Update spacy pipeline to 3.4.0

README.md

@@ -14,70 +14,70 @@ model-index:
     metrics:
     - name: NER Precision
       type: precision
-      value: 0.847826087
+      value: 0.8710737765
     - name: NER Recall
       type: recall
-      value: 0.8570675105
+      value: 0.8386075949
     - name: NER F Score
       type: f_score
-      value: 0.8524217521
+      value: 0.8545324257
   - task:
       name: TAG
       type: token-classification
     metrics:
     - name: TAG (XPOS) Accuracy
       type: accuracy
-      value: 0.9677018039
+      value: 0.9651179482
   - task:
       name: POS
       type: token-classification
     metrics:
     - name: POS (UPOS) Accuracy
       type: accuracy
-      value: 0.9675104072
+      value: 0.9639695679
   - task:
       name: MORPH
       type: token-classification
     metrics:
     - name: Morph (UFeats) Accuracy
       type: accuracy
-      value: 0.9386544167
+      value: 0.9321466169
   - task:
       name: LEMMA
       type: token-classification
     metrics:
     - name: Lemma Accuracy
       type: accuracy
-      value: 0.9716773514
+      value: 0.9711032437
   - task:
       name: UNLABELED_DEPENDENCIES
       type: token-classification
     metrics:
     - name: Unlabeled Attachment Score (UAS)
       type: f_score
-      value: 0.8069939475
+      value: 0.8218578007
   - task:
       name: LABELED_DEPENDENCIES
       type: token-classification
     metrics:
     - name: Labeled Attachment Score (LAS)
       type: f_score
-      value: 0.736004483
+      value: 0.7535662136
   - task:
       name: SENTS
       type: token-classification
     metrics:
     - name: Sentences F-Score
       type: f_score
-      value: 0.9821029083
+      value: 0.9732739421
 ---
 Core Hungarian model for HuSpaCy. Components: tok2vec, senter, tagger, morphologizer, lemmatizer, parser, ner
 
 | Feature | Description |
 | --- | --- |
 | **Name** | `hu_core_news_lg` |
-| **Version** | `3.3.1` |
-| **spaCy** | `>=3.3.0,<3.4.0` |
+| **Version** | `3.4.0` |
+| **spaCy** | `>=3.4.1,<3.5.0` |
 | **Default Pipeline** | `tok2vec`, `senter`, `tagger`, `morphologizer`, `lookup_lemmatizer`, `lemmatizer`, `lemma_smoother`, `parser`, `ner` |
 | **Components** | `tok2vec`, `senter`, `tagger`, `morphologizer`, `lookup_lemmatizer`, `lemmatizer`, `lemma_smoother`, `parser`, `ner` |
 | **Vectors** | -1 keys, 200000 unique vectors (300 dimensions) |
@@ -108,18 +108,18 @@ Core Hungarian model for HuSpaCy. Components: tok2vec, senter, tagger, morpholog
 | `TOKEN_P` | 99.86 |
 | `TOKEN_R` | 99.93 |
 | `TOKEN_F` | 99.89 |
-| `SENTS_P` | 97.77 |
-| `SENTS_R` | 97.55 |
-| `SENTS_F` | 97.66 |
-| `TAG_ACC` | 96.31 |
-| `POS_ACC` | 96.34 |
-| `MORPH_ACC` | 92.89 |
-| `MORPH_MICRO_P` | 96.28 |
-| `MORPH_MICRO_R` | 95.58 |
-| `MORPH_MICRO_F` | 95.93 |
-| `LEMMA_ACC` | 97.25 |
-| `DEP_UAS` | 81.13 |
-| `DEP_LAS` | 74.49 |
-| `ENTS_P` | 87.15 |
-| `ENTS_R` | 83.72 |
-| `ENTS_F` | 85.40 |
+| `SENTS_P` | 98.44 |
+| `SENTS_R` | 98.22 |
+| `SENTS_F` | 98.33 |
+| `TAG_ACC` | 96.50 |
+| `POS_ACC` | 96.45 |
+| `MORPH_ACC` | 93.44 |
+| `MORPH_MICRO_P` | 96.85 |
+| `MORPH_MICRO_R` | 96.14 |
+| `MORPH_MICRO_F` | 96.49 |
+| `LEMMA_ACC` | 97.05 |
+| `DEP_UAS` | 79.50 |
+| `DEP_LAS` | 72.47 |
+| `ENTS_P` | 86.06 |
+| `ENTS_R` | 85.28 |
+| `ENTS_F` | 85.67 |

config.cfg

@@ -1,7 +1,7 @@
 [paths]
-parser_model = "models/hu_core_news_lg-parser-3.3.1/model-best"
-ner_model = "models/hu_core_news_lg-ner-3.3.1/model-best"
-lemmatizer_lookups = "models/hu_core_news_lg-lookup-lemmatizer-3.3.1"
+parser_model = "models/hu_core_news_lg-parser-3.4.0/model-best"
+ner_model = "models/hu_core_news_lg-ner-3.4.0/model-best"
+lemmatizer_lookups = "models/hu_core_news_lg-lookup-lemmatizer-3.4.0"
 train = null
 dev = null
 vectors = null

hu_core_news_lg-any-py3-none-any.whl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da2b5830c7953203b64049813cbb0f4a181aa47be42744aa800af2fe3a22f0aa
-size 403094603
+oid sha256:a53a5744c2048e14b9889c0dcb88375c90d7843d682cc4fef3d733a004f4292e
+size 403067232

lemmatizer/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58b56ab3836952a8e612a411c2a1958630e46569225dce1cabb138e7fdc17658
+oid sha256:24e1bb7789ed97ed80b4d4424397a83a0eb324b095911a7512f17135233c2fdf
 size 64058360

meta.json

@@ -1,13 +1,13 @@
 {
   "lang":"hu",
   "name":"core_news_lg",
-  "version":"3.3.1",
+  "version":"3.4.0",
   "description":"Core Hungarian model for HuSpaCy. Components: tok2vec, senter, tagger, morphologizer, lemmatizer, parser, ner",
   "author":"SzegedAI, MILAB",
   "email":"[email protected]",
   "url":"https://github.com/huspacy/huspacy",
   "license":"cc-by-sa-4.0",
-  "spacy_version":">=3.3.0,<3.4.0",
+  "spacy_version":">=3.4.1,<3.5.0",
   "spacy_git_version":"Unknown",
   "vectors":{
     "width":300,
@@ -1274,85 +1274,80 @@
     "token_p":0.998565417,
     "token_r":0.9993300153,
     "token_f":0.9989475698,
-    "sents_p":0.9865168539,
-    "sents_r":0.9777282851,
-    "sents_f":0.9821029083,
-    "tag_acc":0.9677018039,
-    "pos_acc":0.9675104072,
-    "morph_acc":0.9386544167,
-    "morph_micro_p":0.9693278037,
-    "morph_micro_r":0.9642458101,
-    "morph_micro_f":0.9667801284,
+    "sents_p":0.9732739421,
+    "sents_r":0.9732739421,
+    "sents_f":0.9732739421,
+    "tag_acc":0.9651179482,
+    "pos_acc":0.9639695679,
+    "morph_acc":0.9321466169,
+    "morph_micro_p":0.9646136521,
+    "morph_micro_r":0.9570691878,
+    "morph_micro_f":0.9608266103,
     "morph_per_feat":{
       "Definite":{
-        "p":0.9721835883,
-        "r":0.9785347643,
-        "f":0.9753488372
+        "p":0.9587155963,
+        "r":0.9752683154,
+        "f":0.9669211196
       },
       "PronType":{
-        "p":0.979501385,
-        "r":0.9757174393,
-        "f":0.9776057506
+        "p":0.9733777038,
+        "r":0.9685430464,
+        "f":0.9709543568
       },
       "Case":{
-        "p":0.9769016328,
-        "r":0.9693736416,
-        "f":0.9731230784
+        "p":0.9746405751,
+        "r":0.9644339063,
+        "f":0.9695103784
       },
       "Degree":{
-        "p":0.9226086957,
-        "r":0.8826955075,
-        "f":0.9022108844
+        "p":0.918061674,
+        "r":0.8668885191,
+        "f":0.891741549
       },
       "Number":{
-        "p":0.9862277461,
-        "r":0.9840791017,
-        "f":0.9851522523
+        "p":0.9843223196,
+        "r":0.9785486844,
+        "f":0.9814270107
       },
       "Mood":{
-        "p":0.9276457883,
-        "r":0.9523281596,
-        "f":0.9398249453
+        "p":0.9163952226,
+        "r":0.9356984479,
+        "f":0.9259462425
       },
       "Person":{
-        "p":0.9452054795,
-        "r":0.9646381579,
-        "f":0.9548229548
+        "p":0.9458128079,
+        "r":0.9473684211,
+        "f":0.9465899753
       },
       "Tense":{
-        "p":0.9589632829,
-        "r":0.9812154696,
-        "f":0.9699617695
+        "p":0.9500542888,
+        "r":0.9668508287,
+        "f":0.9583789704
       },
       "VerbForm":{
-        "p":0.9598976109,
-        "r":0.9021651965,
-        "f":0.93013642
+        "p":0.9416666667,
+        "r":0.9061748196,
+        "f":0.9235798937
       },
       "Voice":{
-        "p":0.9570858283,
-        "r":0.9805725971,
-        "f":0.9686868687
+        "p":0.9478435306,
+        "r":0.9662576687,
+        "f":0.9569620253
       },
       "Number[psor]":{
-        "p":0.9793205318,
-        "r":0.9444444444,
-        "f":0.9615663524
+        "p":0.9792899408,
+        "r":0.943019943,
+        "f":0.9608127721
       },
       "Person[psor]":{
-        "p":0.9807976366,
-        "r":0.9472182596,
-        "f":0.9637155298
+        "p":0.9807692308,
+        "r":0.9457917261,
+        "f":0.962962963
       },
       "NumType":{
-        "p":0.9223529412,
-        "r":0.956097561,
-        "f":0.9389221557
-      },
-      "Poss":{
-        "p":0.5,
-        "r":1.0,
-        "f":0.6666666667
+        "p":0.9341463415,
+        "r":0.9341463415,
+        "f":0.9341463415
       },
       "Reflex":{
         "p":1.0,
@@ -1360,9 +1355,14 @@
         "f":0.9333333333
       },
       "Aspect":{
-        "p":1.0,
-        "r":0.25,
-        "f":0.4
+        "p":0.0,
+        "r":0.0,
+        "f":0.0
+      },
+      "Poss":{
+        "p":0.75,
+        "r":1.0,
+        "f":0.8571428571
       },
       "Number[psed]":{
         "p":0.0,
@@ -1370,114 +1370,114 @@
         "f":0.0
       }
     },
-    "lemma_acc":0.9716773514,
-    "dep_uas":0.8069939475,
-    "dep_las":0.736004483,
+    "lemma_acc":0.9711032437,
+    "dep_uas":0.8218578007,
+    "dep_las":0.7535662136,
     "dep_las_per_type":{
       "det":{
-        "p":0.8576923077,
-        "r":0.8877388535,
-        "f":0.872456964
+        "p":0.8716535433,
+        "r":0.8813694268,
+        "f":0.8764845606
       },
       "amod:att":{
-        "p":0.8787878788,
-        "r":0.8062142273,
-        "f":0.8409381663
+        "p":0.8508196721,
+        "r":0.8487326247,
+        "f":0.849774867
       },
       "nsubj":{
-        "p":0.7076923077,
-        "r":0.71875,
-        "f":0.7131782946
+        "p":0.768,
+        "r":0.75,
+        "f":0.7588932806
       },
       "advmod:mode":{
-        "p":0.5563380282,
+        "p":0.6124031008,
         "r":0.5808823529,
-        "f":0.5683453237
+        "f":0.5962264151
       },
       "nmod:att":{
-        "p":0.7508143322,
-        "r":0.7813559322,
-        "f":0.7657807309
+        "p":0.7916666667,
+        "r":0.7728813559,
+        "f":0.782161235
       },
       "obl":{
-        "p":0.7599645704,
-        "r":0.7722772277,
-        "f":0.7660714286
+        "p":0.7557058326,
+        "r":0.804680468,
+        "f":0.7794245859
       },
       "obj":{
-        "p":0.8466819222,
-        "r":0.8314606742,
-        "f":0.8390022676
+        "p":0.8244111349,
+        "r":0.8651685393,
+        "f":0.8442982456
       },
       "root":{
-        "p":0.7730337079,
-        "r":0.7661469933,
-        "f":0.7695749441
+        "p":0.7795100223,
+        "r":0.7795100223,
+        "f":0.7795100223
       },
       "cc":{
-        "p":0.6673913043,
-        "r":0.6463157895,
-        "f":0.656684492
+        "p":0.7068181818,
+        "r":0.6547368421,
+        "f":0.6797814208
       },
       "conj":{
-        "p":0.50456621,
-        "r":0.4604166667,
-        "f":0.4814814815
+        "p":0.5247058824,
+        "r":0.4645833333,
+        "f":0.4928176796
       },
       "advmod":{
-        "p":0.8137254902,
-        "r":0.8736842105,
-        "f":0.8426395939
+        "p":0.8181818182,
+        "r":0.8526315789,
+        "f":0.8350515464
       },
       "flat:name":{
-        "p":0.8085106383,
-        "r":0.8878504673,
-        "f":0.846325167
+        "p":0.8622222222,
+        "r":0.9065420561,
+        "f":0.8838268793
       },
       "appos":{
-        "p":0.4352941176,
-        "r":0.3936170213,
-        "f":0.4134078212
+        "p":0.3131313131,
+        "r":0.329787234,
+        "f":0.3212435233
       },
       "advcl":{
-        "p":0.3552631579,
-        "r":0.2755102041,
-        "f":0.3103448276
+        "p":0.3666666667,
+        "r":0.3367346939,
+        "f":0.3510638298
       },
       "advmod:tlocy":{
-        "p":0.7136752137,
-        "r":0.7260869565,
-        "f":0.7198275862
+        "p":0.6507352941,
+        "r":0.7695652174,
+        "f":0.7051792829
       },
       "ccomp:obj":{
-        "p":0.1746031746,
+        "p":0.2619047619,
         "r":0.3333333333,
-        "f":0.2291666667
+        "f":0.2933333333
       },
       "mark":{
-        "p":0.8104575163,
-        "r":0.7848101266,
-        "f":0.7974276527
+        "p":0.7914110429,
+        "r":0.8164556962,
+        "f":0.8037383178
       },
       "compound:preverb":{
-        "p":0.8928571429,
-        "r":0.9174311927,
-        "f":0.9049773756
+        "p":0.9196428571,
+        "r":0.9449541284,
+        "f":0.9321266968
       },
       "advmod:locy":{
-        "p":0.76,
-        "r":0.59375,
-        "f":0.6666666667
+        "p":0.85,
+        "r":0.53125,
+        "f":0.6538461538
       },
       "cop":{
-        "p":0.9333333333,
-        "r":0.3414634146,
-        "f":0.5
+        "p":0.7352941176,
+        "r":0.6097560976,
+        "f":0.6666666667
       },
       "nmod:obl":{
-        "p":0.3333333333,
-        "r":0.225,
-        "f":0.2686567164
+        "p":0.2413793103,
+        "r":0.175,
+        "f":0.2028985507
       },
       "advmod:to":{
         "p":0.0,
@@ -1490,69 +1490,59 @@
         "f":0.0
       },
       "ccomp:obl":{
-        "p":0.3488372093,
-        "r":0.46875,
-        "f":0.4
+        "p":0.5625,
+        "r":0.28125,
+        "f":0.375
       },
       "iobj":{
-        "p":0.25,
-        "r":0.1333333333,
-        "f":0.1739130435
-      },
-      "xcomp":{
-        "p":0.9428571429,
-        "r":0.8918918919,
-        "f":0.9166666667
+        "p":0.1875,
+        "r":0.2,
+        "f":0.1935483871
       },
       "case":{
-        "p":0.9513513514,
-        "r":0.8979591837,
-        "f":0.9238845144
+        "p":0.9179487179,
+        "r":0.9132653061,
+        "f":0.915601023
       },
       "csubj":{
-        "p":0.3666666667,
-        "r":0.2972972973,
-        "f":0.328358209
+        "p":0.6666666667,
+        "r":0.2702702703,
+        "f":0.3846153846
       },
       "parataxis":{
-        "p":0.2790697674,
-        "r":0.1643835616,
-        "f":0.2068965517
+        "p":0.3333333333,
+        "r":0.1232876712,
+        "f":0.18
+      },
+      "xcomp":{
+        "p":0.8783783784,
+        "r":0.8783783784,
+        "f":0.8783783784
       },
       "nummod":{
-        "p":0.5384615385,
-        "r":0.6774193548,
-        "f":0.6
+        "p":0.592920354,
+        "r":0.7204301075,
+        "f":0.6504854369
       },
       "acl":{
-        "p":0.2823529412,
-        "r":0.3333333333,
-        "f":0.3057324841
-      },
-      "ccomp":{
-        "p":0.3333333333,
-        "r":0.0769230769,
-        "f":0.125
-      },
-      "compound":{
-        "p":0.65,
-        "r":0.975,
-        "f":0.78
+        "p":0.4545454545,
+        "r":0.3472222222,
+        "f":0.3937007874
       },
       "advmod:tto":{
-        "p":0.3157894737,
-        "r":0.6,
-        "f":0.4137931034
+        "p":0.2857142857,
+        "r":0.2,
+        "f":0.2352941176
       },
       "nmod":{
-        "p":0.0526315789,
-        "r":0.0909090909,
-        "f":0.0666666667
+        "p":0.0,
+        "r":0.0,
+        "f":0.0
       },
       "aux":{
-        "p":0.8888888889,
-        "r":0.6666666667,
-        "f":0.7619047619
+        "p":0.9,
+        "r":0.75,
+        "f":0.8181818182
       },
       "advmod:tfrom":{
         "p":0.0,
@@ -1564,7 +1554,12 @@
         "r":0.0,
         "f":0.0
       },
-      "obl:lvc":{
+      "compound":{
+        "p":1.0,
+        "r":0.975,
+        "f":0.9873417722
+      },
+      "dep":{
         "p":0.0,
         "r":0.0,
         "f":0.0
@@ -1574,25 +1569,30 @@
         "r":0.0,
         "f":0.0
       },
+      "obl:lvc":{
+        "p":0.0,
+        "r":0.0,
+        "f":0.0
+      },
       "nsubj:lvc":{
         "p":0.0,
         "r":0.0,
         "f":0.0
       },
       "list":{
-        "p":1.0,
+        "p":0.5,
         "r":0.1666666667,
-        "f":0.2857142857
+        "f":0.25
       },
-      "dep":{
+      "ccomp":{
         "p":0.0,
         "r":0.0,
         "f":0.0
       },
       "advmod:que":{
-        "p":0.6666666667,
+        "p":1.0,
         "r":0.5,
-        "f":0.5714285714
+        "f":0.6666666667
       },
       "ccomp:pred":{
         "p":0.0,
@@ -1600,32 +1600,32 @@
         "f":0.0
       }
     },
-    "ents_p":0.847826087,
-    "ents_r":0.8570675105,
-    "ents_f":0.8524217521,
+    "ents_p":0.8710737765,
+    "ents_r":0.8386075949,
+    "ents_f":0.8545324257,
     "ents_per_type":{
       "ORG":{
-        "p":0.8934198332,
-        "r":0.8938340287,
-        "f":0.893626883
+        "p":0.8817399184,
+        "r":0.9021789522,
+        "f":0.8918423465
       },
       "PER":{
-        "p":0.8527607362,
-        "r":0.9133811231,
-        "f":0.882030574
+        "p":0.870911215,
+        "r":0.8906810036,
+        "f":0.8806851742
       },
       "LOC":{
-        "p":0.8836363636,
-        "r":0.84375,
-        "f":0.8632326821
+        "p":0.918065153,
+        "r":0.8072916667,
+        "f":0.8591224018
       },
       "MISC":{
-        "p":0.6380543634,
-        "r":0.6326241135,
-        "f":0.6353276353
+        "p":0.7408088235,
+        "r":0.5716312057,
+        "f":0.645316253
       }
     },
-    "speed":555.2070840132
+    "speed":522.1357122831
   },
   "sources":[
     {

morphologizer/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5ca20500cbdd421aef3d9684d3a5783decf95365c78d4d57a5f4dd13e4d577a
+oid sha256:f5b44171103e5b0c4bebadf424b2e8b43ee1299e4a994b601598f0d6546c4588
 size 1383846

ner/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eedc3bce0b2163ddc254979ebc0638fd1fafc17757e4174a61a52a220ca67605
+oid sha256:7511c723ca2ed83a785f1967e0af449ce78ebb09721b0826b5854e265a0219f0
 size 56989063

parser/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b6ef22e01aa41f9994276b00d702e8209874838e0b7cb75126a48bf590c62a6
+oid sha256:dab40042e245375b3778f4fd0b0aafb35f0e536f6cf4e768db9052cc7100cf16
 size 26010735

senter/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dc6cfcf9c72e9b95f410351ddb9e3af75ac92379d5bf952bb125cba3d746a4a
+oid sha256:b43885340c99fe99afd2b871eef4c1d5b1c59edb68afba6961022e8f54432867
 size 2845

tagger/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6c130a4c5ad4a2974b06f0c984b4205cbe68ad24a3869ee9fedde33b1277b75
+oid sha256:53d000450dda6c1b293154c0a9f0676bcaf3082aedcc146db74b7c7ff5ea5ebe
 size 20905

tok2vec/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2249eb08d5f2dde70f0267a57d3dce7dbeffd51a5dbbdab6b2ed77680d24cac8
+oid sha256:e11b6c75955ada601de2f49a444d9d984305e1df63ad525247ed4d92ec798dfa
 size 56806299

vocab/strings.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ac5abb49f76f2c3e494f52266f182f777ec5e097cba4125a7107b6c3500792f
-size 6404104
+oid sha256:0fbc9da7f8302ec97cfca76974fc4dce1755093cce27d572cc2012b5c73c8f36
+size 6404762