Update spaCy pipeline

README.md

@@ -14,27 +14,27 @@ model-index:
     metrics:
     - name: NER Precision
       type: precision
-      value: 0.7897948078
+      value: 0.798987704
     - name: NER Recall
       type: recall
-      value: 0.7904761222
+      value: 0.7954112218
     - name: NER F Score
       type: f_score
-      value: 0.7901353181
+      value: 0.7971954516
   - task:
       name: TAG
       type: token-classification
     metrics:
     - name: TAG (XPOS) Accuracy
       type: accuracy
-      value: 0.9422182346
+      value: 0.9698599662
 ---
 English pipeline for part-of-speech and rhetorical tagging.
 
 | Feature | Description |
 | --- | --- |
 | **Name** | `en_docusco_spacy` |
-| **Version** | `1.2` |
+| **Version** | `1.3` |
 | **spaCy** | `>=3.5.0,<3.6.0` |
 | **Default Pipeline** | `tok2vec`, `tagger`, `ner` |
 | **Components** | `tok2vec`, `tagger`, `ner` |
@@ -60,10 +60,10 @@ English pipeline for part-of-speech and rhetorical tagging.
 
 | Type | Score |
 | --- | --- |
-| `TAG_ACC` | 94.22 |
-| `ENTS_F` | 79.01 |
-| `ENTS_P` | 78.98 |
-| `ENTS_R` | 79.05 |
-| `TOK2VEC_LOSS` | 18044765.75 |
-| `TAGGER_LOSS` | 2400921.93 |
-| `NER_LOSS` | 5935848.19 |
+| `TAG_ACC` | 96.99 |
+| `ENTS_F` | 79.72 |
+| `ENTS_P` | 79.90 |
+| `ENTS_R` | 79.54 |
+| `TOK2VEC_LOSS` | 20924847.53 |
+| `TAGGER_LOSS` | 1316790.55 |
+| `NER_LOSS` | 5818469.98 |

config.cfg

@@ -104,7 +104,7 @@ dropout = 0.1
 accumulate_gradient = 1
 patience = 1600
 max_epochs = 0
-max_steps = 35000
+max_steps = 40000
 eval_frequency = 250
 frozen_components = []
 annotating_components = []

en_docusco_spacy-any-py3-none-any.whl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d73aad65d669783246161c1be36f0be9001ee88c4b1fddce57311c8a8bc5030
-size 7502026
+oid sha256:8d5b44d15d93b41b27c0650f71553ece8709eb2717910922fb129809e9423d54
+size 7501545

meta.json

@@ -1,7 +1,7 @@
 {
   "lang":"en",
   "name":"docusco_spacy",
-  "version":"1.2",
+  "version":"1.3",
   "description":"English pipeline for part-of-speech and rhetorical tagging.",
   "author":"David Brown",
   "email":"[email protected]",
@@ -346,195 +346,195 @@
 
   ],
   "performance":{
-    "tag_acc":0.9422182346,
-    "ents_f":0.7901353181,
-    "ents_p":0.7897948078,
-    "ents_r":0.7904761222,
+    "tag_acc":0.9698599662,
+    "ents_f":0.7971954516,
+    "ents_p":0.798987704,
+    "ents_r":0.7954112218,
     "ents_per_type":{
       "Contingent":{
-        "p":0.8286840509,
-        "r":0.7583240844,
-        "f":0.791944364
+        "p":0.818815331,
+        "r":0.782463929,
+        "f":0.8002270148
       },
       "InformationExposition":{
-        "p":0.8400248832,
-        "r":0.8577633567,
-        "f":0.8488014542
+        "p":0.8498392228,
+        "r":0.857557341,
+        "f":0.8536808374
       },
       "AcademicTerms":{
-        "p":0.7894026371,
-        "r":0.8286671247,
-        "f":0.8085584799
+        "p":0.8128432795,
+        "r":0.8176600252,
+        "f":0.8152445377
       },
       "ForceStressed":{
-        "p":0.7898256456,
-        "r":0.7841148116,
-        "f":0.7869598681
+        "p":0.8036501362,
+        "r":0.7950043821,
+        "f":0.7993038804
       },
       "Character":{
-        "p":0.8500444492,
-        "r":0.8432579053,
-        "f":0.8466375774
+        "p":0.8509934653,
+        "r":0.8578615428,
+        "f":0.8544137022
       },
       "Narrative":{
-        "p":0.7737338187,
-        "r":0.7965586415,
-        "f":0.7849803462
+        "p":0.7922994384,
+        "r":0.7865517992,
+        "f":0.789415157
       },
       "Strategic":{
-        "p":0.7364217252,
-        "r":0.6996483435,
-        "f":0.7175642072
+        "p":0.74291956,
+        "r":0.7049416991,
+        "f":0.7234325438
       },
       "MetadiscourseInteractive":{
-        "p":0.8356010661,
-        "r":0.6838480083,
-        "f":0.7521464646
+        "p":0.8243080626,
+        "r":0.7077258639,
+        "f":0.761581223
       },
       "Facilitate":{
-        "p":0.7088353414,
-        "r":0.6600373959,
-        "f":0.6835665874
+        "p":0.7420591457,
+        "r":0.6909739929,
+        "f":0.7156060206
       },
       "Negative":{
-        "p":0.7095155684,
-        "r":0.682564777,
-        "f":0.6957792879
+        "p":0.7366169936,
+        "r":0.6818932229,
+        "f":0.7081995321
       },
       "Interactive":{
-        "p":0.839874111,
-        "r":0.8383435157,
-        "f":0.8391081154
+        "p":0.8438560526,
+        "r":0.8501978617,
+        "f":0.8470150867
       },
       "MetadiscourseCohesive":{
-        "p":0.9192184725,
-        "r":0.9288534712,
-        "f":0.9240108556
+        "p":0.9307703425,
+        "r":0.9246894967,
+        "f":0.9277199553
       },
       "Description":{
-        "p":0.7208328088,
-        "r":0.7628920157,
-        "f":0.7412662853
+        "p":0.7184076094,
+        "r":0.7692427259,
+        "f":0.7429566137
       },
       "PublicTerms":{
-        "p":0.8309137834,
-        "r":0.778781465,
-        "f":0.8040034337
+        "p":0.8250038862,
+        "r":0.8023660141,
+        "f":0.8135274957
       },
       "Reasoning":{
-        "p":0.8395115952,
-        "r":0.7998493535,
-        "f":0.8192006857
+        "p":0.8453436321,
+        "r":0.8060425995,
+        "f":0.8252254568
       },
       "Positive":{
-        "p":0.7291883827,
-        "r":0.6821606119,
-        "f":0.7048909876
+        "p":0.7428654449,
+        "r":0.6843594646,
+        "f":0.7124132921
       },
       "Updates":{
-        "p":0.7837246077,
-        "r":0.7084891137,
-        "f":0.7442102224
+        "p":0.7921472679,
+        "r":0.7476358038,
+        "f":0.7692481756
       },
       "InformationTopics":{
-        "p":0.7918713029,
-        "r":0.8200456611,
-        "f":0.8057122551
+        "p":0.7997236338,
+        "r":0.8110942833,
+        "f":0.8053688262
       },
       "ConfidenceHigh":{
-        "p":0.7615851193,
-        "r":0.7704958272,
-        "f":0.7660145605
+        "p":0.7693539348,
+        "r":0.7862870234,
+        "f":0.7777283211
       },
       "Citation":{
-        "p":0.8037907101,
-        "r":0.7775338928,
-        "f":0.7904443132
+        "p":0.8227242525,
+        "r":0.7993544222,
+        "f":0.8108709889
       },
       "ConfidenceHedged":{
-        "p":0.8374410068,
-        "r":0.8770594696,
-        "f":0.856792489
+        "p":0.8354197349,
+        "r":0.8900831633,
+        "f":0.8618855884
       },
       "InformationChange":{
-        "p":0.7123025371,
-        "r":0.7132585562,
-        "f":0.7127802261
+        "p":0.7294003868,
+        "r":0.7230371009,
+        "f":0.7262048048
       },
       "InformationStates":{
-        "p":0.8041805777,
-        "r":0.8789930188,
-        "f":0.8399241946
+        "p":0.8306426735,
+        "r":0.8544531415,
+        "f":0.8423796861
       },
       "FirstPerson":{
-        "p":0.8766524888,
-        "r":0.8892257463,
-        "f":0.882894356
+        "p":0.8819685753,
+        "r":0.9076103856,
+        "f":0.8946057773
       },
       "Responsibility":{
-        "p":0.7242662257,
-        "r":0.6096033403,
-        "f":0.6620064236
+        "p":0.7287275566,
+        "r":0.6496172582,
+        "f":0.6869021339
       },
       "Inquiry":{
-        "p":0.6661799979,
-        "r":0.6047524378,
-        "f":0.6339817388
+        "p":0.6458673322,
+        "r":0.6369402632,
+        "f":0.6413727359
       },
       "InformationChangeNegative":{
-        "p":0.6824946846,
-        "r":0.5407074677,
-        "f":0.6033834586
+        "p":0.738317757,
+        "r":0.532285233,
+        "f":0.6185970636
       },
       "ConfidenceLow":{
-        "p":0.6462395543,
-        "r":0.5510688836,
-        "f":0.5948717949
+        "p":0.8554216867,
+        "r":0.5059382423,
+        "f":0.6358208955
       },
       "InformationPlace":{
-        "p":0.865587996,
-        "r":0.8944517093,
-        "f":0.8797831779
-      },
-      "InformationReportVerbs":{
-        "p":0.7508147746,
-        "r":0.7912701252,
-        "f":0.7705117932
+        "p":0.8853535824,
+        "r":0.8875035024,
+        "f":0.8864272388
       },
       "Future":{
-        "p":0.756072781,
-        "r":0.7410827449,
-        "f":0.7485027202
+        "p":0.7515119175,
+        "r":0.7649827992,
+        "f":0.758187528
       },
       "AcademicWritingMoves":{
-        "p":0.7083700441,
-        "r":0.4375510204,
-        "f":0.5409587889
+        "p":0.6664195701,
+        "r":0.4892517007,
+        "f":0.5642554527
+      },
+      "InformationReportVerbs":{
+        "p":0.7737441669,
+        "r":0.8067978533,
+        "f":0.7899253862
       },
       "Uncertainty":{
-        "p":0.7549221275,
-        "r":0.6497218007,
-        "f":0.6983824929
+        "p":0.7402862986,
+        "r":0.6408700051,
+        "f":0.6870001356
       },
       "CitationHedged":{
-        "p":0.7483221477,
-        "r":0.9570815451,
-        "f":0.8399246704
+        "p":0.7630662021,
+        "r":0.9399141631,
+        "f":0.8423076923
       },
       "CitationAuthority":{
-        "p":0.7841151386,
-        "r":0.5490854797,
-        "f":0.6458836443
+        "p":0.7866273353,
+        "r":0.5972377753,
+        "f":0.6789730533
       },
       "InformationChangePositive":{
-        "p":0.7640586797,
-        "r":0.546169531,
-        "f":0.6369967725
+        "p":0.7317845829,
+        "r":0.605592776,
+        "f":0.6627350972
       }
     },
-    "tok2vec_loss":180447.6574847773,
-    "tagger_loss":24009.219291687,
-    "ner_loss":59358.4819319265
+    "tok2vec_loss":209248.4752924392,
+    "tagger_loss":13167.9055271149,
+    "ner_loss":58184.6998399578
   },
   "requirements":[
 

ner/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54dd874f25444af84998a48f261e5cddd92e06d5fc7efb7b00f9933afaf47daa
+oid sha256:7aba221a3d579504169f52262fd70ea8a121a9f4e1c6f1fd186ede35abfbe5fe
 size 163912

ner/moves

@@ -1 +1 @@
-��moves�
+��moves�

tagger/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b0ae90f765f0c0201596b5aab08d92d55f55f4afc45caa5355754d2b029502e
+oid sha256:461db1e078111078173d225b54ffabd42ad232623f2dcf885ce021825852e07e
 size 105978

tok2vec/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c084fd57008cccf20a57ad9d78848ba1a041db525d076b662c0ad6186b9ad4c
+oid sha256:5e68cf632c7b7e0720b53ee8c470444f0f69e01ec4044babcce83294c0e02d9d
 size 6009091

vocab/strings.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c44723e3986900b1fa2c5008767f07ada9f3ac3a58a52c6bd57451fab44a894a
-size 6614948
+oid sha256:2397c5f890da06f450cc9102a3d46437e4927baf67e92c6e0b502c9add35a474
+size 6614972