Update spaCy pipeline

.gitattributes

@@ -19,3 +19,4 @@
 *strings.json filter=lfs diff=lfs merge=lfs -text
 vectors filter=lfs diff=lfs merge=lfs -text
 model filter=lfs diff=lfs merge=lfs -text
+*key2row filter=lfs diff=lfs merge=lfs -text

README.md

@@ -14,47 +14,41 @@ model-index:
     metrics:
     - name: NER Precision
       type: precision
-      value: 0.8574246409
+      value: 0.8602117695
     - name: NER Recall
       type: recall
-      value: 0.8490084135
+      value: 0.8462540064
     - name: NER F Score
       type: f_score
-      value: 0.8531957725
+      value: 0.8531758053
   - task:
-      name: POS
+      name: TAG
       type: token-classification
     metrics:
-    - name: POS Accuracy
+    - name: TAG (XPOS) Accuracy
       type: accuracy
-      value: 0.9741780493
+      value: 0.9738145328
   - task:
-      name: SENTER
+      name: UNLABELED_DEPENDENCIES
       type: token-classification
     metrics:
-    - name: SENTER Precision
-      type: precision
-      value: 0.9179358172
-    - name: SENTER Recall
-      type: recall
-      value: 0.8906260307
-    - name: SENTER F Score
+    - name: Unlabeled Attachment Score (UAS)
       type: f_score
-      value: 0.9040747313
+      value: 0.9188508811
   - task:
-      name: UNLABELED_DEPENDENCIES
+      name: LABELED_DEPENDENCIES
       type: token-classification
     metrics:
-    - name: Unlabeled Dependencies Accuracy
-      type: accuracy
-      value: 0.9200593914
+    - name: Labeled Attachment Score (LAS)
+      type: f_score
+      value: 0.9008477499
   - task:
-      name: LABELED_DEPENDENCIES
+      name: SENTS
       type: token-classification
     metrics:
-    - name: Labeled Dependencies Accuracy
-      type: accuracy
-      value: 0.9200593914
+    - name: Sentences F-Score
+      type: f_score
+      value: 0.9033533215
 ---
 ### Details: https://spacy.io/models/en#en_core_web_lg
 
@@ -63,11 +57,11 @@ English pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter,
 | Feature | Description |
 | --- | --- |
 | **Name** | `en_core_web_lg` |
-| **Version** | `3.2.0` |
-| **spaCy** | `>=3.2.0,<3.3.0` |
+| **Version** | `3.3.0` |
+| **spaCy** | `>=3.3.0.dev0,<3.4.0` |
 | **Default Pipeline** | `tok2vec`, `tagger`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
 | **Components** | `tok2vec`, `tagger`, `parser`, `senter`, `attribute_ruler`, `lemmatizer`, `ner` |
-| **Vectors** | 684830 keys, 684830 unique vectors (300 dimensions) |
+| **Vectors** | 684830 keys, 342918 unique vectors (300 dimensions) |
 | **Sources** | [OntoNotes 5](https://catalog.ldc.upenn.edu/LDC2013T19) (Ralph Weischedel, Martha Palmer, Mitchell Marcus, Eduard Hovy, Sameer Pradhan, Lance Ramshaw, Nianwen Xue, Ann Taylor, Jeff Kaufman, Michelle Franchini, Mohammed El-Bachouti, Robert Belvin, Ann Houston)<br />[ClearNLP Constituent-to-Dependency Conversion](https://github.com/clir/clearnlp-guidelines/blob/master/md/components/dependency_conversion.md) (Emory University)<br />[WordNet 3.0](https://wordnet.princeton.edu/) (Princeton University)<br />[GloVe Common Crawl](https://nlp.stanford.edu/projects/glove/) (Jeffrey Pennington, Richard Socher, and Christopher D. Manning) |
 | **License** | `MIT` |
 | **Author** | [Explosion](https://explosion.ai) |
@@ -76,13 +70,12 @@ English pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter,
 
 <details>
 
-<summary>View label scheme (114 labels for 4 components)</summary>
+<summary>View label scheme (112 labels for 3 components)</summary>
 
 | Component | Labels |
 | --- | --- |
 | **`tagger`** | `$`, `''`, `,`, `-LRB-`, `-RRB-`, `.`, `:`, `ADD`, `AFX`, `CC`, `CD`, `DT`, `EX`, `FW`, `HYPH`, `IN`, `JJ`, `JJR`, `JJS`, `LS`, `MD`, `NFP`, `NN`, `NNP`, `NNPS`, `NNS`, `PDT`, `POS`, `PRP`, `PRP$`, `RB`, `RBR`, `RBS`, `RP`, `SYM`, `TO`, `UH`, `VB`, `VBD`, `VBG`, `VBN`, `VBP`, `VBZ`, `WDT`, `WP`, `WP$`, `WRB`, `XX`, ```` |
 | **`parser`** | `ROOT`, `acl`, `acomp`, `advcl`, `advmod`, `agent`, `amod`, `appos`, `attr`, `aux`, `auxpass`, `case`, `cc`, `ccomp`, `compound`, `conj`, `csubj`, `csubjpass`, `dative`, `dep`, `det`, `dobj`, `expl`, `intj`, `mark`, `meta`, `neg`, `nmod`, `npadvmod`, `nsubj`, `nsubjpass`, `nummod`, `oprd`, `parataxis`, `pcomp`, `pobj`, `poss`, `preconj`, `predet`, `prep`, `prt`, `punct`, `quantmod`, `relcl`, `xcomp` |
-| **`senter`** | `I`, `S` |
 | **`ner`** | `CARDINAL`, `DATE`, `EVENT`, `FAC`, `GPE`, `LANGUAGE`, `LAW`, `LOC`, `MONEY`, `NORP`, `ORDINAL`, `ORG`, `PERCENT`, `PERSON`, `PRODUCT`, `QUANTITY`, `TIME`, `WORK_OF_ART` |
 
 </details>
@@ -95,12 +88,12 @@ English pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter,
 | `TOKEN_P` | 99.57 |
 | `TOKEN_R` | 99.58 |
 | `TOKEN_F` | 99.57 |
-| `TAG_ACC` | 97.42 |
-| `SENTS_P` | 91.79 |
-| `SENTS_R` | 89.06 |
-| `SENTS_F` | 90.41 |
-| `DEP_UAS` | 92.01 |
-| `DEP_LAS` | 90.22 |
-| `ENTS_P` | 85.74 |
-| `ENTS_R` | 84.90 |
+| `TAG_ACC` | 97.38 |
+| `SENTS_P` | 91.77 |
+| `SENTS_R` | 88.94 |
+| `SENTS_F` | 90.34 |
+| `DEP_UAS` | 91.89 |
+| `DEP_LAS` | 90.08 |
+| `ENTS_P` | 86.02 |
+| `ENTS_R` | 84.63 |
 | `ENTS_F` | 85.32 |

accuracy.json

@@ -1,229 +1,229 @@
 {
-  "token_acc": 0.9993053983,
-  "token_p": 0.9956742163,
-  "token_r": 0.9957505887,
-  "token_f": 0.9957124011,
-  "tag_acc": 0.9741780493,
-  "sents_p": 0.9179358172,
-  "sents_r": 0.8906260307,
-  "sents_f": 0.9040747313,
-  "dep_uas": 0.9200593914,
-  "dep_las": 0.9021556352,
+  "token_acc": 0.9993092439,
+  "token_p": 0.9956819193,
+  "token_r": 0.9957659295,
+  "token_f": 0.9957239226,
+  "tag_acc": 0.9738145328,
+  "sents_p": 0.9177103185,
+  "sents_r": 0.8894386173,
+  "sents_f": 0.9033533215,
+  "dep_uas": 0.9188508811,
+  "dep_las": 0.9008477499,
   "dep_las_per_type": {
     "prep": {
-      "p": 0.8578239976,
-      "r": 0.8669702144,
-      "f": 0.8623728558
+      "p": 0.8537864878,
+      "r": 0.8645418327,
+      "f": 0.8591305004
     },
     "det": {
-      "p": 0.9798012706,
-      "r": 0.9809997554,
-      "f": 0.9804001467
+      "p": 0.9790682522,
+      "r": 0.9802658403,
+      "f": 0.9796666802
     },
     "pobj": {
-      "p": 0.9617211838,
-      "r": 0.9698409582,
-      "f": 0.9657640043
+      "p": 0.9633579437,
+      "r": 0.9684272531,
+      "f": 0.965885947
     },
     "nsubj": {
-      "p": 0.9608471258,
-      "r": 0.9461555312,
-      "f": 0.9534447363
+      "p": 0.9564757243,
+      "r": 0.9502738226,
+      "f": 0.9533646873
     },
     "aux": {
-      "p": 0.9807231056,
-      "r": 0.9828184813,
-      "f": 0.9817696754
+      "p": 0.9809760868,
+      "r": 0.9823733642,
+      "f": 0.9816742283
     },
     "advmod": {
-      "p": 0.8600169779,
-      "r": 0.8523472993,
-      "f": 0.8561649624
+      "p": 0.8550492715,
+      "r": 0.8541140838,
+      "f": 0.8545814218
     },
     "relcl": {
-      "p": 0.755259467,
-      "r": 0.7815674891,
-      "f": 0.7681883024
+      "p": 0.7709000356,
+      "r": 0.7862844702,
+      "f": 0.7785162565
     },
     "root": {
-      "p": 0.9196325281,
-      "r": 0.8914836071,
-      "f": 0.905339318
+      "p": 0.9183576195,
+      "r": 0.889702487,
+      "f": 0.9038029821
     },
     "xcomp": {
-      "p": 0.8886906885,
-      "r": 0.8941134243,
-      "f": 0.8913938093
+      "p": 0.882620883,
+      "r": 0.9041636755,
+      "f": 0.8932624113
     },
     "amod": {
-      "p": 0.9216490817,
-      "r": 0.9168124393,
-      "f": 0.9192243983
+      "p": 0.9195970101,
+      "r": 0.9166180758,
+      "f": 0.9181051265
     },
     "compound": {
-      "p": 0.9188224309,
-      "r": 0.9316662954,
-      "f": 0.9251997898
+      "p": 0.9193539526,
+      "r": 0.9320004455,
+      "f": 0.9256340054
     },
     "poss": {
-      "p": 0.9760755931,
-      "r": 0.9772544283,
-      "f": 0.976664655
+      "p": 0.9711422846,
+      "r": 0.9754428341,
+      "f": 0.9732878088
     },
     "ccomp": {
-      "p": 0.7797340326,
-      "r": 0.8478615071,
-      "f": 0.8123719387
+      "p": 0.7727868239,
+      "r": 0.8409368635,
+      "f": 0.8054228031
     },
     "attr": {
-      "p": 0.8931845357,
-      "r": 0.9423885618,
-      "f": 0.9171270718
+      "p": 0.8955042527,
+      "r": 0.9297729184,
+      "f": 0.912316897
     },
     "case": {
-      "p": 0.9782823297,
-      "r": 0.991991992,
-      "f": 0.9850894632
+      "p": 0.9758144126,
+      "r": 0.9894894895,
+      "f": 0.9826043738
     },
     "mark": {
-      "p": 0.9105669417,
-      "r": 0.9064652888,
-      "f": 0.9085114859
+      "p": 0.9062829989,
+      "r": 0.9096449391,
+      "f": 0.9079608569
     },
     "intj": {
-      "p": 0.6737089202,
-      "r": 0.6307692308,
-      "f": 0.6515323496
+      "p": 0.6653322658,
+      "r": 0.6087912088,
+      "f": 0.635807192
     },
     "advcl": {
-      "p": 0.67003282,
-      "r": 0.6683455049,
-      "f": 0.6691880988
+      "p": 0.6779661017,
+      "r": 0.6648199446,
+      "f": 0.6713286713
     },
     "cc": {
-      "p": 0.8372232916,
-      "r": 0.8323167085,
-      "f": 0.8347627901
+      "p": 0.8292624233,
+      "r": 0.824303313,
+      "f": 0.8267754319
     },
     "neg": {
-      "p": 0.9408548708,
-      "r": 0.9498243853,
-      "f": 0.9453183521
+      "p": 0.9393336648,
+      "r": 0.9478173608,
+      "f": 0.9435564436
     },
     "conj": {
-      "p": 0.7653624433,
-      "r": 0.7854984894,
-      "f": 0.7752997453
+      "p": 0.763665795,
+      "r": 0.7720292044,
+      "f": 0.7678247261
     },
     "nsubjpass": {
-      "p": 0.9327377824,
-      "r": 0.9102564103,
-      "f": 0.9213599792
+      "p": 0.9263266358,
+      "r": 0.9220512821,
+      "f": 0.9241840144
     },
     "auxpass": {
-      "p": 0.9543624161,
-      "r": 0.9717539863,
-      "f": 0.962979684
+      "p": 0.9499329459,
+      "r": 0.9681093394,
+      "f": 0.9589350181
     },
     "dobj": {
-      "p": 0.9222826087,
-      "r": 0.9466092916,
-      "f": 0.9342876244
+      "p": 0.926432648,
+      "r": 0.9442983505,
+      "f": 0.9352801894
     },
     "nummod": {
-      "p": 0.9430395913,
-      "r": 0.9323232323,
-      "f": 0.9376507937
+      "p": 0.9362134689,
+      "r": 0.9303030303,
+      "f": 0.9332488917
     },
     "npadvmod": {
-      "p": 0.7866254349,
-      "r": 0.7229129663,
-      "f": 0.7534246575
+      "p": 0.7723030982,
+      "r": 0.734991119,
+      "f": 0.753185293
     },
     "prt": {
-      "p": 0.8190082645,
-      "r": 0.8879928315,
-      "f": 0.8521066208
+      "p": 0.8160066007,
+      "r": 0.8862007168,
+      "f": 0.8496563574
     },
     "pcomp": {
-      "p": 0.879020979,
-      "r": 0.8802521008,
-      "f": 0.8796361092
+      "p": 0.8800841515,
+      "r": 0.8788515406,
+      "f": 0.8794674142
     },
     "expl": {
-      "p": 0.9809725159,
-      "r": 0.9935760171,
-      "f": 0.9872340426
+      "p": 0.9809322034,
+      "r": 0.9914346895,
+      "f": 0.9861554846
     },
     "acl": {
-      "p": 0.7443997702,
-      "r": 0.7070376432,
-      "f": 0.7252378288
+      "p": 0.7556456283,
+      "r": 0.7119476268,
+      "f": 0.7331460674
     },
     "agent": {
-      "p": 0.8928571429,
-      "r": 0.9408602151,
-      "f": 0.9162303665
+      "p": 0.8991452991,
+      "r": 0.9426523297,
+      "f": 0.9203849519
     },
     "dative": {
-      "p": 0.7729591837,
-      "r": 0.6949541284,
-      "f": 0.731884058
+      "p": 0.810298103,
+      "r": 0.6857798165,
+      "f": 0.7428571429
     },
     "acomp": {
-      "p": 0.9102505695,
-      "r": 0.906122449,
-      "f": 0.9081818182
+      "p": 0.9111721612,
+      "r": 0.9024943311,
+      "f": 0.9068124858
     },
     "dep": {
-      "p": 0.4491525424,
-      "r": 0.1720779221,
-      "f": 0.2488262911
+      "p": 0.3930131004,
+      "r": 0.1461038961,
+      "f": 0.2130177515
     },
     "csubj": {
-      "p": 0.7243589744,
-      "r": 0.6686390533,
-      "f": 0.6953846154
+      "p": 0.7068965517,
+      "r": 0.7278106509,
+      "f": 0.7172011662
     },
     "quantmod": {
-      "p": 0.8686779059,
-      "r": 0.7952883834,
-      "f": 0.8303647159
+      "p": 0.8746594005,
+      "r": 0.7822908205,
+      "f": 0.8259005146
     },
     "nmod": {
-      "p": 0.76,
-      "r": 0.5789152956,
-      "f": 0.6572120374
+      "p": 0.7651217596,
+      "r": 0.5935405241,
+      "f": 0.6684969115
     },
     "appos": {
-      "p": 0.7035040431,
-      "r": 0.6793926247,
-      "f": 0.6912381373
+      "p": 0.6994459834,
+      "r": 0.6572668113,
+      "f": 0.6777007381
     },
     "predet": {
-      "p": 0.8300395257,
-      "r": 0.9012875536,
-      "f": 0.8641975309
+      "p": 0.8380566802,
+      "r": 0.8884120172,
+      "f": 0.8625
     },
     "preconj": {
-      "p": 0.5784313725,
-      "r": 0.6860465116,
-      "f": 0.6276595745
+      "p": 0.537037037,
+      "r": 0.6744186047,
+      "f": 0.5979381443
     },
     "oprd": {
-      "p": 0.8379310345,
-      "r": 0.7253731343,
-      "f": 0.7776
+      "p": 0.8477508651,
+      "r": 0.7313432836,
+      "f": 0.7852564103
     },
     "parataxis": {
-      "p": 0.6312849162,
-      "r": 0.4902386117,
-      "f": 0.5518925519
+      "p": 0.6187845304,
+      "r": 0.4859002169,
+      "f": 0.5443499392
     },
     "meta": {
-      "p": 0.7647058824,
-      "r": 0.25,
-      "f": 0.3768115942
+      "p": 1.0,
+      "r": 0.3269230769,
+      "f": 0.4927536232
     },
     "csubjpass": {
       "p": 0.5555555556,
@@ -231,100 +231,100 @@
       "f": 0.6666666667
     }
   },
-  "ents_p": 0.8574246409,
-  "ents_r": 0.8490084135,
-  "ents_f": 0.8531957725,
+  "ents_p": 0.8602117695,
+  "ents_r": 0.8462540064,
+  "ents_f": 0.8531758053,
   "ents_per_type": {
     "DATE": {
-      "p": 0.8695102686,
-      "r": 0.8736507937,
-      "f": 0.8715756136
+      "p": 0.872593068,
+      "r": 0.8631746032,
+      "f": 0.8678582828
     },
     "GPE": {
-      "p": 0.9231641622,
-      "r": 0.9082287308,
-      "f": 0.9156355456
+      "p": 0.9257256688,
+      "r": 0.9073919107,
+      "f": 0.916467108
     },
     "ORDINAL": {
-      "p": 0.7971428571,
-      "r": 0.8664596273,
-      "f": 0.8303571429
+      "p": 0.787965616,
+      "r": 0.8540372671,
+      "f": 0.8196721311
     },
     "ORG": {
-      "p": 0.8194444444,
-      "r": 0.8290031813,
-      "f": 0.8241960991
-    },
-    "QUANTITY": {
-      "p": 0.7959183673,
-      "r": 0.6428571429,
-      "f": 0.7112462006
+      "p": 0.8203309693,
+      "r": 0.8279427359,
+      "f": 0.8241192769
     },
     "CARDINAL": {
-      "p": 0.8221709007,
-      "r": 0.8466111772,
-      "f": 0.834212068
+      "p": 0.8304398148,
+      "r": 0.8531510107,
+      "f": 0.8416422287
     },
     "PERSON": {
-      "p": 0.8823895457,
-      "r": 0.9255874674,
-      "f": 0.9034724435
+      "p": 0.8953229399,
+      "r": 0.9184073107,
+      "f": 0.9067182214
     },
     "NORP": {
-      "p": 0.9027888446,
-      "r": 0.9064,
-      "f": 0.9045908184
+      "p": 0.8794048551,
+      "r": 0.8984,
+      "f": 0.8888009497
     },
     "LOC": {
-      "p": 0.7185185185,
-      "r": 0.6178343949,
-      "f": 0.6643835616
+      "p": 0.7147766323,
+      "r": 0.6624203822,
+      "f": 0.6876033058
     },
     "FAC": {
-      "p": 0.4263565891,
-      "r": 0.4230769231,
-      "f": 0.4247104247
+      "p": 0.3949579832,
+      "r": 0.3615384615,
+      "f": 0.3775100402
     },
     "TIME": {
-      "p": 0.7396825397,
-      "r": 0.6812865497,
-      "f": 0.7092846271
+      "p": 0.71875,
+      "r": 0.6725146199,
+      "f": 0.6948640483
     },
-    "PRODUCT": {
-      "p": 0.6022727273,
-      "r": 0.2511848341,
-      "f": 0.3545150502
+    "QUANTITY": {
+      "p": 0.8014184397,
+      "r": 0.6208791209,
+      "f": 0.6996904025
     },
     "EVENT": {
-      "p": 0.5882352941,
-      "r": 0.2873563218,
-      "f": 0.3861003861
+      "p": 0.6354166667,
+      "r": 0.3505747126,
+      "f": 0.4518518519
     },
     "WORK_OF_ART": {
-      "p": 0.4692307692,
-      "r": 0.3144329897,
-      "f": 0.3765432099
-    },
-    "LAW": {
-      "p": 0.5272727273,
-      "r": 0.453125,
-      "f": 0.487394958
+      "p": 0.5,
+      "r": 0.3092783505,
+      "f": 0.3821656051
     },
     "MONEY": {
-      "p": 0.8990498812,
-      "r": 0.893742621,
-      "f": 0.8963883955
+      "p": 0.9039145907,
+      "r": 0.8996458087,
+      "f": 0.9017751479
+    },
+    "LAW": {
+      "p": 0.6428571429,
+      "r": 0.421875,
+      "f": 0.5094339623
     },
     "PERCENT": {
-      "p": 0.9202551834,
+      "p": 0.9187898089,
       "r": 0.8836140888,
-      "f": 0.9015625
+      "f": 0.9008587041
     },
     "LANGUAGE": {
-      "p": 0.8,
-      "r": 0.625,
-      "f": 0.701754386
+      "p": 0.75,
+      "r": 0.65625,
+      "f": 0.7
+    },
+    "PRODUCT": {
+      "p": 0.6097560976,
+      "r": 0.2369668246,
+      "f": 0.3412969283
     }
   },
-  "speed": 7471.5995598921
+  "speed": 7281.6726563626
 }

config.cfg

@@ -55,7 +55,7 @@ nO = null
 @architectures = "spacy.MultiHashEmbed.v2"
 width = 96
 attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
-rows = [5000,2500,2500,2500,100]
+rows = [5000,1000,2500,2500,50]
 include_static_vectors = true
 
 [components.ner.model.tok2vec.encode]
@@ -93,8 +93,9 @@ overwrite = false
 scorer = {"@scorers":"spacy.senter_scorer.v1"}
 
 [components.senter.model]
-@architectures = "spacy.Tagger.v1"
+@architectures = "spacy.Tagger.v2"
 nO = null
+normalize = false
 
 [components.senter.model.tok2vec]
 @architectures = "spacy.Tok2Vec.v2"
@@ -115,12 +116,14 @@ maxout_pieces = 2
 
 [components.tagger]
 factory = "tagger"
+neg_prefix = "!"
 overwrite = false
 scorer = {"@scorers":"spacy.tagger_scorer.v1"}
 
 [components.tagger.model]
-@architectures = "spacy.Tagger.v1"
+@architectures = "spacy.Tagger.v2"
 nO = null
+normalize = false
 
 [components.tagger.model.tok2vec]
 @architectures = "spacy.Tok2VecListener.v1"
@@ -137,7 +140,7 @@ factory = "tok2vec"
 @architectures = "spacy.MultiHashEmbed.v2"
 width = ${components.tok2vec.model.encode:width}
 attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
-rows = [5000,2500,2500,2500,100]
+rows = [5000,1000,2500,2500,50]
 include_static_vectors = true
 
 [components.tok2vec.model.encode]
@@ -174,7 +177,7 @@ dropout = 0.1
 accumulate_gradient = 1
 patience = 5000
 max_epochs = 0
-max_steps = 0
+max_steps = 100000
 eval_frequency = 1000
 frozen_components = []
 before_to_disk = null

en_core_web_lg-any-py3-none-any.whl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae37a39df924099ea9e9d9d4d2912bbed9c534089c9f5f3ac0a3564ca7815521
-size 777382778
+oid sha256:6ce19d37dfe5280400f80a5954d41afca10cbc742b97bfcf4b0e452b6eb24273
+size 400651786

meta.json

@@ -1,17 +1,17 @@
 {
   "lang":"en",
   "name":"core_web_lg",
-  "version":"3.2.0",
+  "version":"3.3.0",
   "description":"English pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter, ner, attribute_ruler, lemmatizer.",
   "author":"Explosion",
   "email":"[email protected]",
   "url":"https://explosion.ai",
   "license":"MIT",
-  "spacy_version":">=3.2.0,<3.3.0",
-  "spacy_git_version":"bb26550e2",
+  "spacy_version":">=3.3.0.dev0,<3.4.0",
+  "spacy_git_version":"849bef2de",
   "vectors":{
     "width":300,
-    "vectors":684830,
+    "vectors":342918,
     "keys":684830,
     "name":"en_vectors"
   },
@@ -117,10 +117,6 @@
       "relcl",
       "xcomp"
     ],
-    "senter":[
-      "I",
-      "S"
-    ],
     "attribute_ruler":[
 
     ],
@@ -169,231 +165,231 @@
     "senter"
   ],
   "performance":{
-    "token_acc":0.9993053983,
-    "token_p":0.9956742163,
-    "token_r":0.9957505887,
-    "token_f":0.9957124011,
-    "tag_acc":0.9741780493,
-    "sents_p":0.9179358172,
-    "sents_r":0.8906260307,
-    "sents_f":0.9040747313,
-    "dep_uas":0.9200593914,
-    "dep_las":0.9021556352,
+    "token_acc":0.9993092439,
+    "token_p":0.9956819193,
+    "token_r":0.9957659295,
+    "token_f":0.9957239226,
+    "tag_acc":0.9738145328,
+    "sents_p":0.9177103185,
+    "sents_r":0.8894386173,
+    "sents_f":0.9033533215,
+    "dep_uas":0.9188508811,
+    "dep_las":0.9008477499,
     "dep_las_per_type":{
       "prep":{
-        "p":0.8578239976,
-        "r":0.8669702144,
-        "f":0.8623728558
+        "p":0.8537864878,
+        "r":0.8645418327,
+        "f":0.8591305004
       },
       "det":{
-        "p":0.9798012706,
-        "r":0.9809997554,
-        "f":0.9804001467
+        "p":0.9790682522,
+        "r":0.9802658403,
+        "f":0.9796666802
       },
       "pobj":{
-        "p":0.9617211838,
-        "r":0.9698409582,
-        "f":0.9657640043
+        "p":0.9633579437,
+        "r":0.9684272531,
+        "f":0.965885947
       },
       "nsubj":{
-        "p":0.9608471258,
-        "r":0.9461555312,
-        "f":0.9534447363
+        "p":0.9564757243,
+        "r":0.9502738226,
+        "f":0.9533646873
       },
       "aux":{
-        "p":0.9807231056,
-        "r":0.9828184813,
-        "f":0.9817696754
+        "p":0.9809760868,
+        "r":0.9823733642,
+        "f":0.9816742283
       },
       "advmod":{
-        "p":0.8600169779,
-        "r":0.8523472993,
-        "f":0.8561649624
+        "p":0.8550492715,
+        "r":0.8541140838,
+        "f":0.8545814218
       },
       "relcl":{
-        "p":0.755259467,
-        "r":0.7815674891,
-        "f":0.7681883024
+        "p":0.7709000356,
+        "r":0.7862844702,
+        "f":0.7785162565
       },
       "root":{
-        "p":0.9196325281,
-        "r":0.8914836071,
-        "f":0.905339318
+        "p":0.9183576195,
+        "r":0.889702487,
+        "f":0.9038029821
       },
       "xcomp":{
-        "p":0.8886906885,
-        "r":0.8941134243,
-        "f":0.8913938093
+        "p":0.882620883,
+        "r":0.9041636755,
+        "f":0.8932624113
       },
       "amod":{
-        "p":0.9216490817,
-        "r":0.9168124393,
-        "f":0.9192243983
+        "p":0.9195970101,
+        "r":0.9166180758,
+        "f":0.9181051265
       },
       "compound":{
-        "p":0.9188224309,
-        "r":0.9316662954,
-        "f":0.9251997898
+        "p":0.9193539526,
+        "r":0.9320004455,
+        "f":0.9256340054
       },
       "poss":{
-        "p":0.9760755931,
-        "r":0.9772544283,
-        "f":0.976664655
+        "p":0.9711422846,
+        "r":0.9754428341,
+        "f":0.9732878088
       },
       "ccomp":{
-        "p":0.7797340326,
-        "r":0.8478615071,
-        "f":0.8123719387
+        "p":0.7727868239,
+        "r":0.8409368635,
+        "f":0.8054228031
       },
       "attr":{
-        "p":0.8931845357,
-        "r":0.9423885618,
-        "f":0.9171270718
+        "p":0.8955042527,
+        "r":0.9297729184,
+        "f":0.912316897
       },
       "case":{
-        "p":0.9782823297,
-        "r":0.991991992,
-        "f":0.9850894632
+        "p":0.9758144126,
+        "r":0.9894894895,
+        "f":0.9826043738
       },
       "mark":{
-        "p":0.9105669417,
-        "r":0.9064652888,
-        "f":0.9085114859
+        "p":0.9062829989,
+        "r":0.9096449391,
+        "f":0.9079608569
       },
       "intj":{
-        "p":0.6737089202,
-        "r":0.6307692308,
-        "f":0.6515323496
+        "p":0.6653322658,
+        "r":0.6087912088,
+        "f":0.635807192
       },
       "advcl":{
-        "p":0.67003282,
-        "r":0.6683455049,
-        "f":0.6691880988
+        "p":0.6779661017,
+        "r":0.6648199446,
+        "f":0.6713286713
       },
       "cc":{
-        "p":0.8372232916,
-        "r":0.8323167085,
-        "f":0.8347627901
+        "p":0.8292624233,
+        "r":0.824303313,
+        "f":0.8267754319
       },
       "neg":{
-        "p":0.9408548708,
-        "r":0.9498243853,
-        "f":0.9453183521
+        "p":0.9393336648,
+        "r":0.9478173608,
+        "f":0.9435564436
       },
       "conj":{
-        "p":0.7653624433,
-        "r":0.7854984894,
-        "f":0.7752997453
+        "p":0.763665795,
+        "r":0.7720292044,
+        "f":0.7678247261
       },
       "nsubjpass":{
-        "p":0.9327377824,
-        "r":0.9102564103,
-        "f":0.9213599792
+        "p":0.9263266358,
+        "r":0.9220512821,
+        "f":0.9241840144
       },
       "auxpass":{
-        "p":0.9543624161,
-        "r":0.9717539863,
-        "f":0.962979684
+        "p":0.9499329459,
+        "r":0.9681093394,
+        "f":0.9589350181
       },
       "dobj":{
-        "p":0.9222826087,
-        "r":0.9466092916,
-        "f":0.9342876244
+        "p":0.926432648,
+        "r":0.9442983505,
+        "f":0.9352801894
       },
       "nummod":{
-        "p":0.9430395913,
-        "r":0.9323232323,
-        "f":0.9376507937
+        "p":0.9362134689,
+        "r":0.9303030303,
+        "f":0.9332488917
       },
       "npadvmod":{
-        "p":0.7866254349,
-        "r":0.7229129663,
-        "f":0.7534246575
+        "p":0.7723030982,
+        "r":0.734991119,
+        "f":0.753185293
       },
       "prt":{
-        "p":0.8190082645,
-        "r":0.8879928315,
-        "f":0.8521066208
+        "p":0.8160066007,
+        "r":0.8862007168,
+        "f":0.8496563574
       },
       "pcomp":{
-        "p":0.879020979,
-        "r":0.8802521008,
-        "f":0.8796361092
+        "p":0.8800841515,
+        "r":0.8788515406,
+        "f":0.8794674142
       },
       "expl":{
-        "p":0.9809725159,
-        "r":0.9935760171,
-        "f":0.9872340426
+        "p":0.9809322034,
+        "r":0.9914346895,
+        "f":0.9861554846
       },
       "acl":{
-        "p":0.7443997702,
-        "r":0.7070376432,
-        "f":0.7252378288
+        "p":0.7556456283,
+        "r":0.7119476268,
+        "f":0.7331460674
       },
       "agent":{
-        "p":0.8928571429,
-        "r":0.9408602151,
-        "f":0.9162303665
+        "p":0.8991452991,
+        "r":0.9426523297,
+        "f":0.9203849519
       },
       "dative":{
-        "p":0.7729591837,
-        "r":0.6949541284,
-        "f":0.731884058
+        "p":0.810298103,
+        "r":0.6857798165,
+        "f":0.7428571429
       },
       "acomp":{
-        "p":0.9102505695,
-        "r":0.906122449,
-        "f":0.9081818182
+        "p":0.9111721612,
+        "r":0.9024943311,
+        "f":0.9068124858
       },
       "dep":{
-        "p":0.4491525424,
-        "r":0.1720779221,
-        "f":0.2488262911
+        "p":0.3930131004,
+        "r":0.1461038961,
+        "f":0.2130177515
       },
       "csubj":{
-        "p":0.7243589744,
-        "r":0.6686390533,
-        "f":0.6953846154
+        "p":0.7068965517,
+        "r":0.7278106509,
+        "f":0.7172011662
       },
       "quantmod":{
-        "p":0.8686779059,
-        "r":0.7952883834,
-        "f":0.8303647159
+        "p":0.8746594005,
+        "r":0.7822908205,
+        "f":0.8259005146
       },
       "nmod":{
-        "p":0.76,
-        "r":0.5789152956,
-        "f":0.6572120374
+        "p":0.7651217596,
+        "r":0.5935405241,
+        "f":0.6684969115
       },
       "appos":{
-        "p":0.7035040431,
-        "r":0.6793926247,
-        "f":0.6912381373
+        "p":0.6994459834,
+        "r":0.6572668113,
+        "f":0.6777007381
       },
       "predet":{
-        "p":0.8300395257,
-        "r":0.9012875536,
-        "f":0.8641975309
+        "p":0.8380566802,
+        "r":0.8884120172,
+        "f":0.8625
       },
       "preconj":{
-        "p":0.5784313725,
-        "r":0.6860465116,
-        "f":0.6276595745
+        "p":0.537037037,
+        "r":0.6744186047,
+        "f":0.5979381443
       },
       "oprd":{
-        "p":0.8379310345,
-        "r":0.7253731343,
-        "f":0.7776
+        "p":0.8477508651,
+        "r":0.7313432836,
+        "f":0.7852564103
       },
       "parataxis":{
-        "p":0.6312849162,
-        "r":0.4902386117,
-        "f":0.5518925519
+        "p":0.6187845304,
+        "r":0.4859002169,
+        "f":0.5443499392
       },
       "meta":{
-        "p":0.7647058824,
-        "r":0.25,
-        "f":0.3768115942
+        "p":1.0,
+        "r":0.3269230769,
+        "f":0.4927536232
       },
       "csubjpass":{
         "p":0.5555555556,
@@ -401,102 +397,102 @@
         "f":0.6666666667
       }
     },
-    "ents_p":0.8574246409,
-    "ents_r":0.8490084135,
-    "ents_f":0.8531957725,
+    "ents_p":0.8602117695,
+    "ents_r":0.8462540064,
+    "ents_f":0.8531758053,
     "ents_per_type":{
       "DATE":{
-        "p":0.8695102686,
-        "r":0.8736507937,
-        "f":0.8715756136
+        "p":0.872593068,
+        "r":0.8631746032,
+        "f":0.8678582828
       },
       "GPE":{
-        "p":0.9231641622,
-        "r":0.9082287308,
-        "f":0.9156355456
+        "p":0.9257256688,
+        "r":0.9073919107,
+        "f":0.916467108
       },
       "ORDINAL":{
-        "p":0.7971428571,
-        "r":0.8664596273,
-        "f":0.8303571429
+        "p":0.787965616,
+        "r":0.8540372671,
+        "f":0.8196721311
       },
       "ORG":{
-        "p":0.8194444444,
-        "r":0.8290031813,
-        "f":0.8241960991
-      },
-      "QUANTITY":{
-        "p":0.7959183673,
-        "r":0.6428571429,
-        "f":0.7112462006
+        "p":0.8203309693,
+        "r":0.8279427359,
+        "f":0.8241192769
       },
       "CARDINAL":{
-        "p":0.8221709007,
-        "r":0.8466111772,
-        "f":0.834212068
+        "p":0.8304398148,
+        "r":0.8531510107,
+        "f":0.8416422287
       },
       "PERSON":{
-        "p":0.8823895457,
-        "r":0.9255874674,
-        "f":0.9034724435
+        "p":0.8953229399,
+        "r":0.9184073107,
+        "f":0.9067182214
       },
       "NORP":{
-        "p":0.9027888446,
-        "r":0.9064,
-        "f":0.9045908184
+        "p":0.8794048551,
+        "r":0.8984,
+        "f":0.8888009497
       },
       "LOC":{
-        "p":0.7185185185,
-        "r":0.6178343949,
-        "f":0.6643835616
+        "p":0.7147766323,
+        "r":0.6624203822,
+        "f":0.6876033058
       },
       "FAC":{
-        "p":0.4263565891,
-        "r":0.4230769231,
-        "f":0.4247104247
+        "p":0.3949579832,
+        "r":0.3615384615,
+        "f":0.3775100402
       },
       "TIME":{
-        "p":0.7396825397,
-        "r":0.6812865497,
-        "f":0.7092846271
+        "p":0.71875,
+        "r":0.6725146199,
+        "f":0.6948640483
       },
-      "PRODUCT":{
-        "p":0.6022727273,
-        "r":0.2511848341,
-        "f":0.3545150502
+      "QUANTITY":{
+        "p":0.8014184397,
+        "r":0.6208791209,
+        "f":0.6996904025
       },
       "EVENT":{
-        "p":0.5882352941,
-        "r":0.2873563218,
-        "f":0.3861003861
+        "p":0.6354166667,
+        "r":0.3505747126,
+        "f":0.4518518519
       },
       "WORK_OF_ART":{
-        "p":0.4692307692,
-        "r":0.3144329897,
-        "f":0.3765432099
-      },
-      "LAW":{
-        "p":0.5272727273,
-        "r":0.453125,
-        "f":0.487394958
+        "p":0.5,
+        "r":0.3092783505,
+        "f":0.3821656051
       },
       "MONEY":{
-        "p":0.8990498812,
-        "r":0.893742621,
-        "f":0.8963883955
+        "p":0.9039145907,
+        "r":0.8996458087,
+        "f":0.9017751479
+      },
+      "LAW":{
+        "p":0.6428571429,
+        "r":0.421875,
+        "f":0.5094339623
       },
       "PERCENT":{
-        "p":0.9202551834,
+        "p":0.9187898089,
         "r":0.8836140888,
-        "f":0.9015625
+        "f":0.9008587041
       },
       "LANGUAGE":{
-        "p":0.8,
-        "r":0.625,
-        "f":0.701754386
+        "p":0.75,
+        "r":0.65625,
+        "f":0.7
+      },
+      "PRODUCT":{
+        "p":0.6097560976,
+        "r":0.2369668246,
+        "f":0.3412969283
       }
     },
-    "speed":7471.5995598921
+    "speed":7281.6726563626
   },
   "sources":[
     {

ner/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d39a012887e3db760ffe6c029e7f6327733a42bd4743475257a0306a8be3380
-size 7106353
+oid sha256:d9d8a97f17d882960a52360ae2e58d9c960937534c9c010e1d912a3b82767a8f
+size 6511153

parser/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e358731646a09000cce13f69498c7b129e8da3a3c94d407392b664fde7ea3e6e
+oid sha256:4b8abfdcfaa0d0a822556f61fa2ab7b48d5528e8ab25375e9c657af78d8e2368
 size 319909

parser/moves

@@ -1,2 +1,2 @@
 ��moves�
-{"0":{"":995932},"1":{"":989662},"2":{"det":172430,"nsubj":165679,"compound":116803,"amod":106128,"aux":87078,"punct":65505,"advmod":62711,"poss":36427,"mark":27913,"nummod":22583,"auxpass":15597,"prep":13989,"nsubjpass":13867,"neg":12358,"cc":10694,"nmod":9572,"advcl":9063,"npadvmod":8135,"quantmod":7071,"intj":6557,"ccomp":5899,"dobj":3427,"expl":3360,"dep":3191,"predet":1945,"parataxis":1826,"csubj":1431,"preconj":620,"pobj||prep":615,"attr":578,"meta":448,"advmod||conj":367,"dobj||xcomp":352,"acomp":284,"nsubj||ccomp":224,"dative":206,"advmod||xcomp":149,"dobj||ccomp":70,"csubjpass":64,"dobj||conj":62,"prep||conj":51,"acl":48,"prep||nsubj":41,"prep||dobj":36,"xcomp":34,"advmod||ccomp":32,"oprd":31},"3":{"punct":183437,"pobj":182256,"prep":173845,"dobj":89650,"conj":59689,"cc":51858,"ccomp":30404,"advmod":22820,"xcomp":21045,"relcl":20968,"advcl":19833,"attr":17739,"acomp":16824,"appos":14963,"case":13361,"acl":12091,"pcomp":10345,"npadvmod":9702,"prt":8179,"agent":3884,"dative":3867,"nsubj":3465,"intj":2898,"neg":2871,"amod":2843,"nummod":2510,"oprd":2304,"dep":1518,"parataxis":1261,"quantmod":317,"nmod":296,"acl||dobj":202,"prep||dobj":190,"prep||nsubj":162,"acl||nsubj":159,"appos||nsubj":145,"relcl||dobj":134,"relcl||nsubj":111,"aux":103,"expl":96,"meta":93,"appos||dobj":86,"preconj":71,"csubj":65,"prep||nsubjpass":55,"prep||advmod":54,"prep||acomp":53,"det":51,"nsubjpass":45,"acl||nsubjpass":42,"relcl||pobj":41,"mark":40,"auxpass":39,"prep||pobj":36,"relcl||nsubjpass":32,"appos||nsubjpass":31},"4":{"ROOT":110979}}�cfg��neg_key�
+{"0":{"":994267},"1":{"":990803},"2":{"det":172595,"nsubj":165748,"compound":116623,"amod":105184,"aux":86667,"punct":65478,"advmod":62763,"poss":36443,"mark":27941,"nummod":22598,"auxpass":15594,"prep":14001,"nsubjpass":13856,"neg":12357,"cc":10739,"nmod":9562,"advcl":9062,"npadvmod":8168,"quantmod":7101,"intj":6464,"ccomp":5896,"dobj":3427,"expl":3360,"dep":2806,"predet":1944,"parataxis":1837,"csubj":1428,"preconj":621,"pobj||prep":616,"attr":578,"meta":376,"advmod||conj":368,"dobj||xcomp":352,"acomp":284,"nsubj||ccomp":224,"dative":206,"advmod||xcomp":149,"dobj||ccomp":70,"csubjpass":64,"dobj||conj":62,"prep||conj":51,"acl":48,"prep||nsubj":41,"prep||dobj":36,"xcomp":34,"advmod||ccomp":32,"oprd":31},"3":{"punct":183790,"pobj":182191,"prep":174008,"dobj":89615,"conj":59687,"cc":51930,"ccomp":30385,"advmod":22861,"xcomp":21021,"relcl":20969,"advcl":19828,"attr":17741,"acomp":16922,"appos":15265,"case":13388,"acl":12085,"pcomp":10324,"npadvmod":9796,"prt":8179,"agent":3903,"dative":3866,"nsubj":3470,"neg":2906,"amod":2839,"intj":2819,"nummod":2732,"oprd":2301,"dep":1487,"parataxis":1261,"quantmod":319,"nmod":294,"acl||dobj":200,"prep||dobj":190,"prep||nsubj":162,"acl||nsubj":159,"appos||nsubj":145,"relcl||dobj":134,"relcl||nsubj":111,"aux":103,"expl":96,"meta":92,"appos||dobj":86,"preconj":71,"csubj":65,"prep||nsubjpass":55,"prep||advmod":54,"prep||acomp":53,"det":51,"nsubjpass":45,"relcl||pobj":42,"acl||nsubjpass":42,"mark":40,"auxpass":39,"prep||pobj":36,"relcl||nsubjpass":32,"appos||nsubjpass":31},"4":{"ROOT":111664}}�cfg��neg_key�

senter/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db1ce4e224f67005f7b94661e1856f5792f140896dfed59015bf9e5b12f6585e
-size 219901
+oid sha256:3a1bdccc5dc2d8c842081528c93680c54508411615b525cef695239f30bb0ed8
+size 219953

tagger/cfg

@@ -50,5 +50,6 @@
     "XX",
     "``"
   ],
+  "neg_prefix":"!",
   "overwrite":false
 }

tagger/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c4b0e2f0c6552bcead2c1da64ff46da4912ab273e24dbb14154702fd213190b
-size 19389
+oid sha256:4481bf82fdaea8773149ca8b637057e0dfaa4f8fa1cc5e8f19f33250568f6fc0
+size 19441

tok2vec/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0c6b29d6d78255e764d45f99bb4d4d594fd6e5709bf3cd62c3df00e702c442c
-size 6960804
+oid sha256:71724ee469b871ec2287455264d692c9b229b1bf129aa5bc06130a4aeb9b7c0e
+size 6365604

vocab/strings.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:266477264a21daaabda7d6b1200598290e20aaf2c72ebaf6e2a671f282f5e2bc
-size 9695169
+oid sha256:649ca580aed1f07d3b761fa73308bc96f72b78e8bd4d51140a3a920b3429ba10
+size 9694998

vocab/vectors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d90b9122eef03666021c0592972138a2d70f785920cdc86588b369ec327074a7
-size 821796128
+oid sha256:dd82f972c4fca3d440c505cdd94c88efdded56457cc86851d584b751f7dea673
+size 411501728