Update spaCy pipeline

README.md

@@ -14,27 +14,27 @@ model-index:
     metrics:
     - name: NER Precision
       type: precision
-      value: 0.7905337091
+      value: 0.7897948078
     - name: NER Recall
       type: recall
-      value: 0.7900620784
+      value: 0.7904761222
     - name: NER F Score
       type: f_score
-      value: 0.7902978234
+      value: 0.7901353181
   - task:
       name: TAG
       type: token-classification
     metrics:
     - name: TAG (XPOS) Accuracy
       type: accuracy
-      value: 0.9421614376
+      value: 0.9422182346
 ---
 English pipeline for part-of-speech and rhetorical tagging.
 
 | Feature | Description |
 | --- | --- |
 | **Name** | `en_docusco_spacy` |
-| **Version** | `1.1` |
+| **Version** | `1.2` |
 | **spaCy** | `>=3.5.0,<3.6.0` |
 | **Default Pipeline** | `tok2vec`, `tagger`, `ner` |
 | **Components** | `tok2vec`, `tagger`, `ner` |
@@ -61,9 +61,9 @@ English pipeline for part-of-speech and rhetorical tagging.
 | Type | Score |
 | --- | --- |
 | `TAG_ACC` | 94.22 |
-| `ENTS_F` | 79.03 |
-| `ENTS_P` | 79.05 |
-| `ENTS_R` | 79.01 |
-| `TOK2VEC_LOSS` | 17939385.03 |
-| `TAGGER_LOSS` | 2398027.79 |
-| `NER_LOSS` | 5987358.43 |
+| `ENTS_F` | 79.01 |
+| `ENTS_P` | 78.98 |
+| `ENTS_R` | 79.05 |
+| `TOK2VEC_LOSS` | 18044765.75 |
+| `TAGGER_LOSS` | 2400921.93 |
+| `NER_LOSS` | 5935848.19 |

config.cfg

@@ -1,6 +1,6 @@
 [paths]
-train = ""
-dev = ""
+train = "spacy_train_fd.spacy"
+dev = "spacy_test_fd.spacy"
 vectors = null
 init_tok2vec = null
 

en_docusco_spacy-any-py3-none-any.whl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80c2d7b616cb187c038261e93ca7996e3e5b67adfb6fc1a81d26b8700c5b4c8c
-size 7501766
+oid sha256:1d73aad65d669783246161c1be36f0be9001ee88c4b1fddce57311c8a8bc5030
+size 7502026

meta.json

@@ -1,7 +1,7 @@
 {
   "lang":"en",
   "name":"docusco_spacy",
-  "version":"1.1",
+  "version":"1.2",
   "description":"English pipeline for part-of-speech and rhetorical tagging.",
   "author":"David Brown",
   "email":"[email protected]",
@@ -346,195 +346,195 @@
 
   ],
   "performance":{
-    "tag_acc":0.9421614376,
-    "ents_f":0.7902978234,
-    "ents_p":0.7905337091,
-    "ents_r":0.7900620784,
+    "tag_acc":0.9422182346,
+    "ents_f":0.7901353181,
+    "ents_p":0.7897948078,
+    "ents_r":0.7904761222,
     "ents_per_type":{
       "Contingent":{
-        "p":0.8194101982,
-        "r":0.7684054754,
-        "f":0.7930886354
+        "p":0.8286840509,
+        "r":0.7583240844,
+        "f":0.791944364
       },
       "InformationExposition":{
-        "p":0.8408782638,
-        "r":0.8514455432,
-        "f":0.8461289112
+        "p":0.8400248832,
+        "r":0.8577633567,
+        "f":0.8488014542
       },
       "AcademicTerms":{
-        "p":0.7917226257,
-        "r":0.8269208748,
-        "f":0.8089390481
+        "p":0.7894026371,
+        "r":0.8286671247,
+        "f":0.8085584799
       },
       "ForceStressed":{
-        "p":0.7889513438,
-        "r":0.7872918493,
-        "f":0.7881207229
+        "p":0.7898256456,
+        "r":0.7841148116,
+        "f":0.7869598681
       },
       "Character":{
-        "p":0.8428886221,
-        "r":0.8535599516,
-        "f":0.8481907234
+        "p":0.8500444492,
+        "r":0.8432579053,
+        "f":0.8466375774
       },
       "Narrative":{
-        "p":0.7941775374,
-        "r":0.7763194725,
-        "f":0.7851469732
+        "p":0.7737338187,
+        "r":0.7965586415,
+        "f":0.7849803462
       },
       "Strategic":{
-        "p":0.7283594711,
-        "r":0.7014251342,
-        "f":0.7146386076
+        "p":0.7364217252,
+        "r":0.6996483435,
+        "f":0.7175642072
       },
       "MetadiscourseInteractive":{
-        "p":0.8314383172,
-        "r":0.6715646883,
-        "f":0.7429986664
-      },
-      "Negative":{
-        "p":0.7079502122,
-        "r":0.6883289496,
-        "f":0.6980017167
+        "p":0.8356010661,
+        "r":0.6838480083,
+        "f":0.7521464646
       },
       "Facilitate":{
-        "p":0.7118275675,
-        "r":0.6680265171,
-        "f":0.6892318485
+        "p":0.7088353414,
+        "r":0.6600373959,
+        "f":0.6835665874
+      },
+      "Negative":{
+        "p":0.7095155684,
+        "r":0.682564777,
+        "f":0.6957792879
       },
       "Interactive":{
-        "p":0.8448483369,
-        "r":0.8406692585,
-        "f":0.8427536169
+        "p":0.839874111,
+        "r":0.8383435157,
+        "f":0.8391081154
       },
       "MetadiscourseCohesive":{
-        "p":0.9115467032,
-        "r":0.9314739034,
-        "f":0.9214025743
+        "p":0.9192184725,
+        "r":0.9288534712,
+        "f":0.9240108556
       },
       "Description":{
-        "p":0.718241746,
-        "r":0.762914221,
-        "f":0.7399043103
+        "p":0.7208328088,
+        "r":0.7628920157,
+        "f":0.7412662853
       },
       "PublicTerms":{
-        "p":0.8216885583,
-        "r":0.7849799683,
-        "f":0.8029149109
+        "p":0.8309137834,
+        "r":0.778781465,
+        "f":0.8040034337
       },
       "Reasoning":{
-        "p":0.8353065446,
-        "r":0.7942001088,
-        "f":0.8142348449
+        "p":0.8395115952,
+        "r":0.7998493535,
+        "f":0.8192006857
       },
       "Positive":{
-        "p":0.7350608922,
-        "r":0.6682026769,
-        "f":0.7000390613
+        "p":0.7291883827,
+        "r":0.6821606119,
+        "f":0.7048909876
       },
       "Updates":{
-        "p":0.7852616757,
-        "r":0.7358698043,
-        "f":0.759763851
+        "p":0.7837246077,
+        "r":0.7084891137,
+        "f":0.7442102224
       },
       "InformationTopics":{
-        "p":0.8050484915,
-        "r":0.8124731572,
-        "f":0.8087437842
+        "p":0.7918713029,
+        "r":0.8200456611,
+        "f":0.8057122551
       },
       "ConfidenceHigh":{
-        "p":0.729696785,
-        "r":0.783668794,
-        "f":0.7557203724
+        "p":0.7615851193,
+        "r":0.7704958272,
+        "f":0.7660145605
       },
       "Citation":{
-        "p":0.7883380426,
-        "r":0.7925112976,
-        "f":0.7904191617
+        "p":0.8037907101,
+        "r":0.7775338928,
+        "f":0.7904443132
       },
-      "Uncertainty":{
-        "p":0.7364028777,
-        "r":0.6471927162,
-        "f":0.688921793
+      "ConfidenceHedged":{
+        "p":0.8374410068,
+        "r":0.8770594696,
+        "f":0.856792489
       },
       "InformationChange":{
-        "p":0.715477206,
-        "r":0.7237081775,
-        "f":0.7195691545
-      },
-      "InformationReportVerbs":{
-        "p":0.7432557524,
-        "r":0.8043649374,
-        "f":0.7726038695
+        "p":0.7123025371,
+        "r":0.7132585562,
+        "f":0.7127802261
       },
       "InformationStates":{
-        "p":0.7881446908,
-        "r":0.8930611381,
-        "f":0.8373292341
-      },
-      "ConfidenceHedged":{
-        "p":0.8401550734,
-        "r":0.8841205084,
-        "f":0.8615772774
+        "p":0.8041805777,
+        "r":0.8789930188,
+        "f":0.8399241946
       },
       "FirstPerson":{
-        "p":0.8702371032,
-        "r":0.8930348259,
-        "f":0.8814885862
+        "p":0.8766524888,
+        "r":0.8892257463,
+        "f":0.882894356
       },
       "Responsibility":{
-        "p":0.7245780156,
-        "r":0.6123869172,
-        "f":0.6637752216
+        "p":0.7242662257,
+        "r":0.6096033403,
+        "f":0.6620064236
       },
       "Inquiry":{
-        "p":0.672815534,
-        "r":0.5904572565,
-        "f":0.6289517471
+        "p":0.6661799979,
+        "r":0.6047524378,
+        "f":0.6339817388
       },
       "InformationChangeNegative":{
-        "p":0.6999255398,
-        "r":0.5277933745,
-        "f":0.6017925736
+        "p":0.6824946846,
+        "r":0.5407074677,
+        "f":0.6033834586
       },
       "ConfidenceLow":{
-        "p":0.796812749,
-        "r":0.4750593824,
-        "f":0.5952380952
+        "p":0.6462395543,
+        "r":0.5510688836,
+        "f":0.5948717949
       },
       "InformationPlace":{
-        "p":0.8673478574,
-        "r":0.8999579655,
-        "f":0.8833520526
+        "p":0.865587996,
+        "r":0.8944517093,
+        "f":0.8797831779
+      },
+      "InformationReportVerbs":{
+        "p":0.7508147746,
+        "r":0.7912701252,
+        "f":0.7705117932
       },
       "Future":{
-        "p":0.7551444043,
-        "r":0.757468767,
-        "f":0.7563047998
+        "p":0.756072781,
+        "r":0.7410827449,
+        "f":0.7485027202
       },
       "AcademicWritingMoves":{
-        "p":0.7072072072,
-        "r":0.4272108844,
-        "f":0.5326547922
+        "p":0.7083700441,
+        "r":0.4375510204,
+        "f":0.5409587889
+      },
+      "Uncertainty":{
+        "p":0.7549221275,
+        "r":0.6497218007,
+        "f":0.6983824929
       },
       "CitationHedged":{
-        "p":0.7910447761,
-        "r":0.9098712446,
-        "f":0.8463073852
+        "p":0.7483221477,
+        "r":0.9570815451,
+        "f":0.8399246704
       },
       "CitationAuthority":{
-        "p":0.7478653943,
-        "r":0.5558044046,
-        "f":0.6376873662
+        "p":0.7841151386,
+        "r":0.5490854797,
+        "f":0.6458836443
       },
       "InformationChangePositive":{
-        "p":0.7891513561,
-        "r":0.5254879114,
-        "f":0.6308795244
+        "p":0.7640586797,
+        "r":0.546169531,
+        "f":0.6369967725
       }
     },
-    "tok2vec_loss":179393.8503061496,
-    "tagger_loss":23980.277885437,
-    "ner_loss":59873.5843254536
+    "tok2vec_loss":180447.6574847773,
+    "tagger_loss":24009.219291687,
+    "ner_loss":59358.4819319265
   },
   "requirements":[
 

ner/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cc11bb5c791bd15c71cccc36896b4851429cd7a428da01ddbebdee8a30c31b0
+oid sha256:54dd874f25444af84998a48f261e5cddd92e06d5fc7efb7b00f9933afaf47daa
 size 163912

ner/moves

@@ -1 +1 @@
-��moves�
+��moves�

tagger/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1983965d07e1d71cc442defe9818cff84461b64be4d239558dabed5a3dffeeee
+oid sha256:6b0ae90f765f0c0201596b5aab08d92d55f55f4afc45caa5355754d2b029502e
 size 105978

tok2vec/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05e2cfc9fcdbf023345f8cd6c80f291f13961dd7b5b233b5793d5b4754a0ac74
+oid sha256:3c084fd57008cccf20a57ad9d78848ba1a041db525d076b662c0ad6186b9ad4c
 size 6009091