Update spacy pipeline to 0.4.2

README.md

@@ -14,69 +14,76 @@ model-index:
     metrics:
     - name: NER Precision
       type: precision
-      value: 0.856968588
+      value: 0.8543930456
     - name: NER Recall
       type: recall
-      value: 0.854622871
+      value: 0.8369829684
     - name: NER F Score
       type: f_score
-      value: 0.8557941221
+      value: 0.8455984022
   - task:
       name: TAG
       type: token-classification
     metrics:
     - name: TAG (XPOS) Accuracy
       type: accuracy
-      value: 0.9643523614
+      value: 0.9648308532
   - task:
       name: POS
       type: token-classification
     metrics:
     - name: POS (UPOS) Accuracy
       type: accuracy
-      value: 0.9621512991
+      value: 0.9652136466
   - task:
       name: MORPH
       type: token-classification
     metrics:
     - name: Morph (UFeats) Accuracy
       type: accuracy
-      value: 0.9253517083
+      value: 0.9279356876
+  - task:
+      name: LEMMA
+      type: token-classification
+    metrics:
+    - name: Lemma Accuracy
+      type: accuracy
+      value: 0.9543584346
   - task:
       name: UNLABELED_DEPENDENCIES
       type: token-classification
     metrics:
     - name: Unlabeled Attachment Score (UAS)
       type: f_score
-      value: 0.8193704057
+      value: 0.8110496002
   - task:
       name: LABELED_DEPENDENCIES
       type: token-classification
     metrics:
     - name: Labeled Attachment Score (LAS)
       type: f_score
-      value: 0.7497475031
+      value: 0.7398792217
   - task:
       name: SENTS
       type: token-classification
     metrics:
     - name: Sentences F-Score
       type: f_score
-      value: 0.9755011136
+      value: 0.9754464286
 ---
 Core Hungarian model for HuSpaCy. Components: tok2vec, senter, tagger, morphologizer, lemmatizer, parser, ner
 
 | Feature | Description |
 | --- | --- |
 | **Name** | `hu_core_news_lg` |
-| **Version** | `0.4.1` |
+| **Version** | `0.4.2` |
 | **spaCy** | `>=3.2.1,<3.3.0` |
 | **Default Pipeline** | `tok2vec`, `senter`, `tagger`, `morphologizer`, `lemmatizer`, `parser`, `ner` |
 | **Components** | `tok2vec`, `senter`, `tagger`, `morphologizer`, `lemmatizer`, `parser`, `ner` |
 | **Vectors** | 1140008 keys, 1140008 unique vectors (300 dimensions) |
 | **Sources** | [UD Hungarian Szeged](https://universaldependencies.org/treebanks/hu_szeged/index.html) (Richárd Farkas, Katalin Simkó, Zsolt Szántó, Viktor Varga, Veronika Vincze (MTA-SZTE Research Group on Artificial Intelligence))<br />[NYTK-NerKor corpus](https://github.com/nytud/NYTK-NerKor) (Eszter Simon, Noémi Vadász (Department of Language Technology and Applied Linguistics))<br />[hunNERwiki](http://hlt.sztaki.hu/resources/hunnerwiki.html) (Eszter Simon, Dávid Márk Nemeskey (HLT Group, Budapest University of Technology and Economics))<br />[Szeged NER Corpus](https://rgai.inf.u-szeged.hu/node/130) (György Szarvas, Richárd Farkas, László Felföldi, András Kocsor, János Csirik (MTA-SZTE Research Group on Artificial Intelligence))<br />[Webcorpuswiki word2vec model](https://github.com/oroszgy/hunlp-resources/releases/tag/webcorpuswiki_word2vec_v0.1) (György Orosz) |
 | **License** | `cc-by-sa-4.0` |
-| **Author** | [MILAB Spacy Research Group](https://github.com/huspacy/huspacy) |
+| **Author** | [SzegedAI, MILAB](https://github.com/huspacy/huspacy) |
 
 ### Label Scheme
 
@@ -102,17 +109,18 @@ Core Hungarian model for HuSpaCy. Components: tok2vec, senter, tagger, morpholog
 | `TOKEN_P` | 99.86 |
 | `TOKEN_R` | 99.93 |
 | `TOKEN_F` | 99.89 |
-| `SENTS_P` | 97.55 |
-| `SENTS_R` | 97.55 |
-| `SENTS_F` | 97.55 |
-| `TAG_ACC` | 96.44 |
-| `POS_ACC` | 96.22 |
-| `MORPH_ACC` | 92.54 |
-| `MORPH_MICRO_P` | 96.66 |
-| `MORPH_MICRO_R` | 95.38 |
+| `SENTS_P` | 97.76 |
+| `SENTS_R` | 97.33 |
+| `SENTS_F` | 97.54 |
+| `TAG_ACC` | 96.48 |
+| `POS_ACC` | 96.52 |
+| `MORPH_ACC` | 92.79 |
+| `MORPH_MICRO_P` | 96.75 |
+| `MORPH_MICRO_R` | 95.29 |
 | `MORPH_MICRO_F` | 96.02 |
-| `DEP_UAS` | 81.94 |
-| `DEP_LAS` | 74.97 |
-| `ENTS_P` | 85.70 |
-| `ENTS_R` | 85.46 |
-| `ENTS_F` | 85.58 |
+| `LEMMA_ACC` | 95.44 |
+| `DEP_UAS` | 81.10 |
+| `DEP_LAS` | 73.99 |
+| `ENTS_P` | 85.44 |
+| `ENTS_R` | 83.70 |
+| `ENTS_F` | 84.56 |

config.cfg

@@ -1,7 +1,7 @@
 [paths]
-parser_model = "../models/hu_core_news_lg-parser-0.4.1/model-best"
-lemmy_model = "../models/lemmy-0.4.1.bin"
-ner_model = "../models/hu_core_news_lg-ner_merged-0.4.1/model-best"
+parser_model = "../models/hu_core_news_lg-parser-0.4.2/model-best"
+lemmy_model = "../models/lemmy-0.4.2.bin"
+ner_model = "../models/hu_core_news_lg-ner_merged-0.4.2/model-best"
 train = null
 dev = null
 vectors = null
@@ -25,7 +25,6 @@ batch_size = 1000
 
 [components.lemmatizer]
 factory = "hu.lemmatizer"
-model_path = ${paths.lemmy_model}
 scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"}
 
 [components.morphologizer]
@@ -236,4 +235,7 @@ after_init = null
 
 [initialize.components]
 
+[initialize.components.lemmatizer]
+model_path = ${paths.lemmy_model}
+
 [initialize.tokenizer]

hu_core_news_lg-any-py3-none-any.whl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:554b8935082f9351924a4e9142a1c7341187dd21550c719af8d3ae4d96d556fb
-size 1419956175
+oid sha256:2fc64776845dc3a42e2b8eef88d89e6d377d6bde7ef4b0ab897adff1a7cadf83
+size 1419986702

meta.json

@@ -1,9 +1,9 @@
 {
   "lang":"hu",
   "name":"core_news_lg",
-  "version":"0.4.1",
+  "version":"0.4.2",
   "description":"Core Hungarian model for HuSpaCy. Components: tok2vec, senter, tagger, morphologizer, lemmatizer, parser, ner",
-  "author":"MILAB Spacy Research Group",
+  "author":"SzegedAI, MILAB",
   "email":"[email protected]",
   "url":"https://github.com/huspacy/huspacy",
   "license":"cc-by-sa-4.0",
@@ -1192,6 +1192,9 @@
       "Case=Dat|Number=Plur|POS=PRON|Person=1|PronType=Prs",
       "Case=Acc|Number=Plur|Number[psor]=Sing|POS=PROPN|Person[psor]=3",
       "Case=All|Number=Sing|Number[psed]=Sing|POS=PRON|Person=3|PronType=Tot"
+    ],
+    "lemmatizer":[
+
     ],
     "parser":[
       "ROOT",
@@ -1271,80 +1274,85 @@
     "token_p":0.998565417,
     "token_r":0.9993300153,
     "token_f":0.9989475698,
-    "sents_p":0.9755011136,
-    "sents_r":0.9755011136,
-    "sents_f":0.9755011136,
-    "tag_acc":0.9643523614,
-    "pos_acc":0.9621512991,
-    "morph_acc":0.9253517083,
-    "morph_micro_p":0.9666376307,
-    "morph_micro_r":0.9537602063,
-    "morph_micro_f":0.960155743,
+    "sents_p":0.9776286353,
+    "sents_r":0.9732739421,
+    "sents_f":0.9754464286,
+    "tag_acc":0.9648308532,
+    "pos_acc":0.9652136466,
+    "morph_acc":0.9279356876,
+    "morph_micro_p":0.9675378507,
+    "morph_micro_r":0.9529437043,
+    "morph_micro_f":0.9601853255,
     "morph_per_feat":{
       "Definite":{
-        "p":0.9669269637,
-        "r":0.9822678488,
-        "f":0.974537037
+        "p":0.9650092081,
+        "r":0.9780681288,
+        "f":0.9714947856
       },
       "PronType":{
-        "p":0.9739900387,
-        "r":0.9713024283,
-        "f":0.9726443769
+        "p":0.9729878721,
+        "r":0.9740618102,
+        "f":0.973524545
       },
       "Case":{
-        "p":0.9718731299,
-        "r":0.9626556017,
-        "f":0.9672424062
+        "p":0.9694915254,
+        "r":0.9606797076,
+        "f":0.9650655022
       },
       "Degree":{
-        "p":0.9248395967,
-        "r":0.8394342762,
-        "f":0.8800697776
+        "p":0.9205357143,
+        "r":0.8577371048,
+        "f":0.8880275624
       },
       "Number":{
-        "p":0.9785617826,
-        "r":0.9715099715,
-        "f":0.9750231267
+        "p":0.98056119,
+        "r":0.9721803251,
+        "f":0.9763527729
       },
       "Mood":{
-        "p":0.936123348,
-        "r":0.9423503326,
-        "f":0.9392265193
+        "p":0.9442586399,
+        "r":0.9390243902,
+        "f":0.9416342412
       },
       "Person":{
-        "p":0.9641666667,
-        "r":0.9514802632,
-        "f":0.957781457
+        "p":0.9671440607,
+        "r":0.9440789474,
+        "f":0.9554723263
       },
       "Tense":{
-        "p":0.9702643172,
-        "r":0.973480663,
-        "f":0.971869829
+        "p":0.9754738016,
+        "r":0.9668508287,
+        "f":0.9711431743
       },
       "VerbForm":{
-        "p":0.9615705931,
-        "r":0.9230152366,
-        "f":0.941898527
+        "p":0.966977138,
+        "r":0.915797915,
+        "f":0.9406919275
       },
       "Voice":{
-        "p":0.967413442,
-        "r":0.9713701431,
-        "f":0.9693877551
+        "p":0.9701952724,
+        "r":0.9652351738,
+        "f":0.9677088672
       },
       "Number[psor]":{
-        "p":0.9506726457,
-        "r":0.905982906,
-        "f":0.9277899344
+        "p":0.9610778443,
+        "r":0.9145299145,
+        "f":0.9372262774
       },
       "Person[psor]":{
-        "p":0.9506726457,
-        "r":0.907275321,
-        "f":0.9284671533
+        "p":0.9610778443,
+        "r":0.9158345221,
+        "f":0.9379108839
       },
       "NumType":{
-        "p":0.9382716049,
-        "r":0.9268292683,
-        "f":0.9325153374
+        "p":0.9296482412,
+        "r":0.9024390244,
+        "f":0.9158415842
+      },
+      "Poss":{
+        "p":0.6,
+        "r":1.0,
+        "f":0.75
       },
       "Reflex":{
         "p":1.0,
@@ -1360,120 +1368,116 @@
         "p":0.0,
         "r":0.0,
         "f":0.0
-      },
-      "Poss":{
-        "p":1.0,
-        "r":1.0,
-        "f":1.0
       }
     },
-    "dep_uas":0.8193704057,
-    "dep_las":0.7497475031,
+    "lemma_acc":0.9543584346,
+    "dep_uas":0.8110496002,
+    "dep_las":0.7398792217,
     "dep_las_per_type":{
       "det":{
-        "p":0.8756841282,
-        "r":0.8917197452,
-        "f":0.8836291913
+        "p":0.8394875659,
+        "r":0.8869426752,
+        "f":0.8625629113
       },
       "amod:att":{
-        "p":0.8552522746,
-        "r":0.8454619787,
-        "f":0.8503289474
+        "p":0.8847549909,
+        "r":0.7972199509,
+        "f":0.8387096774
       },
       "nsubj":{
-        "p":0.7605863192,
-        "r":0.7296875,
-        "f":0.7448165869
+        "p":0.7160305344,
+        "r":0.7328125,
+        "f":0.7243243243
       },
       "advmod:mode":{
-        "p":0.6159793814,
-        "r":0.5857843137,
-        "f":0.6005025126
+        "p":0.5522041763,
+        "r":0.5833333333,
+        "f":0.5673420739
       },
       "nmod:att":{
-        "p":0.7643207856,
-        "r":0.7915254237,
-        "f":0.7776852623
+        "p":0.7521222411,
+        "r":0.7508474576,
+        "f":0.7514843087
       },
       "obl":{
-        "p":0.7665198238,
-        "r":0.7830783078,
-        "f":0.7747105966
+        "p":0.7796143251,
+        "r":0.7641764176,
+        "f":0.7718181818
       },
       "obj":{
-        "p":0.8306997743,
-        "r":0.8269662921,
-        "f":0.8288288288
+        "p":0.8564920273,
+        "r":0.8449438202,
+        "f":0.850678733
       },
       "root":{
-        "p":0.8106904232,
-        "r":0.8106904232,
-        "f":0.8106904232
+        "p":0.8210290828,
+        "r":0.8173719376,
+        "f":0.8191964286
       },
       "cc":{
-        "p":0.6974248927,
-        "r":0.6842105263,
-        "f":0.6907545165
+        "p":0.6175298805,
+        "r":0.6526315789,
+        "f":0.6345957011
       },
       "conj":{
-        "p":0.4454545455,
-        "r":0.5104166667,
-        "f":0.4757281553
+        "p":0.4725274725,
+        "r":0.5375,
+        "f":0.5029239766
       },
       "advmod":{
-        "p":0.7843137255,
+        "p":0.7920792079,
         "r":0.8421052632,
-        "f":0.8121827411
+        "f":0.8163265306
       },
       "flat:name":{
-        "p":0.8362831858,
-        "r":0.8831775701,
-        "f":0.8590909091
+        "p":0.8488888889,
+        "r":0.8925233645,
+        "f":0.8701594533
       },
       "appos":{
-        "p":0.4444444444,
-        "r":0.2978723404,
-        "f":0.3566878981
+        "p":0.3274336283,
+        "r":0.3936170213,
+        "f":0.3574879227
       },
       "advcl":{
-        "p":0.3974358974,
-        "r":0.3163265306,
-        "f":0.3522727273
+        "p":0.3829787234,
+        "r":0.1836734694,
+        "f":0.2482758621
       },
       "advmod:tlocy":{
-        "p":0.6538461538,
-        "r":0.6652173913,
-        "f":0.6594827586
+        "p":0.7004405286,
+        "r":0.6913043478,
+        "f":0.6958424508
       },
       "ccomp:obj":{
-        "p":0.2545454545,
+        "p":0.2857142857,
         "r":0.4242424242,
-        "f":0.3181818182
+        "f":0.3414634146
       },
       "mark":{
-        "p":0.825,
-        "r":0.835443038,
-        "f":0.8301886792
+        "p":0.8176100629,
+        "r":0.8227848101,
+        "f":0.8201892744
       },
       "compound:preverb":{
-        "p":0.8717948718,
-        "r":0.9357798165,
-        "f":0.9026548673
+        "p":0.8888888889,
+        "r":0.9541284404,
+        "f":0.9203539823
       },
       "advmod:locy":{
-        "p":0.7894736842,
-        "r":0.46875,
-        "f":0.5882352941
+        "p":0.6956521739,
+        "r":0.5,
+        "f":0.5818181818
       },
       "cop":{
-        "p":0.7222222222,
-        "r":0.6341463415,
-        "f":0.6753246753
+        "p":0.9,
+        "r":0.6585365854,
+        "f":0.7605633803
       },
       "nmod:obl":{
-        "p":0.2380952381,
-        "r":0.125,
-        "f":0.1639344262
+        "p":0.15,
+        "r":0.075,
+        "f":0.1
       },
       "advmod:to":{
         "p":0.0,
@@ -1481,76 +1485,76 @@
         "f":0.0
       },
       "obj:lvc":{
-        "p":0.3333333333,
-        "r":0.1666666667,
-        "f":0.2222222222
+        "p":0.0,
+        "r":0.0,
+        "f":0.0
       },
       "ccomp:obl":{
-        "p":0.5789473684,
-        "r":0.34375,
-        "f":0.431372549
+        "p":0.56,
+        "r":0.4375,
+        "f":0.4912280702
       },
-      "iobj":{
-        "p":0.4666666667,
-        "r":0.4666666667,
-        "f":0.4666666667
+      "case":{
+        "p":0.9068627451,
+        "r":0.943877551,
+        "f":0.925
+      },
+      "csubj":{
+        "p":0.7368421053,
+        "r":0.3783783784,
+        "f":0.5
       },
       "parataxis":{
         "p":0.1724137931,
         "r":0.0684931507,
         "f":0.0980392157
       },
-      "case":{
-        "p":0.9315789474,
-        "r":0.9030612245,
-        "f":0.9170984456
-      },
-      "csubj":{
-        "p":0.5416666667,
-        "r":0.3513513514,
-        "f":0.4262295082
-      },
       "xcomp":{
-        "p":0.8181818182,
-        "r":0.8513513514,
-        "f":0.8344370861
+        "p":0.9166666667,
+        "r":0.8918918919,
+        "f":0.904109589
       },
       "nummod":{
-        "p":0.5247524752,
-        "r":0.5698924731,
-        "f":0.5463917526
+        "p":0.4671052632,
+        "r":0.7634408602,
+        "f":0.5795918367
+      },
+      "ccomp":{
+        "p":0.0,
+        "r":0.0,
+        "f":0.0
       },
       "acl":{
-        "p":0.36,
-        "r":0.25,
-        "f":0.2950819672
+        "p":0.4029850746,
+        "r":0.375,
+        "f":0.3884892086
+      },
+      "iobj":{
+        "p":0.2857142857,
+        "r":0.1333333333,
+        "f":0.1818181818
+      },
+      "dep":{
+        "p":0.0,
+        "r":0.0,
+        "f":0.0
       },
       "advmod:tto":{
-        "p":0.5714285714,
-        "r":0.4,
-        "f":0.4705882353
+        "p":0.3571428571,
+        "r":0.5,
+        "f":0.4166666667
       },
       "nmod":{
-        "p":0.3333333333,
+        "p":0.1666666667,
         "r":0.0909090909,
-        "f":0.1428571429
-      },
-      "ccomp":{
-        "p":0.1,
-        "r":0.0769230769,
-        "f":0.0869565217
+        "f":0.1176470588
       },
       "aux":{
-        "p":0.9090909091,
-        "r":0.8333333333,
-        "f":0.8695652174
+        "p":0.8888888889,
+        "r":0.6666666667,
+        "f":0.7619047619
       },
       "advmod:tfrom":{
-        "p":0.3333333333,
-        "r":0.1666666667,
-        "f":0.2222222222
-      },
-      "dep":{
         "p":0.0,
         "r":0.0,
         "f":0.0
@@ -1561,9 +1565,9 @@
         "f":0.0
       },
       "compound":{
-        "p":1.0,
-        "r":0.975,
-        "f":0.9873417722
+        "p":0.9268292683,
+        "r":0.95,
+        "f":0.9382716049
       },
       "obl:lvc":{
         "p":0.0,
@@ -1581,47 +1585,47 @@
         "f":0.0
       },
       "list":{
-        "p":0.2,
-        "r":0.1666666667,
-        "f":0.1818181818
-      },
-      "advmod:que":{
         "p":1.0,
-        "r":0.25,
-        "f":0.4
+        "r":0.1666666667,
+        "f":0.2857142857
       },
       "ccomp:pred":{
         "p":0.0,
         "r":0.0,
         "f":0.0
+      },
+      "advmod:que":{
+        "p":1.0,
+        "r":0.25,
+        "f":0.4
       }
     },
-    "ents_p":0.856968588,
-    "ents_r":0.854622871,
-    "ents_f":0.8557941221,
+    "ents_p":0.8543930456,
+    "ents_r":0.8369829684,
+    "ents_f":0.8455984022,
     "ents_per_type":{
       "ORG":{
-        "p":0.8991157556,
-        "r":0.875880971,
-        "f":0.8873462912
+        "p":0.8789659224,
+        "r":0.8786217698,
+        "f":0.8787938124
       },
       "LOC":{
-        "p":0.8272980501,
-        "r":0.8959276018,
-        "f":0.8602461984
+        "p":0.8245981831,
+        "r":0.8898944193,
+        "f":0.8560029017
       },
       "MISC":{
-        "p":0.684287812,
-        "r":0.5974358974,
-        "f":0.6379192334
+        "p":0.6983606557,
+        "r":0.5461538462,
+        "f":0.6129496403
       },
       "PER":{
-        "p":0.8853046595,
-        "r":0.9024008351,
-        "f":0.8937710003
+        "p":0.895021645,
+        "r":0.863256785,
+        "f":0.8788522848
       }
     },
-    "speed":1560.7043552634
+    "speed":1576.1377252055
   },
   "sources":[
     {

morphologizer/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d516c696a86b9e1c23a34c6d429c62e2b2c5f28a81813ed13863a41afeb06dc6
+oid sha256:419afa1fa20c17c7ebdf36d9d16bb529c59af77f4a85a7e33feef6df06d99f6b
 size 1383794

ner/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e376b09a99732aa3ba59acafa63af2a9b8f6b256932d708976fa37729c04eaaa
+oid sha256:dcfdc7eb9e7ccb82c22bea8582667773a93a7ad2786c323ac6dadeedafe1878c
 size 56989356

parser/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f333789b506d2d673146abf86c3b0a27ac002e9e4c28b16d696c42733a28c53
+oid sha256:4d253b22f1fc99cae9567cd03a04470b5d191d2dd9c0937890f36d4a6d55b45d
 size 26010735

senter/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:667d590c7593b4eb3e061dd5ba3e1b946368f28f9d84fd33310efa0a249ff5a5
+oid sha256:49a7d066ca7a7f8a029d9010dc7038016067caf4e9926b4d58bf4be7651cb6f0
 size 2793

tagger/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f1a2d4d6db8ad9155d22ae9ec9cd4156fb9bd4a559f200c98bca3060a1fff05
+oid sha256:5c2554af41b1dc7c6b8c86bbfaec8617ea11a09037db0ecdd4ca83bdbdc62364
 size 20853

tok2vec/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3362ed475999bb8ed77600b04f30d01bcf99f9ad2bae95eba9bb4074390e985b
+oid sha256:261fde9b3cc88d5bd398b95d6b078a4bf54c350a510d18705c9420da15f05e8c
 size 56806592