Update spaCy pipeline

README.md

@@ -13,42 +13,42 @@ model-index:
     metrics:
     - name: TAG (XPOS) Accuracy
       type: accuracy
-      value: 0.973255026
+      value: 0.9723063022
   - task:
       name: POS
       type: token-classification
     metrics:
     - name: POS (UPOS) Accuracy
       type: accuracy
-      value: 0.9719448837
+      value: 0.9717189971
   - task:
       name: MORPH
       type: token-classification
     metrics:
     - name: Morph (UFeats) Accuracy
       type: accuracy
-      value: 0.9470973571
+      value: 0.9466455839
   - task:
       name: LEMMA
       type: token-classification
     metrics:
     - name: Lemma Accuracy
       type: accuracy
-      value: 0.9687634105
+      value: 0.9714737436
   - task:
       name: UNLABELED_DEPENDENCIES
       type: token-classification
     metrics:
     - name: Unlabeled Attachment Score (UAS)
       type: f_score
-      value: 0.8300239687
+      value: 0.8278332829
   - task:
       name: LABELED_DEPENDENCIES
       type: token-classification
     metrics:
     - name: Labeled Attachment Score (LAS)
       type: f_score
-      value: 0.7853160086
+      value: 0.7808557877
   - task:
       name: SENTS
       type: token-classification
@@ -60,8 +60,8 @@ model-index:
 | Feature | Description |
 | --- | --- |
 | **Name** | `grc_perseus_trf` |
-| **Version** | `3.7` |
-| **spaCy** | `>=3.7.4,<3.8.0` |
+| **Version** | `3.7.5` |
+| **spaCy** | `>=3.7.5,<3.8.0` |
 | **Default Pipeline** | `transformer`, `morphologizer`, `tagger`, `senter`, `parser`, `lemmatizer`, `attribute_ruler` |
 | **Components** | `transformer`, `morphologizer`, `tagger`, `senter`, `parser`, `lemmatizer`, `attribute_ruler` |
 | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
@@ -87,17 +87,17 @@ model-index:
 
 | Type | Score |
 | --- | --- |
-| `POS_ACC` | 96.52 |
-| `MORPH_ACC` | 95.04 |
-| `TAG_ACC` | 96.60 |
+| `POS_ACC` | 97.17 |
+| `MORPH_ACC` | 94.66 |
+| `TAG_ACC` | 97.23 |
 | `SENTS_F` | 99.34 |
 | `SENTS_P` | 99.30 |
 | `SENTS_R` | 99.38 |
-| `DEP_UAS` | 81.72 |
-| `DEP_LAS` | 76.93 |
-| `LEMMA_ACC` | 97.23 |
-| `TRANSFORMER_LOSS` | 99065.36 |
-| `MORPHOLOGIZER_LOSS` | 7157.58 |
-| `TAGGER_LOSS` | 3968.99 |
-| `SENTER_LOSS` | 13391.75 |
-| `PARSER_LOSS` | 1908487.82 |
+| `DEP_UAS` | 82.78 |
+| `DEP_LAS` | 78.09 |
+| `LEMMA_ACC` | 97.15 |
+| `TRANSFORMER_LOSS` | 181871.36 |
+| `MORPHOLOGIZER_LOSS` | 20683.74 |
+| `TAGGER_LOSS` | 16994.14 |
+| `SENTER_LOSS` | 68301.80 |
+| `PARSER_LOSS` | 9682034.86 |

config.cfg

@@ -1,6 +1,6 @@
 [paths]
-train = "corpus/train/grc_perseus-ud-train.spacy"
-dev = "corpus/dev/grc_perseus-ud-dev.spacy"
+train = "corpus/parser/perseus/train/grc_perseus-ud-train.spacy"
+dev = "corpus/parser/perseus/dev/grc_perseus-ud-dev.spacy"
 vectors = null
 init_tok2vec = null
 
@@ -178,7 +178,7 @@ dropout = 0.1
 patience = 5000
 max_epochs = 0
 max_steps = 20000
-eval_frequency = 200
+eval_frequency = 1000
 frozen_components = ["lemmatizer"]
 annotating_components = ["lemmatizer"]
 before_to_disk = null

grc_perseus_trf-any-py3-none-any.whl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e70a98ec79ba1af612fe44d91d006efce93e923504cb3bf81e135d9e13727597
-size 579700077
+oid sha256:560ad38f98987bb12b60d71efd8004e515859fbd19aad26af9b0b4982c8ec8b0
+size 497307169

lemmatizer/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee3567720a57a22b28099f9ccd9c39ee5b455f448e531763e00d59219f0b4671
-size 27089840
+oid sha256:becf7d37bd570f1a89a157da3184d2710dccc79804ec6f0ad3cae090aafe5c2a
+size 29215702

lemmatizer/trees

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a53607dd846f3e82212b030f5fde5e8487e55fe146f7f90da6078e87837bc0a
-size 6009899
+oid sha256:86606a185ea3cbd4c6f071029121d17265dfe9d5a468c6dbeb071a5808cf49f9
+size 6516433

meta.json

@@ -1,14 +1,14 @@
 {
   "lang":"grc",
   "name":"perseus_trf",
-  "version":"3.7",
+  "version":"3.7.5",
   "description":"",
   "author":"",
   "email":"",
   "url":"",
   "license":"",
-  "spacy_version":">=3.7.4,<3.8.0",
-  "spacy_git_version":"bff8725f4",
+  "spacy_version":">=3.7.5,<3.8.0",
+  "spacy_git_version":"a6d0fc360",
   "vectors":{
     "width":0,
     "vectors":0,
@@ -963,156 +963,156 @@
 
   ],
   "performance":{
-    "pos_acc":0.9719448837,
-    "morph_acc":0.9470973571,
+    "pos_acc":0.9717189971,
+    "morph_acc":0.9466455839,
     "morph_per_feat":{
       "Case":{
-        "p":0.9787910923,
-        "r":0.9768057148,
-        "f":0.9777973957
+        "p":0.9781647808,
+        "r":0.9758356116,
+        "f":0.976998808
       },
       "Gender":{
-        "p":0.9614159292,
-        "r":0.9597173145,
-        "f":0.9605658709
+        "p":0.9618449008,
+        "r":0.9598056537,
+        "f":0.9608241953
       },
       "Number":{
-        "p":0.98920054,
-        "r":0.9875711291,
-        "f":0.988385163
+        "p":0.9891948676,
+        "r":0.9870470201,
+        "f":0.9881197766
       },
       "Degree":{
-        "p":0.8441558442,
-        "r":0.7647058824,
-        "f":0.8024691358
+        "p":0.8048780488,
+        "r":0.7764705882,
+        "f":0.7904191617
       },
       "Tense":{
-        "p":0.9648143654,
-        "r":0.9634116792,
-        "f":0.9641125121
+        "p":0.9640252795,
+        "r":0.9609886116,
+        "f":0.9625045504
       },
       "VerbForm":{
-        "p":0.9927202135,
-        "r":0.9912769566,
-        "f":0.9919980601
+        "p":0.9934370442,
+        "r":0.9903077296,
+        "f":0.9918699187
       },
       "Voice":{
-        "p":0.965525613,
-        "r":0.9643549952,
-        "f":0.964939949
+        "p":0.9654753221,
+        "r":0.962900097,
+        "f":0.96418599
       },
       "Aspect":{
-        "p":0.9528061224,
-        "r":0.9098660171,
-        "f":0.9308411215
+        "p":0.9555273189,
+        "r":0.915956151,
+        "f":0.9353233831
       },
       "Mood":{
-        "p":0.982160555,
-        "r":0.9826474963,
-        "f":0.9824039653
+        "p":0.982630273,
+        "r":0.9816559246,
+        "f":0.9821428571
       },
       "Person":{
-        "p":0.9853729888,
-        "r":0.9642175573,
-        "f":0.9746804919
+        "p":0.9868099658,
+        "r":0.963740458,
+        "f":0.9751387883
       }
     },
-    "tag_acc":0.973255026,
+    "tag_acc":0.9723063022,
     "sents_f":0.9934065934,
     "sents_p":0.992970123,
     "sents_r":0.9938434477,
-    "dep_uas":0.8300239687,
-    "dep_las":0.7853160086,
+    "dep_uas":0.8278332829,
+    "dep_las":0.7808557877,
     "dep_las_per_type":{
       "det":{
-        "p":0.9101460127,
-        "r":0.9033816425,
-        "f":0.9067512122
+        "p":0.9116104869,
+        "r":0.9044964697,
+        "f":0.9080395449
       },
       "advmod":{
-        "p":0.8054195233,
-        "r":0.7952933591,
-        "f":0.800324412
+        "p":0.7959779436,
+        "r":0.7911025145,
+        "f":0.7935327405
       },
       "case":{
-        "p":0.941826215,
-        "r":0.9502228826,
-        "f":0.9460059172
+        "p":0.9423076923,
+        "r":0.9465081724,
+        "f":0.9444032617
       },
       "nmod":{
-        "p":0.717268623,
-        "r":0.6848060345,
-        "f":0.7006615215
+        "p":0.7173666288,
+        "r":0.6810344828,
+        "f":0.6987285793
       },
       "cc":{
-        "p":0.7668292683,
-        "r":0.7631067961,
-        "f":0.7649635036
+        "p":0.7729516288,
+        "r":0.7601941748,
+        "f":0.7665198238
       },
       "conj":{
-        "p":0.7571035747,
-        "r":0.7441441441,
-        "f":0.7505679237
+        "p":0.7578268877,
+        "r":0.7414414414,
+        "f":0.7495446266
       },
       "csubj":{
-        "p":0.6588235294,
-        "r":0.5436893204,
-        "f":0.5957446809
+        "p":0.6352941176,
+        "r":0.5242718447,
+        "f":0.5744680851
       },
       "obl":{
-        "p":0.7193347193,
-        "r":0.7330508475,
-        "f":0.7261280168
+        "p":0.7283687943,
+        "r":0.7252824859,
+        "f":0.7268223638
       },
       "root":{
-        "p":0.9516695958,
-        "r":0.9525065963,
-        "f":0.9520879121
+        "p":0.9525483304,
+        "r":0.9533861038,
+        "f":0.952967033
       },
       "cop":{
-        "p":0.7964912281,
-        "r":0.8021201413,
-        "f":0.7992957746
+        "p":0.7665505226,
+        "r":0.777385159,
+        "f":0.7719298246
       },
       "obj":{
-        "p":0.7563704164,
-        "r":0.7821336761,
-        "f":0.7690363349
+        "p":0.7562972292,
+        "r":0.7718508997,
+        "f":0.7639949109
       },
       "acl":{
-        "p":0.4836065574,
-        "r":0.3641975309,
-        "f":0.4154929577
+        "p":0.4910714286,
+        "r":0.3395061728,
+        "f":0.401459854
       },
       "xcomp":{
-        "p":0.5787965616,
-        "r":0.5923753666,
-        "f":0.5855072464
+        "p":0.5683139535,
+        "r":0.573313783,
+        "f":0.5708029197
       },
       "nsubj":{
-        "p":0.7847498014,
-        "r":0.7767295597,
-        "f":0.7807190834
+        "p":0.7786499215,
+        "r":0.7798742138,
+        "f":0.7792615868
       },
       "amod":{
-        "p":0.4468085106,
-        "r":0.3088235294,
-        "f":0.3652173913
+        "p":0.3461538462,
+        "r":0.2647058824,
+        "f":0.3
       },
       "advcl":{
-        "p":0.7131849315,
-        "r":0.7256097561,
-        "f":0.719343696
+        "p":0.6948160535,
+        "r":0.7238675958,
+        "f":0.7090443686
       },
       "mark":{
-        "p":0.8833333333,
+        "p":0.8808864266,
         "r":0.8857938719,
-        "f":0.8845618915
+        "f":0.8833333333
       },
       "iobj":{
-        "p":0.5955882353,
-        "r":0.5955882353,
-        "f":0.5955882353
+        "p":0.5414012739,
+        "r":0.625,
+        "f":0.5802047782
       },
       "dep":{
         "p":0.0,
@@ -1120,19 +1120,19 @@
         "f":0.0
       },
       "ccomp":{
-        "p":0.6203208556,
-        "r":0.5576923077,
-        "f":0.5873417722
+        "p":0.5606060606,
+        "r":0.5336538462,
+        "f":0.5467980296
       },
       "appos":{
-        "p":0.2,
-        "r":0.12,
-        "f":0.15
+        "p":0.2222222222,
+        "r":0.16,
+        "f":0.1860465116
       },
       "nummod":{
-        "p":0.3157894737,
-        "r":0.375,
-        "f":0.3428571429
+        "p":0.3,
+        "r":0.1875,
+        "f":0.2307692308
       },
       "discourse":{
         "p":1.0,
@@ -1140,9 +1140,9 @@
         "f":0.9696969697
       },
       "vocative":{
-        "p":0.8421052632,
-        "r":0.6956521739,
-        "f":0.7619047619
+        "p":0.8333333333,
+        "r":0.652173913,
+        "f":0.7317073171
       },
       "parataxis":{
         "p":0.0,
@@ -1150,14 +1150,14 @@
         "f":0.0
       }
     },
-    "lemma_acc":0.9687634105,
-    "transformer_loss":229.1886046889,
-    "morphologizer_loss":31.0409947152,
-    "tagger_loss":27.2031119848,
-    "senter_loss":134.9575767298,
-    "parser_loss":19260.8797536265
+    "lemma_acc":0.9714737436,
+    "transformer_loss":1818.713642158,
+    "morphologizer_loss":206.8374374373,
+    "tagger_loss":169.9414253123,
+    "senter_loss":683.018002257,
+    "parser_loss":96820.3485642595
   },
   "requirements":[
-    "spacy-transformers>=1.3.4,<1.4.0"
+    "spacy-transformers>=1.3.5,<1.4.0"
   ]
 }

morphologizer/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78c2bc2a75f6085499efe7c84594cd2232135b286f2eca55ddfb2f68a8379a82
+oid sha256:84cdd86aab4cb28269444ee5f9a8f0a4d3baadd01c84efb99427a1bb4a405928
 size 2667545

parser/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c6b00df2b710485e686eb62d9bf45131fd68ead6b96e52b1d862e8ec9104f01
+oid sha256:8a2083eafe099d28ec478c0d6b52d9f3301a16f6aeedbf8268566d39a5533755
 size 2030887

transformer/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16599b137b7ab585bba7999d13bd1559892a4bd38935584999484c5c7eece319
+oid sha256:5489b0e1b432464fe8d2c201b8dd529bad88671d36dd08451a8d0d23413e35c0
 size 500074867

vocab/strings.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44cfaf0d411aaad34b0a67e353cfe8f85fbaf34513e489542dee0409fd3d1fd7
-size 23346083
+oid sha256:991bdcde1c93f43861f5213f350babb9194774a93df0b4c0f106e28876ee2b3b
+size 22428003