Update spacy pipeline to 3.2.1

README.md

@@ -14,69 +14,69 @@ model-index:
     metrics:
     - name: NER Precision
       type: precision
-      value: 0.9073426573
+      value: 0.9078212291
     - name: NER Recall
       type: recall
-      value: 0.9124472574
+      value: 0.9142053446
     - name: NER F Score
       type: f_score
-      value: 0.909887798
+      value: 0.9110021023
   - task:
       name: TAG
       type: token-classification
     metrics:
     - name: TAG (XPOS) Accuracy
       type: accuracy
-      value: 0.9726289597
+      value: 0.9738730979
   - task:
       name: POS
       type: token-classification
     metrics:
     - name: POS (UPOS) Accuracy
       type: accuracy
-      value: 0.9720547421
+      value: 0.973777395
   - task:
       name: MORPH
       type: token-classification
     metrics:
     - name: Morph (UFeats) Accuracy
       type: accuracy
-      value: 0.9359747344
+      value: 0.9364532491
   - task:
       name: LEMMA
       type: token-classification
     metrics:
     - name: Lemma Accuracy
       type: accuracy
-      value: 0.9856473065
+      value: 0.9863170988
   - task:
       name: UNLABELED_DEPENDENCIES
       type: token-classification
     metrics:
     - name: Unlabeled Attachment Score (UAS)
       type: f_score
-      value: 0.9141544645
+      value: 0.911718264
   - task:
       name: LABELED_DEPENDENCIES
       type: token-classification
     metrics:
     - name: Labeled Attachment Score (LAS)
       type: f_score
-      value: 0.8754485861
+      value: 0.8713458686
   - task:
       name: SENTS
       type: token-classification
     metrics:
     - name: Sentences F-Score
       type: f_score
-      value: 0.9888641425
+      value: 0.986636971
 ---
 Hungarian transformer pipeline (huBert) for HuSpaCy. Components: transformer, senter, tagger, morphologizer, lemmatizer, parser, ner
 
 | Feature | Description |
 | --- | --- |
 | **Name** | `hu_core_news_trf` |
-| **Version** | `3.2.0b4` |
+| **Version** | `3.2.1` |
 | **spaCy** | `>=3.2.4,<3.3.0` |
 | **Default Pipeline** | `transformer`, `senter`, `tagger`, `morphologizer`, `experimental_edit_tree_lemmatizer`, `experimental_arc_predicter`, `experimental_arc_labeler`, `ner` |
 | **Components** | `transformer`, `senter`, `tagger`, `morphologizer`, `experimental_edit_tree_lemmatizer`, `experimental_arc_predicter`, `experimental_arc_labeler`, `ner` |
@@ -109,20 +109,20 @@ Hungarian transformer pipeline (huBert) for HuSpaCy. Components: transformer, se
 | `TOKEN_P` | 99.86 |
 | `TOKEN_R` | 99.93 |
 | `TOKEN_F` | 99.89 |
-| `SENTS_P` | 98.89 |
-| `SENTS_R` | 98.89 |
-| `SENTS_F` | 98.89 |
-| `TAG_ACC` | 97.26 |
-| `POS_ACC` | 97.21 |
-| `MORPH_ACC` | 93.60 |
-| `MORPH_MICRO_P` | 97.69 |
-| `MORPH_MICRO_R` | 96.98 |
-| `MORPH_MICRO_F` | 97.33 |
-| `LEMMA_ACC` | 98.56 |
-| `BOUND_DEP_LAS` | 87.53 |
-| `BOUND_DEP_UAS` | 91.40 |
-| `DEP_UAS` | 91.42 |
-| `DEP_LAS` | 87.54 |
-| `ENTS_P` | 90.73 |
-| `ENTS_R` | 91.24 |
-| `ENTS_F` | 90.99 |
+| `SENTS_P` | 98.66 |
+| `SENTS_R` | 98.66 |
+| `SENTS_F` | 98.66 |
+| `TAG_ACC` | 97.39 |
+| `POS_ACC` | 97.38 |
+| `MORPH_ACC` | 93.65 |
+| `MORPH_MICRO_P` | 97.75 |
+| `MORPH_MICRO_R` | 97.09 |
+| `MORPH_MICRO_F` | 97.42 |
+| `LEMMA_ACC` | 98.63 |
+| `BOUND_DEP_LAS` | 87.15 |
+| `BOUND_DEP_UAS` | 91.19 |
+| `DEP_UAS` | 91.17 |
+| `DEP_LAS` | 87.13 |
+| `ENTS_P` | 90.78 |
+| `ENTS_R` | 91.42 |
+| `ENTS_F` | 91.10 |

config.cfg

@@ -1,7 +1,7 @@
 [paths]
-tagger_model = "models/hu_core_news_trf-tagger-3.2.0b4/model-best"
-parser_model = "models/hu_core_news_trf-parser-3.2.0b4/model-best"
-ner_model = "models/hu_core_news_trf-ner-3.2.0b4/model-best"
+tagger_model = "models/hu_core_news_trf-tagger-3.2.1/model-best"
+parser_model = "models/hu_core_news_trf-parser-3.2.1/model-best"
+ner_model = "models/hu_core_news_trf-ner-3.2.1/model-best"
 train = null
 dev = null
 vectors = null

experimental_arc_labeler/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:312c1f73111dd98264a8093b2465e2c2e2f9ace5710578e8a720ddbb362e4003
+oid sha256:990bd725ef174d1d6d38f22c6da304252fe49c5bb3a007727f65a38d38a145f5
 size 447476722

experimental_arc_predicter/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e299d1b9103092275226bf19723c85f492453f3c833d55ad26ab25fe4106b4fd
+oid sha256:df945fcedd45cf4f83bea09366a04cf51e8a8bcc9409033108ae86e0c9cc0b18
 size 445185682

experimental_edit_tree_lemmatizer/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81bafd52719cefd7dfaf1134843a30db6a8909ff6f7bf21ab8746899f17577bb
+oid sha256:81741f969bff5b91aee97d0fc608e30892609fcd79aa2096ba2b4ed13feb1272
 size 18527401

hu_core_news_trf-any-py3-none-any.whl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f91f3a8a1f04be37549850edf4562506fee7d33c00d4b8e0903926c435956162
-size 1672222175
+oid sha256:ca3e08013b4549af474c26465027b678cdf3ec2edbeb3d2dc3a2715f3e13aa96
+size 1672216913

meta.json

@@ -1,7 +1,7 @@
 {
   "lang":"hu",
   "name":"core_news_trf",
-  "version":"3.2.0b4",
+  "version":"3.2.1",
   "description":"Hungarian transformer pipeline (huBert) for HuSpaCy. Components: transformer, senter, tagger, morphologizer, lemmatizer, parser, ner",
   "author":"SzegedAI, MILAB",
   "email":"[email protected]",
@@ -7305,15 +7305,15 @@
     "token_p":0.998565417,
     "token_r":0.9993300153,
     "token_f":0.9989475698,
-    "sents_p":0.9888641425,
-    "sents_r":0.9888641425,
-    "sents_f":0.9888641425,
-    "tag_acc":0.9726289597,
-    "pos_acc":0.9720547421,
-    "morph_acc":0.9359747344,
-    "morph_micro_p":0.9769264069,
-    "morph_micro_r":0.9697894284,
-    "morph_micro_f":0.973344835,
+    "sents_p":0.986636971,
+    "sents_r":0.986636971,
+    "sents_f":0.986636971,
+    "tag_acc":0.9738730979,
+    "pos_acc":0.973777395,
+    "morph_acc":0.9364532491,
+    "morph_micro_p":0.9775451045,
+    "morph_micro_r":0.9709497207,
+    "morph_micro_f":0.9742362504,
     "morph_per_feat":{
       "Definite":{
         "p":0.9881460408,
@@ -7321,64 +7321,64 @@
         "f":0.9802445908
       },
       "PronType":{
-        "p":0.9450134771,
-        "r":0.9674392936,
-        "f":0.9560949005
+        "p":0.9425349087,
+        "r":0.9685430464,
+        "f":0.9553620033
       },
       "Case":{
-        "p":0.9898305085,
-        "r":0.9808338273,
-        "f":0.9853116316
+        "p":0.9912385504,
+        "r":0.983600079,
+        "f":0.9874045423
       },
       "Degree":{
-        "p":0.9012944984,
-        "r":0.9267886855,
-        "f":0.9138638228
+        "p":0.8984,
+        "r":0.9342762063,
+        "f":0.9159869494
       },
       "Number":{
-        "p":0.9927803895,
-        "r":0.9909502262,
-        "f":0.9918644636
+        "p":0.9931208054,
+        "r":0.9919557567,
+        "f":0.9925379391
       },
       "Mood":{
-        "p":0.9480662983,
-        "r":0.9512195122,
-        "f":0.9496402878
+        "p":0.9480088496,
+        "r":0.9501108647,
+        "f":0.9490586932
       },
       "Person":{
-        "p":0.9656549521,
-        "r":0.9942434211,
-        "f":0.9797406807
+        "p":0.9695512821,
+        "r":0.9950657895,
+        "f":0.9821428571
       },
       "Tense":{
-        "p":0.9944751381,
+        "p":0.9955752212,
         "r":0.9944751381,
-        "f":0.9944751381
+        "f":0.9950248756
       },
       "VerbForm":{
-        "p":0.994047619,
-        "r":0.8035284683,
-        "f":0.888691796
+        "p":0.9969849246,
+        "r":0.7955092221,
+        "f":0.8849241748
       },
       "Voice":{
-        "p":0.9806517312,
-        "r":0.9846625767,
-        "f":0.9826530612
+        "p":0.9836734694,
+        "r":0.9856850716,
+        "f":0.9846782431
       },
       "Number[psor]":{
-        "p":0.9957203994,
+        "p":0.9971428571,
         "r":0.9943019943,
-        "f":0.9950106914
+        "f":0.9957203994
       },
       "Person[psor]":{
-        "p":0.9942938659,
+        "p":0.9957142857,
         "r":0.9942938659,
-        "f":0.9942938659
+        "f":0.9950035689
       },
       "NumType":{
-        "p":0.9571428571,
-        "r":0.9804878049,
-        "f":0.9686746988
+        "p":0.96,
+        "r":0.9951219512,
+        "f":0.977245509
       },
       "Poss":{
         "p":0.5,
@@ -7417,125 +7417,125 @@
       },
       "Number[psed]":{
         "p":1.0,
-        "r":0.7777777778,
-        "f":0.875
+        "r":0.6666666667,
+        "f":0.8
       }
     },
-    "lemma_acc":0.9856473065,
-    "bound_dep_las":0.8753110048,
-    "bound_dep_uas":0.9139712919,
-    "dep_uas":0.9141544645,
-    "dep_las":0.8754485861,
+    "lemma_acc":0.9863170988,
+    "bound_dep_las":0.8715420695,
+    "bound_dep_uas":0.9119364411,
+    "dep_uas":0.911718264,
+    "dep_las":0.8713458686,
     "dep_las_per_type":{
       "415":{
-        "p":0.9489225858,
-        "r":0.946656051,
-        "f":0.9477879633
+        "p":0.9335418296,
+        "r":0.9506369427,
+        "f":0.9420118343
       },
       "7411097074813287689":{
-        "p":0.9114420063,
-        "r":0.9509403107,
-        "f":0.9307723089
+        "p":0.926507019,
+        "r":0.9174161897,
+        "f":0.9219391947
       },
       "429":{
-        "p":0.9293739968,
-        "r":0.9046875,
-        "f":0.9168646081
+        "p":0.9270186335,
+        "r":0.9328125,
+        "f":0.9299065421
       },
       "15861261214731031920":{
-        "p":0.7702020202,
-        "r":0.7475490196,
-        "f":0.7587064677
+        "p":0.7407407407,
+        "r":0.7352941176,
+        "f":0.7380073801
       },
       "991268021520064439":{
-        "p":0.8827470687,
-        "r":0.893220339,
-        "f":0.8879528222
+        "p":0.8996539792,
+        "r":0.8813559322,
+        "f":0.8904109589
       },
       "435":{
-        "p":0.8867427568,
-        "r":0.9090909091,
-        "f":0.8977777778
+        "p":0.8904469763,
+        "r":0.9144914491,
+        "f":0.9023090586
       },
       "434":{
-        "p":0.9602649007,
-        "r":0.9775280899,
-        "f":0.9688195991
+        "p":0.951754386,
+        "r":0.9752808989,
+        "f":0.9633740289
       },
       "8206900633647566924":{
-        "p":0.8773006135,
-        "r":0.9554565702,
-        "f":0.9147121535
+        "p":0.8799171843,
+        "r":0.9465478842,
+        "f":0.9120171674
       },
       "407":{
-        "p":0.8259958071,
-        "r":0.8294736842,
-        "f":0.8277310924
+        "p":0.8445378151,
+        "r":0.8463157895,
+        "f":0.8454258675
       },
       "410":{
-        "p":0.7577002053,
-        "r":0.76875,
-        "f":0.7631851086
+        "p":0.7594936709,
+        "r":0.75,
+        "f":0.7547169811
       },
       "445":{
-        "p":0.8798370672,
-        "r":0.8762677485,
-        "f":0.8780487805
+        "p":0.8629579376,
+        "r":0.860040568,
+        "f":0.8614967829
       },
       "400":{
-        "p":0.8585858586,
-        "r":0.8947368421,
-        "f":0.8762886598
+        "p":0.8367346939,
+        "r":0.8631578947,
+        "f":0.8497409326
       },
       "17772752594865228322":{
-        "p":0.9806763285,
+        "p":0.9530516432,
         "r":0.9485981308,
-        "f":0.9643705463
+        "f":0.9508196721
       },
       "403":{
-        "p":0.6395348837,
-        "r":0.585106383,
-        "f":0.6111111111
+        "p":0.6744186047,
+        "r":0.6170212766,
+        "f":0.6444444444
       },
       "399":{
-        "p":0.625,
-        "r":0.612244898,
-        "f":0.618556701
+        "p":0.6161616162,
+        "r":0.6224489796,
+        "f":0.6192893401
       },
       "3143985677199705895":{
-        "p":0.8106995885,
-        "r":0.8565217391,
-        "f":0.8329809725
+        "p":0.7803921569,
+        "r":0.8652173913,
+        "f":0.8206185567
       },
       "9241468201421778905":{
-        "p":0.5277777778,
-        "r":0.5757575758,
-        "f":0.5507246377
+        "p":0.5238095238,
+        "r":0.6666666667,
+        "f":0.5866666667
       },
       "423":{
-        "p":0.9245283019,
-        "r":0.9303797468,
-        "f":0.927444795
+        "p":0.9622641509,
+        "r":0.9683544304,
+        "f":0.9652996845
       },
       "13543738850102096385":{
-        "p":0.9719626168,
-        "r":0.9541284404,
-        "f":0.962962963
+        "p":0.9724770642,
+        "r":0.9724770642,
+        "f":0.9724770642
       },
       "10901028881100056900":{
-        "p":0.75,
-        "r":0.84375,
-        "f":0.7941176471
+        "p":0.8125,
+        "r":0.8125,
+        "f":0.8125
       },
       "411":{
-        "p":0.8648648649,
-        "r":0.7804878049,
-        "f":0.8205128205
+        "p":0.8333333333,
+        "r":0.7317073171,
+        "f":0.7792207792
       },
       "12549387360942434255":{
-        "p":0.5135135135,
-        "r":0.475,
-        "f":0.4935064935
+        "p":0.5806451613,
+        "r":0.45,
+        "f":0.5070422535
       },
       "303601073839818384":{
         "p":0.6,
@@ -7543,59 +7543,59 @@
         "f":0.4615384615
       },
       "8884235091647096537":{
-        "p":0.75,
-        "r":0.25,
-        "f":0.375
+        "p":0.4,
+        "r":0.1666666667,
+        "f":0.2352941176
       },
       "2249809950233855422":{
-        "p":0.6363636364,
-        "r":0.65625,
-        "f":0.6461538462
+        "p":0.5,
+        "r":0.71875,
+        "f":0.5897435897
       },
       "422":{
-        "p":0.3846153846,
-        "r":0.6666666667,
-        "f":0.487804878
+        "p":0.4583333333,
+        "r":0.7333333333,
+        "f":0.5641025641
       },
       "8110129090154140942":{
-        "p":0.9844559585,
-        "r":0.9693877551,
-        "f":0.9768637532
+        "p":0.9791666667,
+        "r":0.9591836735,
+        "f":0.9690721649
       },
       "412":{
-        "p":0.7419354839,
-        "r":0.6216216216,
-        "f":0.6764705882
+        "p":0.84,
+        "r":0.5675675676,
+        "f":0.6774193548
       },
       "436":{
-        "p":0.375,
-        "r":0.2054794521,
-        "f":0.2654867257
+        "p":0.2564102564,
+        "r":0.1369863014,
+        "f":0.1785714286
       },
       "450":{
-        "p":0.9473684211,
-        "r":0.972972973,
-        "f":0.96
+        "p":0.9589041096,
+        "r":0.9459459459,
+        "f":0.9523809524
       },
       "12837356684637874264":{
-        "p":0.803030303,
-        "r":0.5698924731,
-        "f":0.6666666667
+        "p":0.6770833333,
+        "r":0.6989247312,
+        "f":0.6878306878
       },
       "451":{
-        "p":0.5942028986,
-        "r":0.5694444444,
-        "f":0.5815602837
+        "p":0.6142857143,
+        "r":0.5972222222,
+        "f":0.6056338028
       },
       "7349492218059511525":{
-        "p":0.7272727273,
-        "r":0.8,
-        "f":0.7619047619
+        "p":0.7777777778,
+        "r":0.7,
+        "f":0.7368421053
       },
       "426":{
-        "p":0.625,
+        "p":0.7142857143,
         "r":0.4545454545,
-        "f":0.5263157895
+        "f":0.5555555556
       },
       "405":{
         "p":0.9166666667,
@@ -7603,9 +7603,9 @@
         "f":0.9166666667
       },
       "17865338459503383721":{
-        "p":0.6666666667,
-        "r":0.3333333333,
-        "f":0.4444444444
+        "p":1.0,
+        "r":0.1666666667,
+        "f":0.2857142857
       },
       "17311980334327143026":{
         "p":0.0,
@@ -7613,9 +7613,9 @@
         "f":0.0
       },
       "7037928807040764755":{
-        "p":0.9523809524,
+        "p":0.9756097561,
         "r":1.0,
-        "f":0.9756097561
+        "f":0.987654321
       },
       "11190527879068114961":{
         "p":0.0,
@@ -7623,9 +7623,9 @@
         "f":0.0
       },
       "3350290345017230236":{
-        "p":0.1428571429,
-        "r":0.0416666667,
-        "f":0.064516129
+        "p":0.0,
+        "r":0.0,
+        "f":0.0
       },
       "10069665988847657778":{
         "p":0.0,
@@ -7633,52 +7633,52 @@
         "f":0.0
       },
       "17473201795025412735":{
-        "p":0.1428571429,
+        "p":0.125,
         "r":0.1666666667,
-        "f":0.1538461538
-      },
-      "203073658115086772":{
-        "p":0.0,
-        "r":0.0,
-        "f":0.0
+        "f":0.1428571429
       },
       "408":{
-        "p":0.3333333333,
+        "p":0.2,
         "r":0.0769230769,
-        "f":0.125
+        "f":0.1111111111
       },
       "6522094215780122214":{
         "p":0.8,
         "r":1.0,
         "f":0.8888888889
+      },
+      "203073658115086772":{
+        "p":0.0,
+        "r":0.0,
+        "f":0.0
       }
     },
-    "ents_p":0.9073426573,
-    "ents_r":0.9124472574,
-    "ents_f":0.909887798,
+    "ents_p":0.9078212291,
+    "ents_r":0.9142053446,
+    "ents_f":0.9110021023,
     "ents_per_type":{
       "ORG":{
-        "p":0.9234296194,
-        "r":0.9337042188,
-        "f":0.928538497
+        "p":0.9280742459,
+        "r":0.9272137228,
+        "f":0.9276437848
       },
       "PER":{
-        "p":0.940688019,
+        "p":0.9423648247,
         "r":0.9474313023,
-        "f":0.944047619
+        "f":0.944891272
       },
       "LOC":{
-        "p":0.9369369369,
-        "r":0.9027777778,
-        "f":0.9195402299
+        "p":0.9258936356,
+        "r":0.921875,
+        "f":0.9238799478
       },
       "MISC":{
-        "p":0.7402422611,
-        "r":0.780141844,
-        "f":0.7596685083
+        "p":0.7429340511,
+        "r":0.7829787234,
+        "f":0.7624309392
       }
     },
-    "speed":3269.2877085782
+    "speed":2488.2218404265
   },
   "sources":[
     {

morphologizer/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:300f49216ac82a5d0d8742bc63129bd90132a31a09d3487d773e64a87a8fef43
+oid sha256:39d3eb6c5986af95257f202f4978615c3cba507636172a0f057d2c8ccff22994
 size 3534977

ner/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f1a2eb84fa39cbbef3655e29611ea573e6d707d5287560713f082c229509130
+oid sha256:7965ae35085d883e8e9f9a5c5df11d763b93af32932f0c5a6e6040c49035fd4c
 size 443626204

senter/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47f7c9b3a9b84184e590a2bcc6044210566cd7505694a3b2242af3a19d1a39ee
+oid sha256:f8131b83d8007cb1c83c2817038287e779f8d234b52b69d9c8d54dbe2a417db3
 size 6792

tagger/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43e8e3c5807e393040783ad002d6ad564ab50787c4161cf64f8584566aa6e0c6
+oid sha256:008d55c1f2114c0966dea8c2d24787c2968b1561750100f58cad0ed340805f6d
 size 52932

transformer/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4b7961f837d39cdf48599919d60541a164b1a00ebfd35858ee0787202d578f9
+oid sha256:e9f20173c2a1ea1f3d4e540eb5fc7a72daa8844c31a0bd74d9c76c83c054df90
 size 443344004

vocab/strings.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bb00f61ae99c2964d148614472e32ee9d2702a097a5a8c57bf3b3b854c0f423
-size 6398347
+oid sha256:e7a51645f565864f0c11c1ce381f6315ab460a19439bd6aeb61135963f0eca20
+size 6398948