCategoricalCrossentropy(normalize=False, missing_value=-1)
+
+        truths = []
+        for eg in examples:
+            eg_truths = []
+            for (predicted, gold_lemma, gold_pos, gold_sent_start) in zip(
+                eg.predicted,
+                eg.get_aligned("LEMMA", as_string=True),
+                eg.get_aligned("POS", as_string=True),
+                eg.get_aligned_sent_starts(),
+            ):
+                if gold_lemma is None:
+                    label = -1
+                else:
+                    form = self._get_true_cased_form(
+                        predicted.text, gold_sent_start, gold_pos
+                    )
+                    tree_id = self.trees.add(form, gold_lemma)
+                    # debug(f"@get_loss: {predicted}/{gold_pos}[{gold_sent_start}]->{form}|{gold_lemma}[{tree_id}]")
+                    label = self.tree2label.get(tree_id, 0)
+                eg_truths.append(label)
+
+            truths.append(eg_truths)
+
+        d_scores, loss = loss_func(scores, truths)
+        if self.model.ops.xp.isnan(loss):
+            raise ValueError(Errors.E910.format(name=self.name))
+
+        return float(loss), d_scores
+
+    def predict(self, docs: Iterable[Doc]) -> List[Ints2d]:
+        if self.top_k == 1:
+            scores2guesses = self._scores2guesses_top_k_equals_1
+        elif self.top_k <= TOP_K_GUARDRAIL:
+            scores2guesses = self._scores2guesses_top_k_greater_1
+        else:
+            scores2guesses = self._scores2guesses_top_k_guardrail
+        # The behaviour of *_scores2guesses_top_k_greater_1()* is efficient for values
+        # of *top_k>1* that are likely to be useful when the edit tree lemmatizer is used
+        # for its principal purpose of lemmatizing tokens. However, the code could also
+        # be used for other purposes, and with very large values of *top_k* the method
+        # becomes inefficient. In such cases, *_scores2guesses_top_k_guardrail()* is used
+        # instead.
+        n_docs = len(list(docs))
+        if not any(len(doc) for doc in docs):
+            # Handle cases where there are no tokens in any docs.
+            n_labels = len(self.cfg["labels"])
+            guesses: List[Ints2d] = [self.model.ops.alloc2i(0, n_labels) for _ in docs]
+            assert len(guesses) == n_docs
+            return guesses
+        scores = self.model.predict(docs)
+        assert len(scores) == n_docs
+        guesses = scores2guesses(docs, scores)
+        assert len(guesses) == n_docs
+        return guesses
+
+    def _scores2guesses_top_k_equals_1(self, docs, scores):
+        guesses = []
+        for doc, doc_scores in zip(docs, scores):
+            doc_guesses = doc_scores.argmax(axis=1)
+            doc_guesses = self.numpy_ops.asarray(doc_guesses)
+
+            doc_compat_guesses = []
+            for i, token in enumerate(doc):
+                tree_id = self.cfg["labels"][doc_guesses[i]]
+                form: str = self._get_true_cased_form_of_token(token)
+                if self.trees.apply(tree_id, form) is not None:
+                    doc_compat_guesses.append(tree_id)
+                else:
+                    doc_compat_guesses.append(-1)
+            guesses.append(np.array(doc_compat_guesses))
+
+        return guesses
+
+    def _scores2guesses_top_k_greater_1(self, docs, scores):
+        guesses = []
+        top_k = min(self.top_k, len(self.labels))
+        for doc, doc_scores in zip(docs, scores):
+            doc_scores = self.numpy_ops.asarray(doc_scores)
+            doc_compat_guesses = []
+            for i, token in enumerate(doc):
+                for _ in range(top_k):
+                    candidate = int(doc_scores[i].argmax())
+                    candidate_tree_id = self.cfg["labels"][candidate]
+                    form: str = self._get_true_cased_form_of_token(token)
+                    if self.trees.apply(candidate_tree_id, form) is not None:
+                        doc_compat_guesses.append(candidate_tree_id)
+                        break
+                    doc_scores[i, candidate] = np.finfo(np.float32).min
+                else:
+                    doc_compat_guesses.append(-1)
+            guesses.append(np.array(doc_compat_guesses))
+
+        return guesses
+
+    def _scores2guesses_top_k_guardrail(self, docs, scores):
+        guesses = []
+        for doc, doc_scores in zip(docs, scores):
+            doc_guesses = np.argsort(doc_scores)[..., : -self.top_k - 1 : -1]
+            doc_guesses = self.numpy_ops.asarray(doc_guesses)
+
+            doc_compat_guesses = []
+            for token, candidates in zip(doc, doc_guesses):
+                tree_id = -1
+                for candidate in candidates:
+                    candidate_tree_id = self.cfg["labels"][candidate]
+
+                    form: str = self._get_true_cased_form_of_token(token)
+
+                    if self.trees.apply(candidate_tree_id, form) is not None:
+                        tree_id = candidate_tree_id
+                        break
+                doc_compat_guesses.append(tree_id)
+
+            guesses.append(np.array(doc_compat_guesses))
+
+        return guesses
+
+    def set_annotations(self, docs: Iterable[Doc], batch_tree_ids):
+        for i, doc in enumerate(docs):
+            doc_tree_ids = batch_tree_ids[i]
+            if hasattr(doc_tree_ids, "get"):
+                doc_tree_ids = doc_tree_ids.get()
+            for j, tree_id in enumerate(doc_tree_ids):
+                if self.overwrite or doc[j].lemma == 0:
+                    # If no applicable tree could be found during prediction,
+                    # the special identifier -1 is used. Otherwise the tree
+                    # is guaranteed to be applicable.
+                    if tree_id == -1:
+                        if self.backoff is not None:
+                            doc[j].lemma = getattr(doc[j], self.backoff)
+                    else:
+                        form = self._get_true_cased_form_of_token(doc[j])
+                        lemma = self.trees.apply(tree_id, form) or form
+                        # debug(f"@set_annotations: {doc[j]}/{doc[j].pos_}[{doc[j].is_sent_start}]->{form}|{lemma}[{tree_id}]")
+                        doc[j].lemma_ = lemma
+
+    @property
+    def labels(self) -> Tuple[int, ...]:
+        """Returns the labels currently added to the component."""
+        return tuple(self.cfg["labels"])
+
+    @property
+    def hide_labels(self) -> bool:
+        return True
+
+    @property
+    def label_data(self) -> Dict:
+        trees = []
+        for tree_id in range(len(self.trees)):
+            tree = self.trees[tree_id]
+            if "orig" in tree:
+                tree["orig"] = self.vocab.strings[tree["orig"]]
+            if "subst" in tree:
+                tree["subst"] = self.vocab.strings[tree["subst"]]
+            trees.append(tree)
+        return dict(trees=trees, labels=tuple(self.cfg["labels"]))
+
+    def initialize(
+        self,
+        get_examples: Callable[[], Iterable[Example]],
+        *,
+        nlp: Optional[Language] = None,
+        labels: Optional[Dict] = None,
+    ):
+        validate_get_examples(get_examples, "EditTreeLemmatizer.initialize")
+
+        if self.overwrite_labels:
+            if labels is None:
+                self._labels_from_data(get_examples)
+            else:
+                self._add_labels(labels)
+
+        # Sample for the model.
+        doc_sample = []
+        label_sample = []
+        for example in islice(get_examples(), 10):
+            doc_sample.append(example.x)
+            gold_labels: List[List[float]] = []
+            for token in example.reference:
+                if token.lemma == 0:
+                    gold_label = None
+                else:
+                    gold_label = self._pair2label(token.text, token.lemma_)
+
+                gold_labels.append(
+                    [
+                        1.0 if label == gold_label else 0.0
+                        for label in self.cfg["labels"]
+                    ]
+                )
+
+            gold_labels = cast(Floats2d, gold_labels)
+            label_sample.append(self.model.ops.asarray(gold_labels, dtype="float32"))
+
+        self._require_labels()
+        assert len(doc_sample) > 0, Errors.E923.format(name=self.name)
+        assert len(label_sample) > 0, Errors.E923.format(name=self.name)
+
+        self.model.initialize(X=doc_sample, Y=label_sample)
+
+    def from_bytes(self, bytes_data, *, exclude=tuple()):
+        deserializers = {
+            "cfg": lambda b: self.cfg.update(srsly.json_loads(b)),
+            "model": lambda b: self.model.from_bytes(b),
+            "vocab": lambda b: self.vocab.from_bytes(b, exclude=exclude),
+            "trees": lambda b: self.trees.from_bytes(b),
+        }
+
+        util.from_bytes(bytes_data, deserializers, exclude)
+
+        return self
+
+    def to_bytes(self, *, exclude=tuple()):
+        serializers = {
+            "cfg": lambda: srsly.json_dumps(self.cfg),
+            "model": lambda: self.model.to_bytes(),
+            "vocab": lambda: self.vocab.to_bytes(exclude=exclude),
+            "trees": lambda: self.trees.to_bytes(),
+        }
+
+        return util.to_bytes(serializers, exclude)
+
+    def to_disk(self, path, exclude=tuple()):
+        path = util.ensure_path(path)
+        serializers = {
+            "cfg": lambda p: srsly.write_json(p, self.cfg),
+            "model": lambda p: self.model.to_disk(p),
+            "vocab": lambda p: self.vocab.to_disk(p, exclude=exclude),
+            "trees": lambda p: self.trees.to_disk(p),
+        }
+        util.to_disk(path, serializers, exclude)
+
+    def from_disk(self, path, exclude=tuple()):
+        def load_model(p):
+            try:
+                with open(p, "rb") as mfile:
+                    self.model.from_bytes(mfile.read())
+            except AttributeError:
+                raise ValueError(Errors.E149) from None
+
+        deserializers = {
+            "cfg": lambda p: self.cfg.update(srsly.read_json(p)),
+            "model": load_model,
+            "vocab": lambda p: self.vocab.from_disk(p, exclude=exclude),
+            "trees": lambda p: self.trees.from_disk(p),
+        }
+
+        util.from_disk(path, deserializers, exclude)
+        return self
+
+    def _add_labels(self, labels: Dict):
+        if "labels" not in labels:
+            raise ValueError(Errors.E857.format(name="labels"))
+        if "trees" not in labels:
+            raise ValueError(Errors.E857.format(name="trees"))
+
+        self.cfg["labels"] = list(labels["labels"])
+        trees = []
+        for tree in labels["trees"]:
+            errors = validate_edit_tree(tree)
+            if errors:
+                raise ValueError(Errors.E1026.format(errors="\n".join(errors)))
+
+            tree = dict(tree)
+            if "orig" in tree:
+                tree["orig"] = self.vocab.strings[tree["orig"]]
+            if "orig" in tree:
+                tree["subst"] = self.vocab.strings[tree["subst"]]
+
+            trees.append(tree)
+
+        self.trees.from_json(trees)
+
+        for label, tree in enumerate(self.labels):
+            self.tree2label[tree] = label
+
+    def _labels_from_data(self, get_examples: Callable[[], Iterable[Example]]):
+        # Count corpus tree frequencies in ad-hoc storage to avoid cluttering
+        # the final pipe/string store.
+        vocab = Vocab()
+        trees = EditTrees(vocab.strings)
+        tree_freqs: Counter = Counter()
+        repr_pairs: Dict = {}
+        for example in get_examples():
+            for token in example.reference:
+                if token.lemma != 0:
+                    form = self._get_true_cased_form_of_token(token)
+                    # debug("_labels_from_data", str(token) + "->" + form, token.lemma_)
+                    tree_id = trees.add(form, token.lemma_)
+                    tree_freqs[tree_id] += 1
+                    repr_pairs[tree_id] = (form, token.lemma_)
+
+        # Construct trees that make the frequency cut-off using representative
+        # form - token pairs.
+        for tree_id, freq in tree_freqs.items():
+            if freq >= self.min_tree_freq:
+                form, lemma = repr_pairs[tree_id]
+                self._pair2label(form, lemma, add_label=True)
+
+    @lru_cache()
+    def _get_true_cased_form(self, token: str, is_sent_start: bool, pos: str) -> str:
+        if is_sent_start and pos != "PROPN":
+            return token.lower()
+        else:
+            return token
+
+    def _get_true_cased_form_of_token(self, token: Token) -> str:
+        return self._get_true_cased_form(token.text, token.is_sent_start, token.pos_)
+
+    def _pair2label(self, form, lemma, add_label=False):
+        """
+        Look up the edit tree identifier for a form/label pair. If the edit
+        tree is unknown and "add_label" is set, the edit tree will be added to
+        the labels.
+        """
+        tree_id = self.trees.add(form, lemma)
+        if tree_id not in self.tree2label:
+            if not add_label:
+                return None
+
+            self.tree2label[tree_id] = len(self.cfg["labels"])
+            self.cfg["labels"].append(tree_id)
+        return self.tree2label[tree_id]

hu_core_news_md-any-py3-none-any.whl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ab54c4d2c130a072908715e9f7953bf4616fad7bfe15016184f3c20e2f3ac30
-size 126998229
+oid sha256:0fd89c6ccf0efe1d7591910065c3bec4eadb1e25313d6ceea551150832b0f861
+size 127018056

lemma_postprocessing.py

@@ -1,113 +1,113 @@
-"""
-This module contains various rule-based components aiming to improve on baseline lemmatization tools.
-"""
-
-import re
-from typing import List, Callable
-
-from spacy.lang.hu import Hungarian
-from spacy.pipeline import Pipe
-from spacy.tokens import Token
-from spacy.tokens.doc import Doc
-
-
-@Hungarian.component(
-    "lemma_case_smoother",
-    assigns=["token.lemma"],
-    requires=["token.lemma", "token.pos"],
-)
-def lemma_case_smoother(doc: Doc) -> Doc:
-    """Smooth lemma casing by POS.
-
-    DEPRECATED: This is not needed anymore, as the lemmatizer is now case-insensitive.
-
-    Args:
-        doc (Doc): Input document.
-
-    Returns:
-        Doc: Output document.
-    """
-    for token in doc:
-        if token.is_sent_start and token.tag_ != "PROPN":
-            token.lemma_ = token.lemma_.lower()
-
-    return doc
-
-
-class LemmaSmoother(Pipe):
-    """Smooths lemma by fixing common errors of the edit-tree lemmatizer."""
-
-    _DATE_PATTERN = re.compile(r"(\d+)-j?[éá]?n?a?(t[őó]l)?")
-    _NUMBER_PATTERN = re.compile(r"(\d+([-,/_.:]?(._)?\d+)*%?)")
-
-    # noinspection PyUnusedLocal
-    @staticmethod
-    @Hungarian.factory("lemma_smoother", assigns=["token.lemma"], requires=["token.lemma", "token.pos"])
-    def create_lemma_smoother(nlp: Hungarian, name: str) -> "LemmaSmoother":
-        return LemmaSmoother()
-
-    def __call__(self, doc: Doc) -> Doc:
-        rules: List[Callable] = [
-            self._remove_exclamation_marks,
-            self._remove_question_marks,
-            self._remove_date_suffixes,
-            self._remove_suffix_after_numbers,
-        ]
-
-        for token in doc:
-            for rule in rules:
-                rule(token)
-
-        return doc
-
-    @classmethod
-    def _remove_exclamation_marks(cls, token: Token) -> None:
-        """Removes exclamation marks from the lemma.
-
-        Args:
-            token (Token): The original token.
-        """
-
-        if "!" != token.lemma_:
-            exclamation_mark_index = token.lemma_.find("!")
-            if exclamation_mark_index != -1:
-                token.lemma_ = token.lemma_[:exclamation_mark_index]
-
-    @classmethod
-    def _remove_question_marks(cls, token: Token) -> None:
-        """Removes question marks from the lemma.
-
-        Args:
-            token (Token): The original token.
-        """
-
-        if "?" != token.lemma_:
-            question_mark_index = token.lemma_.find("?")
-            if question_mark_index != -1:
-                token.lemma_ = token.lemma_[:question_mark_index]
-
-    @classmethod
-    def _remove_date_suffixes(cls, token: Token) -> None:
-        """Fixes the suffixes of dates.
-
-        Args:
-            token (Token): The original token.
-        """
-
-        if token.pos_ == "NOUN":
-            match = cls._DATE_PATTERN.match(token.lemma_)
-            if match is not None:
-                token.lemma_ = match.group(1) + "."
-
-    @classmethod
-    def _remove_suffix_after_numbers(cls, token: Token) -> None:
-        """Removes suffixes after numbers.
-
-        Args:
-            token (str): The original token.
-        """
-
-        if token.pos_ == "NUM":
-            match = cls._NUMBER_PATTERN.match(token.text)
-            if match is not None:
-                token.lemma_ = match.group(0)
+"""
+This module contains various rule-based components aiming to improve on baseline lemmatization tools.
+"""
+
+import re
+from typing import List, Callable
+
+from spacy.lang.hu import Hungarian
+from spacy.pipeline import Pipe
+from spacy.tokens import Token
+from spacy.tokens.doc import Doc
+
+
+@Hungarian.component(
+    "lemma_case_smoother",
+    assigns=["token.lemma"],
+    requires=["token.lemma", "token.pos"],
+)
+def lemma_case_smoother(doc: Doc) -> Doc:
+    """Smooth lemma casing by POS.
+
+    DEPRECATED: This is not needed anymore, as the lemmatizer is now case-insensitive.
+
+    Args:
+        doc (Doc): Input document.
+
+    Returns:
+        Doc: Output document.
+    """
+    for token in doc:
+        if token.is_sent_start and token.tag_ != "PROPN":
+            token.lemma_ = token.lemma_.lower()
+
+    return doc
+
+
+class LemmaSmoother(Pipe):
+    """Smooths lemma by fixing common errors of the edit-tree lemmatizer."""
+
+    _DATE_PATTERN = re.compile(r"(\d+)-j?[éá]?n?a?(t[őó]l)?")
+    _NUMBER_PATTERN = re.compile(r"(\d+([-,/_.:]?(._)?\d+)*%?)")
+
+    # noinspection PyUnusedLocal
+    @staticmethod
+    @Hungarian.factory("lemma_smoother", assigns=["token.lemma"], requires=["token.lemma", "token.pos"])
+    def create_lemma_smoother(nlp: Hungarian, name: str) -> "LemmaSmoother":
+        return LemmaSmoother()
+
+    def __call__(self, doc: Doc) -> Doc:
+        rules: List[Callable] = [
+            self._remove_exclamation_marks,
+            self._remove_question_marks,
+            self._remove_date_suffixes,
+            self._remove_suffix_after_numbers,
+        ]
+
+        for token in doc:
+            for rule in rules:
+                rule(token)
+
+        return doc
+
+    @classmethod
+    def _remove_exclamation_marks(cls, token: Token) -> None:
+        """Removes exclamation marks from the lemma.
+
+        Args:
+            token (Token): The original token.
+        """
+
+        if "!" != token.lemma_:
+            exclamation_mark_index = token.lemma_.find("!")
+            if exclamation_mark_index != -1:
+                token.lemma_ = token.lemma_[:exclamation_mark_index]
+
+    @classmethod
+    def _remove_question_marks(cls, token: Token) -> None:
+        """Removes question marks from the lemma.
+
+        Args:
+            token (Token): The original token.
+        """
+
+        if "?" != token.lemma_:
+            question_mark_index = token.lemma_.find("?")
+            if question_mark_index != -1:
+                token.lemma_ = token.lemma_[:question_mark_index]
+
+    @classmethod
+    def _remove_date_suffixes(cls, token: Token) -> None:
+        """Fixes the suffixes of dates.
+
+        Args:
+            token (Token): The original token.
+        """
+
+        if token.pos_ == "NOUN":
+            match = cls._DATE_PATTERN.match(token.lemma_)
+            if match is not None:
+                token.lemma_ = match.group(1) + "."
+
+    @classmethod
+    def _remove_suffix_after_numbers(cls, token: Token) -> None:
+        """Removes suffixes after numbers.
+
+        Args:
+            token (str): The original token.
+        """
+
+        if token.pos_ == "NUM":
+            match = cls._NUMBER_PATTERN.match(token.text)
+            if match is not None:
+                token.lemma_ = match.group(0)

lookup_lemmatizer.py

@@ -1,132 +1,132 @@
-import re
-from collections import defaultdict
-from operator import itemgetter
-from pathlib import Path
-from re import Pattern
-from typing import Optional, Callable, Iterable, Dict, Tuple
-
-from spacy.lang.hu import Hungarian
-from spacy.language import Language
-from spacy.lookups import Lookups, Table
-from spacy.pipeline import Pipe
-from spacy.pipeline.lemmatizer import lemmatizer_score
-from spacy.tokens import Token
-from spacy.tokens.doc import Doc
-
-# noinspection PyUnresolvedReferences
-from spacy.training.example import Example
-from spacy.util import ensure_path
-
-
-class LookupLemmatizer(Pipe):
-    """
-    LookupLemmatizer learn `(token, pos, morph. feat) -> lemma` mappings during training, and applies them at prediction
-    time.
-    """
-
-    _number_pattern: Pattern = re.compile(r"\d")
-
-    # noinspection PyUnusedLocal
-    @staticmethod
-    @Hungarian.factory(
-        "lookup_lemmatizer",
-        assigns=["token.lemma"],
-        requires=["token.pos"],
-        default_config={"scorer": {"@scorers": "spacy.lemmatizer_scorer.v1"}, "source": ""},
-    )
-    def create(nlp: Language, name: str, scorer: Optional[Callable], source: str) -> "LookupLemmatizer":
-        return LookupLemmatizer(None, source, scorer)
-
-    def train(self, sentences: Iterable[Iterable[Tuple[str, str, str, str]]], min_occurrences: int = 1) -> None:
-        """
-
-        Args:
-            sentences (Iterable[Iterable[Tuple[str, str, str, str]]]): Sentences to learn the mappings from
-            min_occurrences (int): mapping occurring less than this threshold are not learned
-
-        """
-
-        # Lookup table which maps (upos, form) to (lemma -> frequency),
-        # e.g. `{ ("NOUN", "alma"): { "alma" : 99, "alom": 1} }`
-        lemma_lookup_table: Dict[Tuple[str, str], Dict[str, int]] = defaultdict(lambda: defaultdict(int))
-
-        for sentence in sentences:
-            for token, pos, feats, lemma in sentence:
-                token = self.__mask_numbers(token)
-                lemma = self.__mask_numbers(lemma)
-                feats_str = ("|" + feats) if feats else ""
-                key = (token, pos + feats_str)
-                lemma_lookup_table[key][lemma] += 1
-        lemma_lookup_table = dict(lemma_lookup_table)
-
-        self._lookups = Lookups()
-        table = Table(name="lemma_lookups")
-
-        lemma_freq: Dict[str, int]
-        for (form, pos), lemma_freq in dict(lemma_lookup_table).items():
-            most_freq_lemma, freq = sorted(lemma_freq.items(), key=itemgetter(1), reverse=True)[0]
-            if freq >= min_occurrences:
-                if form not in table:
-                    # lemma by pos
-                    table[form]: Dict[str, str] = dict()
-                table[form][pos] = most_freq_lemma
-
-        self._lookups.set_table(name=f"lemma_lookups", table=table)
-
-    def __init__(
-        self,
-        lookups: Optional[Lookups] = None,
-        source: Optional[str] = None,
-        scorer: Optional[Callable] = lemmatizer_score,
-    ):
-        self._lookups: Optional[Lookups] = lookups
-        self.scorer = scorer
-        self.source = source
-
-    def __call__(self, doc: Doc) -> Doc:
-        assert self._lookups is not None, "Lookup table should be initialized first"
-
-        token: Token
-        for token in doc:
-            lemma_lookup_table = self._lookups.get_table(f"lemma_lookups")
-            masked_token = self.__mask_numbers(token.text)
-
-            if masked_token in lemma_lookup_table:
-                lemma_by_pos: Dict[str, str] = lemma_lookup_table[masked_token]
-                feats_str = ("|" + str(token.morph)) if str(token.morph) else ""
-                key = token.pos_ + feats_str
-                if key in lemma_by_pos:
-                    if masked_token != token.text:
-                        # If the token contains numbers, we need to replace the numbers in the lemma as well
-                        token.lemma_ = self.__replace_numbers(lemma_by_pos[key], token.text)
-                        pass
-                    else:
-                        token.lemma_ = lemma_by_pos[key]
-        return doc
-
-    # noinspection PyUnusedLocal
-    def to_disk(self, path, exclude=tuple()):
-        assert self._lookups is not None, "Lookup table should be initialized first"
-
-        path: Path = ensure_path(path)
-        path.mkdir(exist_ok=True)
-        self._lookups.to_disk(path)
-
-    # noinspection PyUnusedLocal
-    def from_disk(self, path, exclude=tuple()) -> "LookupLemmatizer":
-        path: Path = ensure_path(path)
-        lookups = Lookups()
-        self._lookups = lookups.from_disk(path=path)
-        return self
-
-    def initialize(self, get_examples: Callable[[], Iterable[Example]], *, nlp: Language = None) -> None:
-        lookups = Lookups()
-        self._lookups = lookups.from_disk(path=self.source)
-
-    @classmethod
-    def __mask_numbers(cls, token: str) -> str:
-        return cls._number_pattern.sub("0", token)
-
-    @classmethod
-    def __replace_numbers(cls, lemma: str, token: str) -> str:
-        return cls._number_pattern.sub(lambda match: token[match.start()], lemma)
+import re
+from collections import defaultdict
+from operator import itemgetter
+from pathlib import Path
+from re import Pattern
+from typing import Optional, Callable, Iterable, Dict, Tuple
+
+from spacy.lang.hu import Hungarian
+from spacy.language import Language
+from spacy.lookups import Lookups, Table
+from spacy.pipeline import Pipe
+from spacy.pipeline.lemmatizer import lemmatizer_score
+from spacy.tokens import Token
+from spacy.tokens.doc import Doc
+
+# noinspection PyUnresolvedReferences
+from spacy.training.example import Example
+from spacy.util import ensure_path
+
+
+class LookupLemmatizer(Pipe):
+    """
+    LookupLemmatizer learn `(token, pos, morph. feat) -> lemma` mappings during training, and applies them at prediction
+    time.
+    """
+
+    _number_pattern: Pattern = re.compile(r"\d")
+
+    # noinspection PyUnusedLocal
+    @staticmethod
+    @Hungarian.factory(
+        "lookup_lemmatizer",
+        assigns=["token.lemma"],
+        requires=["token.pos"],
+        default_config={"scorer": {"@scorers": "spacy.lemmatizer_scorer.v1"}, "source": ""},
+    )
+    def create(nlp: Language, name: str, scorer: Optional[Callable], source: str) -> "LookupLemmatizer":
+        return LookupLemmatizer(None, source, scorer)
+
+    def train(self, sentences: Iterable[Iterable[Tuple[str, str, str, str]]], min_occurrences: int = 1) -> None:
+        """
+
+        Args:
+            sentences (Iterable[Iterable[Tuple[str, str, str, str]]]): Sentences to learn the mappings from
+            min_occurrences (int): mapping occurring less than this threshold are not learned
+
+        """
+
+        # Lookup table which maps (upos, form) to (lemma -> frequency),
+        # e.g. `{ ("NOUN", "alma"): { "alma" : 99, "alom": 1} }`
+        lemma_lookup_table: Dict[Tuple[str, str], Dict[str, int]] = defaultdict(lambda: defaultdict(int))
+
+        for sentence in sentences:
+            for token, pos, feats, lemma in sentence:
+                token = self.__mask_numbers(token)
+                lemma = self.__mask_numbers(lemma)
+                feats_str = ("|" + feats) if feats else ""
+                key = (token, pos + feats_str)
+                lemma_lookup_table[key][lemma] += 1
+        lemma_lookup_table = dict(lemma_lookup_table)
+
+        self._lookups = Lookups()
+        table = Table(name="lemma_lookups")
+
+        lemma_freq: Dict[str, int]
+        for (form, pos), lemma_freq in dict(lemma_lookup_table).items():
+            most_freq_lemma, freq = sorted(lemma_freq.items(), key=itemgetter(1), reverse=True)[0]
+            if freq >= min_occurrences:
+                if form not in table:
+                    # lemma by pos
+                    table[form]: Dict[str, str] = dict()
+                table[form][pos] = most_freq_lemma
+
+        self._lookups.set_table(name=f"lemma_lookups", table=table)
+
+    def __init__(
+        self,
+        lookups: Optional[Lookups] = None,
+        source: Optional[str] = None,
+        scorer: Optional[Callable] = lemmatizer_score,
+    ):
+        self._lookups: Optional[Lookups] = lookups
+        self.scorer = scorer
+        self.source = source
+
+    def __call__(self, doc: Doc) -> Doc:
+        assert self._lookups is not None, "Lookup table should be initialized first"
+
+        token: Token
+        for token in doc:
+            lemma_lookup_table = self._lookups.get_table(f"lemma_lookups")
+            masked_token = self.__mask_numbers(token.text)
+
+            if masked_token in lemma_lookup_table:
+                lemma_by_pos: Dict[str, str] = lemma_lookup_table[masked_token]
+                feats_str = ("|" + str(token.morph)) if str(token.morph) else ""
+                key = token.pos_ + feats_str
+                if key in lemma_by_pos:
+                    if masked_token != token.text:
+                        # If the token contains numbers, we need to replace the numbers in the lemma as well
+                        token.lemma_ = self.__replace_numbers(lemma_by_pos[key], token.text)
+                        pass
+                    else:
+                        token.lemma_ = lemma_by_pos[key]
+        return doc
+
+    # noinspection PyUnusedLocal
+    def to_disk(self, path, exclude=tuple()):
+        assert self._lookups is not None, "Lookup table should be initialized first"
+
+        path: Path = ensure_path(path)
+        path.mkdir(exist_ok=True)
+        self._lookups.to_disk(path)
+
+    # noinspection PyUnusedLocal
+    def from_disk(self, path, exclude=tuple()) -> "LookupLemmatizer":
+        path: Path = ensure_path(path)
+        lookups = Lookups()
+        self._lookups = lookups.from_disk(path=path)
+        return self
+
+    def initialize(self, get_examples: Callable[[], Iterable[Example]], *, nlp: Language = None) -> None:
+        lookups = Lookups()
+        self._lookups = lookups.from_disk(path=self.source)
+
+    @classmethod
+    def __mask_numbers(cls, token: str) -> str:
+        return cls._number_pattern.sub("0", token)
+
+    @classmethod
+    def __replace_numbers(cls, lemma: str, token: str) -> str:
+        return cls._number_pattern.sub(lambda match: token[match.start()], lemma)

meta.json

@@ -1,14 +1,14 @@
 {
   "lang":"hu",
   "name":"core_news_md",
-  "version":"3.7.0",
+  "version":"3.8.0",
   "description":"Core Hungarian model for HuSpaCy. Components: tok2vec, senter, tagger, morphologizer, lemmatizer, parser, ner",
   "author":"SzegedAI, MILAB",
   "email":"[email protected]",
   "url":"https://github.com/huspacy/huspacy",
   "license":"cc-by-sa-4.0",
-  "spacy_version":">=3.7.0,<3.8.0",
-  "spacy_git_version":"a89eae928",
+  "spacy_version":">=3.8.0,<3.9.0",
+  "spacy_git_version":"63f1b53",
   "vectors":{
     "width":100,
     "vectors":200000,
@@ -1268,90 +1268,90 @@
     "token_p":0.998565417,
     "token_r":0.9993300153,
     "token_f":0.9989475698,
-    "sents_p":0.9711111111,
-    "sents_r":0.9732739421,
-    "sents_f":0.9721913237,
-    "tag_acc":0.9696128631,
-    "pos_acc":0.9688965451,
-    "morph_acc":0.9451117385,
-    "morph_micro_p":0.9764287881,
-    "morph_micro_r":0.9684142673,
-    "morph_micro_f":0.9724050141,
+    "sents_p":0.977827051,
+    "sents_r":0.9821826281,
+    "sents_f":0.98,
+    "tag_acc":0.9710512465,
+    "pos_acc":0.9685137334,
+    "morph_acc":0.9431524548,
+    "morph_micro_p":0.9750909721,
+    "morph_micro_r":0.9672969489,
+    "morph_micro_f":0.9711783233,
     "morph_per_feat":{
       "Definite":{
-        "p":0.9744779582,
-        "r":0.979934671,
-        "f":0.9771986971
+        "p":0.9770920991,
+        "r":0.9752683154,
+        "f":0.9761793554
       },
       "PronType":{
-        "p":0.9708791209,
-        "r":0.9751655629,
-        "f":0.9730176211
+        "p":0.9718387631,
+        "r":0.9713024283,
+        "f":0.9715705217
       },
       "Case":{
-        "p":0.9850538063,
-        "r":0.9766844497,
-        "f":0.9808512749
+        "p":0.9834792994,
+        "r":0.9762892709,
+        "f":0.9798710957
       },
       "Degree":{
-        "p":0.9387938794,
-        "r":0.8677204659,
-        "f":0.9018590575
+        "p":0.9336283186,
+        "r":0.877703827,
+        "f":0.9048027444
       },
       "Number":{
-        "p":0.9907516395,
-        "r":0.9874308698,
-        "f":0.9890884673
+        "p":0.9897668176,
+        "r":0.988771577,
+        "f":0.989268947
       },
       "Mood":{
-        "p":0.9459161148,
-        "r":0.9501108647,
-        "f":0.9480088496
+        "p":0.9351648352,
+        "r":0.94345898,
+        "f":0.9392935982
       },
       "Person":{
-        "p":0.9625101874,
+        "p":0.9555016181,
         "r":0.9712171053,
-        "f":0.9668440442
+        "f":0.9632952692
       },
       "Tense":{
-        "p":0.9801324503,
-        "r":0.9812154696,
-        "f":0.980673661
+        "p":0.9747252747,
+        "r":0.9801104972,
+        "f":0.9774104683
       },
       "VerbForm":{
-        "p":0.9696714406,
-        "r":0.9230152366,
-        "f":0.9457682827
+        "p":0.9723899914,
+        "r":0.9037690457,
+        "f":0.9368246052
       },
       "Voice":{
-        "p":0.9704684318,
+        "p":0.9665314402,
         "r":0.9744376278,
-        "f":0.9724489796
+        "f":0.9704684318
       },
       "Number[psor]":{
-        "p":0.9841498559,
+        "p":0.9956268222,
         "r":0.9729344729,
-        "f":0.9785100287
+        "f":0.9841498559
       },
       "Person[psor]":{
-        "p":0.9841498559,
-        "r":0.9743223966,
-        "f":0.9792114695
+        "p":0.9941690962,
+        "r":0.9728958631,
+        "f":0.9834174477
       },
       "NumType":{
-        "p":0.9414634146,
-        "r":0.9414634146,
-        "f":0.9414634146
+        "p":0.9376498801,
+        "r":0.9536585366,
+        "f":0.9455864571
       },
       "Poss":{
-        "p":0.6,
+        "p":0.5,
         "r":1.0,
-        "f":0.75
+        "f":0.6666666667
       },
       "Reflex":{
         "p":1.0,
-        "r":0.5,
-        "f":0.6666666667
+        "r":0.375,
+        "f":0.5454545455
       },
       "Reflexive":{
         "p":0.0,
@@ -1375,118 +1375,118 @@
       },
       "Number[psed]":{
         "p":1.0,
-        "r":0.1111111111,
-        "f":0.2
+        "r":0.2222222222,
+        "f":0.3636363636
       }
     },
-    "lemma_acc":0.9745478902,
-    "dep_uas":0.8089662094,
-    "dep_las":0.7368831893,
+    "lemma_acc":0.974069467,
+    "dep_uas":0.818445411,
+    "dep_las":0.7425002788,
     "dep_las_per_type":{
       "det":{
-        "p":0.8714733542,
-        "r":0.8853503185,
-        "f":0.87835703
+        "p":0.8732394366,
+        "r":0.8885350318,
+        "f":0.8808208366
       },
       "amod:att":{
-        "p":0.8639798489,
-        "r":0.8413736713,
-        "f":0.8525269263
+        "p":0.8492257539,
+        "r":0.8520032706,
+        "f":0.8506122449
       },
       "nsubj":{
-        "p":0.7271293375,
-        "r":0.7203125,
-        "f":0.7237048666
+        "p":0.7138413686,
+        "r":0.7171875,
+        "f":0.7155105222
       },
       "advmod:mode":{
-        "p":0.5321100917,
-        "r":0.568627451,
-        "f":0.5497630332
+        "p":0.5352422907,
+        "r":0.5955882353,
+        "f":0.5638051044
       },
       "nmod:att":{
-        "p":0.7595993322,
-        "r":0.7711864407,
-        "f":0.7653490328
+        "p":0.7360655738,
+        "r":0.7610169492,
+        "f":0.7483333333
       },
       "obl":{
-        "p":0.7508833922,
-        "r":0.7650765077,
-        "f":0.7579135087
+        "p":0.7799263352,
+        "r":0.7623762376,
+        "f":0.7710514338
       },
       "obj":{
-        "p":0.8561797753,
-        "r":0.8561797753,
-        "f":0.8561797753
+        "p":0.8684807256,
+        "r":0.8606741573,
+        "f":0.8645598194
       },
       "root":{
-        "p":0.8,
-        "r":0.8017817372,
-        "f":0.8008898776
+        "p":0.844789357,
+        "r":0.8485523385,
+        "f":0.8466666667
       },
       "cc":{
-        "p":0.6856540084,
-        "r":0.6842105263,
-        "f":0.6849315068
+        "p":0.7149028078,
+        "r":0.6968421053,
+        "f":0.7057569296
       },
       "conj":{
-        "p":0.4558823529,
-        "r":0.5166666667,
-        "f":0.484375
+        "p":0.4516129032,
+        "r":0.525,
+        "f":0.4855491329
       },
       "advmod":{
-        "p":0.7878787879,
-        "r":0.8210526316,
-        "f":0.8041237113
+        "p":0.8058252427,
+        "r":0.8736842105,
+        "f":0.8383838384
       },
       "flat:name":{
-        "p":0.8266666667,
-        "r":0.8691588785,
-        "f":0.84738041
+        "p":0.8434782609,
+        "r":0.9065420561,
+        "f":0.8738738739
       },
       "appos":{
-        "p":0.3636363636,
-        "r":0.3404255319,
-        "f":0.3516483516
+        "p":0.5230769231,
+        "r":0.3617021277,
+        "f":0.427672956
       },
       "advcl":{
-        "p":0.2380952381,
+        "p":0.2247191011,
         "r":0.2040816327,
-        "f":0.2197802198
+        "f":0.2139037433
       },
       "advmod:tlocy":{
-        "p":0.611814346,
-        "r":0.6304347826,
-        "f":0.6209850107
+        "p":0.6034482759,
+        "r":0.6086956522,
+        "f":0.6060606061
       },
       "ccomp:obj":{
-        "p":0.1698113208,
-        "r":0.2727272727,
-        "f":0.2093023256
+        "p":0.1818181818,
+        "r":0.303030303,
+        "f":0.2272727273
       },
       "mark":{
-        "p":0.79375,
-        "r":0.8037974684,
-        "f":0.7987421384
+        "p":0.821656051,
+        "r":0.8164556962,
+        "f":0.819047619
       },
       "compound:preverb":{
-        "p":0.8928571429,
-        "r":0.9174311927,
-        "f":0.9049773756
+        "p":0.8606557377,
+        "r":0.9633027523,
+        "f":0.9090909091
       },
       "advmod:locy":{
-        "p":0.652173913,
-        "r":0.46875,
-        "f":0.5454545455
+        "p":0.6666666667,
+        "r":0.3125,
+        "f":0.4255319149
       },
       "cop":{
-        "p":0.92,
-        "r":0.5609756098,
-        "f":0.696969697
+        "p":0.7857142857,
+        "r":0.5365853659,
+        "f":0.6376811594
       },
       "nmod:obl":{
-        "p":0.1621621622,
-        "r":0.15,
-        "f":0.1558441558
+        "p":0.1951219512,
+        "r":0.2,
+        "f":0.1975308642
       },
       "advmod:to":{
         "p":0.0,
@@ -1494,69 +1494,74 @@
         "f":0.0
       },
       "obj:lvc":{
-        "p":0.2857142857,
-        "r":0.1666666667,
-        "f":0.2105263158
+        "p":0.1666666667,
+        "r":0.0833333333,
+        "f":0.1111111111
       },
       "ccomp:obl":{
-        "p":0.28,
-        "r":0.21875,
-        "f":0.2456140351
+        "p":0.36,
+        "r":0.28125,
+        "f":0.3157894737
       },
       "iobj":{
-        "p":0.3333333333,
-        "r":0.2,
-        "f":0.25
-      },
-      "dep":{
-        "p":0.0,
-        "r":0.0,
-        "f":0.0
-      },
-      "acl":{
-        "p":0.3606557377,
-        "r":0.3055555556,
-        "f":0.3308270677
+        "p":0.2,
+        "r":0.1333333333,
+        "f":0.16
       },
       "case":{
-        "p":0.9484536082,
-        "r":0.9387755102,
-        "f":0.9435897436
+        "p":0.9336734694,
+        "r":0.9336734694,
+        "f":0.9336734694
       },
       "csubj":{
-        "p":0.4615384615,
-        "r":0.3243243243,
-        "f":0.380952381
+        "p":0.4166666667,
+        "r":0.2702702703,
+        "f":0.3278688525
       },
       "parataxis":{
-        "p":0.2173913043,
-        "r":0.0684931507,
-        "f":0.1041666667
+        "p":0.2068965517,
+        "r":0.0821917808,
+        "f":0.1176470588
       },
       "xcomp":{
-        "p":0.8630136986,
-        "r":0.8513513514,
-        "f":0.8571428571
+        "p":0.8904109589,
+        "r":0.8783783784,
+        "f":0.8843537415
       },
       "nummod":{
-        "p":0.5169491525,
-        "r":0.6559139785,
-        "f":0.5781990521
+        "p":0.5242718447,
+        "r":0.5806451613,
+        "f":0.5510204082
+      },
+      "acl":{
+        "p":0.3333333333,
+        "r":0.2361111111,
+        "f":0.2764227642
       },
       "advmod:tto":{
-        "p":0.5,
-        "r":0.3,
-        "f":0.375
+        "p":0.2,
+        "r":0.1,
+        "f":0.1333333333
       },
       "nmod":{
-        "p":0.4,
+        "p":0.2857142857,
         "r":0.1818181818,
-        "f":0.25
+        "f":0.2222222222
+      },
+      "ccomp":{
+        "p":0.25,
+        "r":0.0769230769,
+        "f":0.1176470588
+      },
+      "dep":{
+        "p":0.0,
+        "r":0.0,
+        "f":0.0
       },
       "aux":{
-        "p":0.8888888889,
+        "p":0.8,
         "r":0.6666666667,
-        "f":0.7619047619
+        "f":0.7272727273
       },
       "advmod:tfrom":{
         "p":0.0,
@@ -1564,9 +1569,9 @@
         "f":0.0
       },
       "list":{
-        "p":0.1,
+        "p":0.0769230769,
         "r":0.1666666667,
-        "f":0.125
+        "f":0.1052631579
       },
       "goeswith":{
         "p":0.0,
@@ -1574,14 +1579,9 @@
         "f":0.0
       },
       "compound":{
-        "p":0.8863636364,
-        "r":0.975,
-        "f":0.9285714286
-      },
-      "ccomp":{
-        "p":0.1111111111,
-        "r":0.0769230769,
-        "f":0.0909090909
+        "p":0.95,
+        "r":0.95,
+        "f":0.95
       },
       "obl:lvc":{
         "p":0.0,
@@ -1600,8 +1600,8 @@
       },
       "advmod:que":{
         "p":1.0,
-        "r":0.25,
-        "f":0.4
+        "r":0.5,
+        "f":0.6666666667
       },
       "ccomp:pred":{
         "p":0.0,
@@ -1609,32 +1609,32 @@
         "f":0.0
       }
     },
-    "ents_p":0.8441212981,
-    "ents_r":0.8368495077,
-    "ents_f":0.8404696742,
+    "ents_p":0.8499734936,
+    "ents_r":0.8456399437,
+    "ents_f":0.8478011809,
     "ents_per_type":{
       "ORG":{
-        "p":0.8761301989,
-        "r":0.8984700974,
-        "f":0.8871595331
+        "p":0.8741573034,
+        "r":0.9017153454,
+        "f":0.8877225011
       },
       "PER":{
-        "p":0.8759926695,
-        "r":0.8566308244,
-        "f":0.8662035639
+        "p":0.8958333333,
+        "r":0.8733572282,
+        "f":0.8844525106
       },
       "LOC":{
-        "p":0.8630259624,
-        "r":0.8368055556,
-        "f":0.8497135302
+        "p":0.8658865887,
+        "r":0.8350694444,
+        "f":0.8501988511
       },
       "MISC":{
-        "p":0.6300148588,
-        "r":0.6014184397,
-        "f":0.6153846154
+        "p":0.6382054993,
+        "r":0.6255319149,
+        "f":0.6318051576
       }
     },
-    "speed":2399.5533428162
+    "speed":4473.6366022181
   },
   "sources":[
     {
@@ -1663,6 +1663,6 @@
     }
   ],
   "requirements":[
-
+    "spacy>=3.8.0,<3.9.0"
   ]
 }

morphologizer/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cf6c8b0c4ce8fa51226d9db9077809cd535d131e1fdf3421471bfa49c5476df
+oid sha256:d2b94e9da7c6ae76ea19b0deeaa9244606a8c4aa610a3fd2e06aae8b0253d5ad
 size 463022

ner/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65e0a7d26da1aa62dfdf9f7c2876aebb6d798c7a4786f151ab94437d60a2a5fd
+oid sha256:05134e628d4094b7e167701fc1eb41db49f7ad1ada234facd1bfe8f8c10ae022
 size 9791307

parser/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b4da42caf4aa9e46e6f907e1ac72d5a552b8f5d3c96c26515e7e7db80ee0cca
+oid sha256:7f38aee8f61557fd7529a3d51c69188f8721a893e83e7bdb78dc1fd19dc89105
 size 25601129

senter/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ec5e97c58af6c3c0dacd2a06c0c7477d34eed0bc55e5a6a28223315cee82211
+oid sha256:2aff0a005319472d364853603d0700f2f1f78268161842dd99c26d8d1571f180
 size 1237

tagger/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2018a57379826e3f3e12a2f10ca832a00a304a662b06ea10751fe85c381b030d
+oid sha256:87da5da8e02ab091f00a4110ce8e690a749926272f1e079e7ae7f5935003f64e
 size 7297

tok2vec/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9c33d47580051510bf34eda63668a7f02d3c57d4533041e0fd7a35e6c9dcf11
+oid sha256:3b31693678a7fda755d8c9b9b313572c26086c7d7dfab29716eed5864b592655
 size 9659749

trainable_lemmatizer/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eab9bb915a45aef358b82d325dd42cab9fe4071c384fcaddbb8e5a19c5adde2d
+oid sha256:c0c3842d4b4e28a704f66c24be343a2f27b12ee37fb0cbe5113e384196202694
 size 11281364

vocab/strings.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b23538bf7674fbc3a5aa75885e9e3afe93eac53b3762bc9da6b0789a4b7e731
-size 6389907
+oid sha256:1f7d6d928c4beb7598b0ccfb9c58c82a4629f9de30f75923eb92a864c2a6e65b
+size 6390466