Update spaCy pipeline

README.md

@@ -4,6 +4,7 @@ tags:
 - token-classification
 language:
 - en
+license: mit
 model-index:
 - name: en_docusco_spacy
   results:
@@ -13,43 +14,45 @@ model-index:
     metrics:
     - name: NER Precision
       type: precision
-      value: 0.7498327416
+      value: 0.7905337091
     - name: NER Recall
       type: recall
-      value: 0.7475641104
+      value: 0.7900620784
     - name: NER F Score
       type: f_score
-      value: 0.7486967075
+      value: 0.7902978234
   - task:
       name: TAG
       type: token-classification
     metrics:
     - name: TAG (XPOS) Accuracy
       type: accuracy
-      value: 0.9249740665
+      value: 0.9421614376
 ---
+English pipeline for part-of-speech and rhetorical tagging.
+
 | Feature | Description |
 | --- | --- |
 | **Name** | `en_docusco_spacy` |
-| **Version** | `0.2` |
-| **spaCy** | `>=3.3.0,<3.4.0` |
-| **Default Pipeline** | `tok2vec`, `ner`, `tagger` |
-| **Components** | `tok2vec`, `ner`, `tagger` |
+| **Version** | `1.1` |
+| **spaCy** | `>=3.5.0,<3.6.0` |
+| **Default Pipeline** | `tok2vec`, `tagger`, `ner` |
+| **Components** | `tok2vec`, `tagger`, `ner` |
 | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
 | **Sources** | n/a |
-| **License** | n/a |
-| **Author** | [n/a]() |
+| **License** | `MIT` |
+| **Author** | [David Brown](https://docuscope.github.io) |
 
 ### Label Scheme
 
 <details>
 
-<summary>View label scheme (311 labels for 2 components)</summary>
+<summary>View label scheme (308 labels for 2 components)</summary>
 
 | Component | Labels |
 | --- | --- |
-| **`ner`** | `AcademicTerms`, `AcademicWritingMoves`, `Character`, `Citation`, `CitationAuthority`, `CitationHedged`, `ConfidenceHedged`, `ConfidenceHigh`, `ConfidenceLow`, `Contingent`, `Description`, `Facilitate`, `FirstPerson`, `ForceStressed`, `Future`, `InformationChange`, `InformationChangeNegative`, `InformationChangePositive`, `InformationExposition`, `InformationPlace`, `InformationReportVerbs`, `InformationStates`, `InformationTopics`, `Inquiry`, `Interactive`, `MetadiscourseCohesive`, `MetadiscourseInteractive`, `Narrative`, `Negative`, `Positive`, `PublicTerms`, `Reasoning`, `Responsibility`, `Strategic`, `SyntacticComplexity`, `Uncertainty`, `Updates` |
-| **`tagger`** | `APPGE`, `AT`, `AT1`, `BCL21`, `BCL22`, `CC`, `CCB`, `CS`, `CS21`, `CS22`, `CS31`, `CS32`, `CS33`, `CS41`, `CS42`, `CS43`, `CS44`, `CSA`, `CSN`, `CST`, `CSW`, `CSW31`, `CSW32`, `CSW33`, `DA`, `DA1`, `DA2`, `DAR`, `DAT`, `DB`, `DB2`, `DD`, `DD1`, `DD2`, `DDQ`, `DDQGE`, `DDQGE31`, `DDQGE32`, `DDQGE33`, `DDQV`, `DDQV31`, `DDQV32`, `DDQV33`, `EX`, `FO`, `FU`, `FW`, `GE`, `IF`, `II`, `II21`, `II22`, `II31`, `II32`, `II33`, `II41`, `II42`, `II43`, `II44`, `IO`, `IW`, `JJ`, `JJ21`, `JJ22`, `JJ31`, `JJ32`, `JJ33`, `JJ41`, `JJ42`, `JJ43`, `JJ44`, `JJR`, `JJT`, `JK`, `MC`, `MC1`, `MC2`, `MC221`, `MC222`, `MCMC`, `MD`, `MF`, `ND1`, `NN`, `NN1`, `NN121`, `NN122`, `NN131`, `NN132`, `NN133`, `NN141`, `NN142`, `NN143`, `NN144`, `NN2`, `NN21`, `NN22`, `NN221`, `NN222`, `NN231`, `NN232`, `NN233`, `NN31`, `NN32`, `NN33`, `NNA`, `NNB`, `NNL1`, `NNL2`, `NNO`, `NNO2`, `NNT1`, `NNT131`, `NNT132`, `NNT133`, `NNT2`, `NNU`, `NNU1`, `NNU2`, `NNU21`, `NNU22`, `NP`, `NP1`, `NP2`, `NPD1`, `NPD2`, `NPM1`, `NPM2`, `PN`, `PN1`, `PN121`, `PN122`, `PN21`, `PN22`, `PNQO`, `PNQS`, `PNQS31`, `PNQS32`, `PNQS33`, `PNQV`, `PNQV31`, `PNQV32`, `PNQV33`, `PNX1`, `PPGE`, `PPH1`, `PPHO1`, `PPHO2`, `PPHS1`, `PPHS2`, `PPIO1`, `PPIO2`, `PPIS1`, `PPIS2`, `PPX1`, `PPX121`, `PPX122`, `PPX2`, `PPX221`, `PPX222`, `PPY`, `RA`, `RA21`, `RA22`, `REX`, `REX21`, `REX22`, `REX41`, `REX42`, `REX43`, `REX44`, `RG`, `RG21`, `RG22`, `RG31`, `RG32`, `RG33`, `RG41`, `RG42`, `RG43`, `RG44`, `RGQ`, `RGQV`, `RGQV31`, `RGQV32`, `RGQV33`, `RGR`, `RGT`, `RL`, `RL21`, `RL22`, `RL31`, `RL32`, `RL33`, `RP`, `RPK`, `RR`, `RR21`, `RR22`, `RR31`, `RR32`, `RR33`, `RR41`, `RR42`, `RR43`, `RR44`, `RR51`, `RR52`, `RR53`, `RR54`, `RR55`, `RRQ`, `RRQV`, `RRQV31`, `RRQV32`, `RRQV33`, `RRR`, `RRT`, `RT`, `RT21`, `RT22`, `RT31`, `RT32`, `RT33`, `RT41`, `RT42`, `RT43`, `RT44`, `TO`, `UH`, `UH21`, `UH22`, `UH31`, `UH32`, `UH33`, `VB0`, `VBDR`, `VBDZ`, `VBG`, `VBI`, `VBM`, `VBN`, `VBR`, `VBZ`, `VD0`, `VDD`, `VDG`, `VDI`, `VDN`, `VDZ`, `VH0`, `VHD`, `VHG`, `VHI`, `VHN`, `VHZ`, `VM`, `VM21`, `VM22`, `VMK`, `VV0`, `VVD`, `VVG`, `VVGK`, `VVI`, `VVN`, `VVNK`, `VVZ`, `XX`, `Y`, `ZZ1`, `ZZ2`, `ZZ221`, `ZZ222` |
+| **`tagger`** | `APPGE`, `AT`, `AT1`, `BCL21`, `BCL22`, `CC`, `CCB`, `CS`, `CS21`, `CS22`, `CS31`, `CS32`, `CS33`, `CS41`, `CS42`, `CS43`, `CS44`, `CSA`, `CSN`, `CST`, `CSW`, `CSW31`, `CSW32`, `CSW33`, `DA`, `DA1`, `DA2`, `DAR`, `DAT`, `DB`, `DB2`, `DD`, `DD1`, `DD2`, `DDQ`, `DDQGE`, `DDQGE31`, `DDQGE32`, `DDQGE33`, `DDQV`, `DDQV31`, `DDQV32`, `DDQV33`, `EX`, `FO`, `FU`, `FW`, `GE`, `IF`, `II`, `II21`, `II22`, `II31`, `II32`, `II33`, `II41`, `II42`, `II43`, `II44`, `IO`, `IW`, `JJ`, `JJ21`, `JJ22`, `JJ31`, `JJ32`, `JJ33`, `JJ41`, `JJ42`, `JJ43`, `JJ44`, `JJR`, `JJT`, `JK`, `MC`, `MC1`, `MC2`, `MC221`, `MC222`, `MCMC`, `MD`, `MF`, `ND1`, `NN`, `NN1`, `NN121`, `NN122`, `NN131`, `NN132`, `NN133`, `NN141`, `NN142`, `NN143`, `NN144`, `NN2`, `NN21`, `NN22`, `NN221`, `NN222`, `NN231`, `NN232`, `NN233`, `NN31`, `NN32`, `NN33`, `NNA`, `NNB`, `NNL1`, `NNL2`, `NNO`, `NNO2`, `NNT1`, `NNT131`, `NNT133`, `NNT2`, `NNU`, `NNU1`, `NNU2`, `NNU21`, `NNU22`, `NNU221`, `NNU222`, `NP`, `NP1`, `NP2`, `NPD1`, `NPD2`, `NPM1`, `NPM2`, `PN`, `PN1`, `PN121`, `PN122`, `PN21`, `PN22`, `PNQO`, `PNQS`, `PNQS31`, `PNQS32`, `PNQS33`, `PNQV`, `PNQV31`, `PNQV32`, `PNQV33`, `PNX1`, `PPGE`, `PPH1`, `PPHO1`, `PPHO2`, `PPHS1`, `PPHS2`, `PPIO1`, `PPIO2`, `PPIS1`, `PPIS2`, `PPX1`, `PPX121`, `PPX122`, `PPX2`, `PPX221`, `PPX222`, `PPY`, `RA`, `RA21`, `RA22`, `REX`, `REX21`, `REX22`, `REX41`, `REX42`, `REX43`, `REX44`, `RG`, `RG21`, `RG22`, `RG41`, `RG42`, `RG43`, `RG44`, `RGQ`, `RGQV`, `RGQV31`, `RGQV32`, `RGQV33`, `RGR`, `RGT`, `RL`, `RL21`, `RL22`, `RL31`, `RL32`, `RL33`, `RP`, `RPK`, `RR`, `RR21`, `RR22`, `RR31`, `RR32`, `RR33`, `RR41`, `RR42`, `RR43`, `RR44`, `RR51`, `RR52`, `RR53`, `RR54`, `RR55`, `RRQ`, `RRQV`, `RRQV31`, `RRQV32`, `RRQV33`, `RRR`, `RRT`, `RT`, `RT21`, `RT22`, `RT31`, `RT32`, `RT33`, `RT41`, `RT42`, `RT43`, `RT44`, `TO`, `UH`, `UH21`, `UH22`, `UH31`, `UH32`, `UH33`, `VB0`, `VBDR`, `VBDZ`, `VBG`, `VBI`, `VBM`, `VBN`, `VBR`, `VBZ`, `VD0`, `VDD`, `VDG`, `VDI`, `VDN`, `VDZ`, `VH0`, `VHD`, `VHG`, `VHI`, `VHN`, `VHZ`, `VM`, `VM21`, `VM22`, `VMK`, `VV0`, `VVD`, `VVG`, `VVGK`, `VVI`, `VVN`, `VVNK`, `VVZ`, `XX`, `Y`, `ZZ1`, `ZZ2`, `ZZ221`, `ZZ222` |
+| **`ner`** | `AcademicTerms`, `AcademicWritingMoves`, `Character`, `Citation`, `CitationAuthority`, `CitationHedged`, `ConfidenceHedged`, `ConfidenceHigh`, `ConfidenceLow`, `Contingent`, `Description`, `Facilitate`, `FirstPerson`, `ForceStressed`, `Future`, `InformationChange`, `InformationChangeNegative`, `InformationChangePositive`, `InformationExposition`, `InformationPlace`, `InformationReportVerbs`, `InformationStates`, `InformationTopics`, `Inquiry`, `Interactive`, `MetadiscourseCohesive`, `MetadiscourseInteractive`, `Narrative`, `Negative`, `Positive`, `PublicTerms`, `Reasoning`, `Responsibility`, `Strategic`, `Uncertainty`, `Updates` |
 
 </details>
 
@@ -57,10 +60,10 @@ model-index:
 
 | Type | Score |
 | --- | --- |
-| `ENTS_F` | 74.87 |
-| `ENTS_P` | 74.98 |
-| `ENTS_R` | 74.76 |
-| `TAG_ACC` | 92.50 |
-| `TOK2VEC_LOSS` | 9919092.94 |
-| `NER_LOSS` | 6441655.97 |
-| `TAGGER_LOSS` | 2474292.88 |
+| `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 |

config.cfg

@@ -1,6 +1,6 @@
 [paths]
-train = "spacy_train.spacy"
-dev = "spacy_dev.spacy"
+train = ""
+dev = ""
 vectors = null
 init_tok2vec = null
 
@@ -10,7 +10,7 @@ seed = 0
 
 [nlp]
 lang = "en"
-pipeline = ["tok2vec","ner","tagger"]
+pipeline = ["tok2vec","tagger","ner"]
 batch_size = 1000
 disabled = []
 before_creation = null
@@ -66,8 +66,8 @@ factory = "tok2vec"
 [components.tok2vec.model.embed]
 @architectures = "spacy.MultiHashEmbed.v2"
 width = ${components.tok2vec.model.encode.width}
-attrs = ["ORTH","SHAPE"]
-rows = [5000,2500]
+attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
+rows = [5000,1000,2500,2500]
 include_static_vectors = false
 
 [components.tok2vec.model.encode]
@@ -104,11 +104,12 @@ dropout = 0.1
 accumulate_gradient = 1
 patience = 1600
 max_epochs = 0
-max_steps = 20000
-eval_frequency = 200
+max_steps = 35000
+eval_frequency = 250
 frozen_components = []
 annotating_components = []
 before_to_disk = null
+before_update = null
 
 [training.batcher]
 @batchers = "spacy.batch_by_words.v1"
@@ -139,11 +140,11 @@ eps = 0.00000001
 learn_rate = 0.001
 
 [training.score_weights]
+tag_acc = 0.5
 ents_f = 0.5
 ents_p = 0.0
 ents_r = 0.0
 ents_per_type = null
-tag_acc = 0.5
 
 [pretraining]
 
@@ -157,4 +158,18 @@ after_init = null
 
 [initialize.components]
 
+[initialize.components.ner]
+
+[initialize.components.ner.labels]
+@readers = "spacy.read_labels.v1"
+path = "ner.json"
+require = false
+
+[initialize.components.tagger]
+
+[initialize.components.tagger.labels]
+@readers = "spacy.read_labels.v1"
+path = "tagger.json"
+require = false
+
 [initialize.tokenizer]

en_docusco_spacy-any-py3-none-any.whl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:443d5b1a4188a40e0c1de56e0c9551a97b5b05b013fe995a842ba1840a4dafb0
-size 6415723
+oid sha256:80c2d7b616cb187c038261e93ca7996e3e5b67adfb6fc1a81d26b8700c5b4c8c
+size 7501766

meta.json

@@ -1,13 +1,13 @@
 {
   "lang":"en",
   "name":"docusco_spacy",
-  "version":"0.2",
-  "description":"",
-  "author":"",
-  "email":"",
-  "url":"",
-  "license":"",
-  "spacy_version":">=3.3.0,<3.4.0",
+  "version":"1.1",
+  "description":"English pipeline for part-of-speech and rhetorical tagging.",
+  "author":"David Brown",
+  "email":"dwb2@andrew.cmu.edu",
+  "url":"https://docuscope.github.io",
+  "license":"MIT",
+  "spacy_version":">=3.5.0,<3.6.0",
   "spacy_git_version":"Unknown",
   "vectors":{
     "width":0,
@@ -18,45 +18,6 @@
   "labels":{
     "tok2vec":[
 
-    ],
-    "ner":[
-      "AcademicTerms",
-      "AcademicWritingMoves",
-      "Character",
-      "Citation",
-      "CitationAuthority",
-      "CitationHedged",
-      "ConfidenceHedged",
-      "ConfidenceHigh",
-      "ConfidenceLow",
-      "Contingent",
-      "Description",
-      "Facilitate",
-      "FirstPerson",
-      "ForceStressed",
-      "Future",
-      "InformationChange",
-      "InformationChangeNegative",
-      "InformationChangePositive",
-      "InformationExposition",
-      "InformationPlace",
-      "InformationReportVerbs",
-      "InformationStates",
-      "InformationTopics",
-      "Inquiry",
-      "Interactive",
-      "MetadiscourseCohesive",
-      "MetadiscourseInteractive",
-      "Narrative",
-      "Negative",
-      "Positive",
-      "PublicTerms",
-      "Reasoning",
-      "Responsibility",
-      "Strategic",
-      "SyntacticComplexity",
-      "Uncertainty",
-      "Updates"
     ],
     "tagger":[
       "APPGE",
@@ -172,7 +133,6 @@
       "NNO2",
       "NNT1",
       "NNT131",
-      "NNT132",
       "NNT133",
       "NNT2",
       "NNU",
@@ -180,6 +140,8 @@
       "NNU2",
       "NNU21",
       "NNU22",
+      "NNU221",
+      "NNU222",
       "NP",
       "NP1",
       "NP2",
@@ -233,9 +195,6 @@
       "RG",
       "RG21",
       "RG22",
-      "RG31",
-      "RG32",
-      "RG33",
       "RG41",
       "RG42",
       "RG43",
@@ -333,216 +292,249 @@
       "ZZ2",
       "ZZ221",
       "ZZ222"
+    ],
+    "ner":[
+      "AcademicTerms",
+      "AcademicWritingMoves",
+      "Character",
+      "Citation",
+      "CitationAuthority",
+      "CitationHedged",
+      "ConfidenceHedged",
+      "ConfidenceHigh",
+      "ConfidenceLow",
+      "Contingent",
+      "Description",
+      "Facilitate",
+      "FirstPerson",
+      "ForceStressed",
+      "Future",
+      "InformationChange",
+      "InformationChangeNegative",
+      "InformationChangePositive",
+      "InformationExposition",
+      "InformationPlace",
+      "InformationReportVerbs",
+      "InformationStates",
+      "InformationTopics",
+      "Inquiry",
+      "Interactive",
+      "MetadiscourseCohesive",
+      "MetadiscourseInteractive",
+      "Narrative",
+      "Negative",
+      "Positive",
+      "PublicTerms",
+      "Reasoning",
+      "Responsibility",
+      "Strategic",
+      "Uncertainty",
+      "Updates"
     ]
   },
   "pipeline":[
     "tok2vec",
-    "ner",
-    "tagger"
+    "tagger",
+    "ner"
   ],
   "components":[
     "tok2vec",
-    "ner",
-    "tagger"
+    "tagger",
+    "ner"
   ],
   "disabled":[
 
   ],
   "performance":{
-    "ents_f":0.7486967075,
-    "ents_p":0.7498327416,
-    "ents_r":0.7475641104,
+    "tag_acc":0.9421614376,
+    "ents_f":0.7902978234,
+    "ents_p":0.7905337091,
+    "ents_r":0.7900620784,
     "ents_per_type":{
-      "Narrative":{
-        "p":0.7509423361,
-        "r":0.7103704114,
-        "f":0.7300931537
-      },
-      "SyntacticComplexity":{
-        "p":0.7886246175,
-        "r":0.8646070539,
-        "f":0.8248697614
-      },
-      "Character":{
-        "p":0.785967443,
-        "r":0.7897207251,
-        "f":0.7878396139
+      "Contingent":{
+        "p":0.8194101982,
+        "r":0.7684054754,
+        "f":0.7930886354
       },
-      "ConfidenceHigh":{
-        "p":0.7023789438,
-        "r":0.7254298327,
-        "f":0.7137183187
+      "InformationExposition":{
+        "p":0.8408782638,
+        "r":0.8514455432,
+        "f":0.8461289112
       },
-      "FirstPerson":{
-        "p":0.8278481013,
-        "r":0.8889566978,
-        "f":0.8573148383
+      "AcademicTerms":{
+        "p":0.7917226257,
+        "r":0.8269208748,
+        "f":0.8089390481
       },
-      "Negative":{
-        "p":0.658557511,
-        "r":0.583953954,
-        "f":0.6190160386
+      "ForceStressed":{
+        "p":0.7889513438,
+        "r":0.7872918493,
+        "f":0.7881207229
       },
-      "Description":{
-        "p":0.6476571898,
-        "r":0.6760073115,
-        "f":0.6615286505
+      "Character":{
+        "p":0.8428886221,
+        "r":0.8535599516,
+        "f":0.8481907234
       },
-      "InformationExposition":{
-        "p":0.7949913335,
-        "r":0.8201482322,
-        "f":0.8073738649
+      "Narrative":{
+        "p":0.7941775374,
+        "r":0.7763194725,
+        "f":0.7851469732
       },
       "Strategic":{
-        "p":0.6668451911,
-        "r":0.622929668,
-        "f":0.6441397901
-      },
-      "ConfidenceHedged":{
-        "p":0.8015741286,
-        "r":0.8440072161,
-        "f":0.8222435809
+        "p":0.7283594711,
+        "r":0.7014251342,
+        "f":0.7146386076
       },
-      "Interactive":{
-        "p":0.7874628485,
-        "r":0.8065506265,
-        "f":0.7968924527
+      "MetadiscourseInteractive":{
+        "p":0.8314383172,
+        "r":0.6715646883,
+        "f":0.7429986664
       },
-      "InformationReportVerbs":{
-        "p":0.7481178396,
-        "r":0.7079138919,
-        "f":0.7274608101
+      "Negative":{
+        "p":0.7079502122,
+        "r":0.6883289496,
+        "f":0.6980017167
       },
-      "ForceStressed":{
-        "p":0.7539183667,
-        "r":0.7242613439,
-        "f":0.7387923478
+      "Facilitate":{
+        "p":0.7118275675,
+        "r":0.6680265171,
+        "f":0.6892318485
       },
-      "AcademicTerms":{
-        "p":0.7375272228,
-        "r":0.7532883043,
-        "f":0.7453244495
+      "Interactive":{
+        "p":0.8448483369,
+        "r":0.8406692585,
+        "f":0.8427536169
       },
       "MetadiscourseCohesive":{
-        "p":0.904598282,
-        "r":0.9147441302,
-        "f":0.9096429161
+        "p":0.9115467032,
+        "r":0.9314739034,
+        "f":0.9214025743
       },
-      "InformationPlace":{
-        "p":0.8304918033,
-        "r":0.8436303081,
-        "f":0.8370095002
-      },
-      "Positive":{
-        "p":0.6864356164,
-        "r":0.5833436218,
-        "f":0.6307046557
-      },
-      "Citation":{
-        "p":0.7408448066,
-        "r":0.7192216767,
-        "f":0.7298731257
+      "Description":{
+        "p":0.718241746,
+        "r":0.762914221,
+        "f":0.7399043103
       },
       "PublicTerms":{
-        "p":0.7523439934,
-        "r":0.7137098941,
-        "f":0.7325178924
-      },
-      "CitationAuthority":{
-        "p":0.7350628931,
-        "r":0.4909425046,
-        "f":0.5886982528
+        "p":0.8216885583,
+        "r":0.7849799683,
+        "f":0.8029149109
       },
       "Reasoning":{
-        "p":0.8164492458,
-        "r":0.7225796753,
-        "f":0.76665178
+        "p":0.8353065446,
+        "r":0.7942001088,
+        "f":0.8142348449
+      },
+      "Positive":{
+        "p":0.7350608922,
+        "r":0.6682026769,
+        "f":0.7000390613
+      },
+      "Updates":{
+        "p":0.7852616757,
+        "r":0.7358698043,
+        "f":0.759763851
       },
       "InformationTopics":{
-        "p":0.7416131335,
-        "r":0.7561374001,
-        "f":0.7488048431
+        "p":0.8050484915,
+        "r":0.8124731572,
+        "f":0.8087437842
       },
-      "Responsibility":{
-        "p":0.6843984291,
-        "r":0.4750929368,
-        "f":0.5608543008
+      "ConfidenceHigh":{
+        "p":0.729696785,
+        "r":0.783668794,
+        "f":0.7557203724
       },
-      "Updates":{
-        "p":0.7556217827,
-        "r":0.6524994151,
-        "f":0.7002845665
+      "Citation":{
+        "p":0.7883380426,
+        "r":0.7925112976,
+        "f":0.7904191617
       },
-      "InformationStates":{
-        "p":0.7582508535,
-        "r":0.8421234057,
-        "f":0.7979893297
+      "Uncertainty":{
+        "p":0.7364028777,
+        "r":0.6471927162,
+        "f":0.688921793
       },
       "InformationChange":{
-        "p":0.6703578762,
-        "r":0.6338672769,
-        "f":0.6516020957
+        "p":0.715477206,
+        "r":0.7237081775,
+        "f":0.7195691545
       },
-      "Contingent":{
-        "p":0.7394308387,
-        "r":0.7160649222,
-        "f":0.7275603271
+      "InformationReportVerbs":{
+        "p":0.7432557524,
+        "r":0.8043649374,
+        "f":0.7726038695
       },
-      "MetadiscourseInteractive":{
-        "p":0.7715463918,
-        "r":0.6160684886,
-        "f":0.6850970341
+      "InformationStates":{
+        "p":0.7881446908,
+        "r":0.8930611381,
+        "f":0.8373292341
       },
-      "Future":{
-        "p":0.7021050535,
-        "r":0.6896034438,
-        "f":0.6957980981
+      "ConfidenceHedged":{
+        "p":0.8401550734,
+        "r":0.8841205084,
+        "f":0.8615772774
       },
-      "Inquiry":{
-        "p":0.5940041831,
-        "r":0.5108253947,
-        "f":0.5492836676
+      "FirstPerson":{
+        "p":0.8702371032,
+        "r":0.8930348259,
+        "f":0.8814885862
       },
-      "Uncertainty":{
-        "p":0.6979017644,
-        "r":0.5465919701,
-        "f":0.6130484868
+      "Responsibility":{
+        "p":0.7245780156,
+        "r":0.6123869172,
+        "f":0.6637752216
       },
-      "AcademicWritingMoves":{
-        "p":0.5667743673,
-        "r":0.42723767,
-        "f":0.4872121282
+      "Inquiry":{
+        "p":0.672815534,
+        "r":0.5904572565,
+        "f":0.6289517471
       },
       "InformationChangeNegative":{
-        "p":0.6899070385,
-        "r":0.4249488753,
-        "f":0.5259427993
+        "p":0.6999255398,
+        "r":0.5277933745,
+        "f":0.6017925736
       },
-      "Facilitate":{
-        "p":0.6855355281,
-        "r":0.5659124447,
-        "f":0.6200067363
+      "ConfidenceLow":{
+        "p":0.796812749,
+        "r":0.4750593824,
+        "f":0.5952380952
       },
-      "InformationChangePositive":{
-        "p":0.7209653092,
-        "r":0.4085470085,
-        "f":0.5215493726
+      "InformationPlace":{
+        "p":0.8673478574,
+        "r":0.8999579655,
+        "f":0.8833520526
       },
-      "ConfidenceLow":{
-        "p":0.751572327,
-        "r":0.4127806563,
-        "f":0.5328874025
+      "Future":{
+        "p":0.7551444043,
+        "r":0.757468767,
+        "f":0.7563047998
+      },
+      "AcademicWritingMoves":{
+        "p":0.7072072072,
+        "r":0.4272108844,
+        "f":0.5326547922
       },
       "CitationHedged":{
-        "p":0.7021276596,
-        "r":0.9328621908,
-        "f":0.8012139605
+        "p":0.7910447761,
+        "r":0.9098712446,
+        "f":0.8463073852
+      },
+      "CitationAuthority":{
+        "p":0.7478653943,
+        "r":0.5558044046,
+        "f":0.6376873662
+      },
+      "InformationChangePositive":{
+        "p":0.7891513561,
+        "r":0.5254879114,
+        "f":0.6308795244
       }
     },
-    "tag_acc":0.9249740665,
-    "tok2vec_loss":99190.9293975094,
-    "ner_loss":64416.5596667872,
-    "tagger_loss":24742.9288185574
+    "tok2vec_loss":179393.8503061496,
+    "tagger_loss":23980.277885437,
+    "ner_loss":59873.5843254536
   },
   "requirements":[
 

ner/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d056afe6ac62c1b4455b4418bb51fb2860d465e64b2bb09fd2ce8087b81bf0d6
-size 164952
+oid sha256:9cc11bb5c791bd15c71cccc36896b4851429cd7a428da01ddbebdee8a30c31b0
+size 163912

ner/moves

@@ -1 +1 @@
-��moves�
+��moves�

tagger/cfg

@@ -113,7 +113,6 @@
     "NNO2",
     "NNT1",
     "NNT131",
-    "NNT132",
     "NNT133",
     "NNT2",
     "NNU",
@@ -121,6 +120,8 @@
     "NNU2",
     "NNU21",
     "NNU22",
+    "NNU221",
+    "NNU222",
     "NP",
     "NP1",
     "NP2",
@@ -174,9 +175,6 @@
     "RG",
     "RG21",
     "RG22",
-    "RG31",
-    "RG32",
-    "RG33",
     "RG41",
     "RG42",
     "RG43",

tagger/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:082fdb2ef45d5a5956b0e6b75136ea58e3b385f3b7dd8553f3a4cf2948fa63a9
-size 106754
+oid sha256:1983965d07e1d71cc442defe9818cff84461b64be4d239558dabed5a3dffeeee
+size 105978

tok2vec/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32b3d9da5e1b1c7d218e12e3ca5acb0ce17645c696ac2385cc56951d9492c2b7
-size 4443194
+oid sha256:05e2cfc9fcdbf023345f8cd6c80f291f13961dd7b5b233b5793d5b4754a0ac74
+size 6009091

vocab/strings.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0d0b3cc2098ae111e5a0391aeb7f1b783e85f167d1fdb277933af2fd934308a
-size 8084734
+oid sha256:c44723e3986900b1fa2c5008767f07ada9f3ac3a58a52c6bd57451fab44a894a
+size 6614948