Update spacy pipeline to 3.4.2

README.md

@@ -14,70 +14,70 @@ model-index:
     metrics:
     - name: NER Precision
       type: precision
-      value: 0.8497702368
+      value: 0.8538804639
     - name: NER Recall
       type: recall
-      value: 0.8452883263
+      value: 0.8414205345
     - name: NER F Score
       type: f_score
-      value: 0.8475233562
+      value: 0.8476047109
   - task:
       name: TAG
       type: token-classification
     metrics:
     - name: TAG (XPOS) Accuracy
       type: accuracy
-      value: 0.96286726
+      value: 0.9619102306
   - task:
       name: POS
       type: token-classification
     metrics:
     - name: POS (UPOS) Accuracy
       type: accuracy
-      value: 0.9636328835
+      value: 0.9619102306
   - task:
       name: MORPH
       type: token-classification
     metrics:
     - name: Morph (UFeats) Accuracy
       type: accuracy
-      value: 0.9306153699
+      value: 0.9279356876
   - task:
       name: LEMMA
       type: token-classification
     metrics:
     - name: Lemma Accuracy
       type: accuracy
-      value: 0.9714859822
+      value: 0.9716773514
   - task:
       name: UNLABELED_DEPENDENCIES
       type: token-classification
     metrics:
     - name: Unlabeled Attachment Score (UAS)
       type: f_score
-      value: 0.8216374269
+      value: 0.8106528823
   - task:
       name: LABELED_DEPENDENCIES
       type: token-classification
     metrics:
     - name: Labeled Attachment Score (LAS)
       type: f_score
-      value: 0.7502951926
+      value: 0.7407573885
   - task:
       name: SENTS
       type: token-classification
     metrics:
     - name: Sentences F-Score
       type: f_score
-      value: 0.9755011136
+      value: 0.9719416386
 ---
 Core Hungarian model for HuSpaCy. Components: tok2vec, senter, tagger, morphologizer, lemmatizer, parser, ner
 
 | Feature | Description |
 | --- | --- |
 | **Name** | `hu_core_news_md` |
-| **Version** | `3.4.1` |
-| **spaCy** | `>=3.4.1,<3.5.0` |
+| **Version** | `3.4.2` |
+| **spaCy** | `>=3.4.0,<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 (100 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` | 97.55 |
-| `SENTS_R` | 97.55 |
-| `SENTS_F` | 97.55 |
-| `TAG_ACC` | 96.29 |
-| `POS_ACC` | 96.36 |
-| `MORPH_ACC` | 93.06 |
-| `MORPH_MICRO_P` | 96.71 |
-| `MORPH_MICRO_R` | 95.83 |
-| `MORPH_MICRO_F` | 96.27 |
-| `LEMMA_ACC` | 97.15 |
-| `DEP_UAS` | 82.16 |
-| `DEP_LAS` | 75.03 |
-| `ENTS_P` | 84.98 |
-| `ENTS_R` | 84.53 |
-| `ENTS_F` | 84.75 |
+| `SENTS_P` | 97.96 |
+| `SENTS_R` | 96.44 |
+| `SENTS_F` | 97.19 |
+| `TAG_ACC` | 96.19 |
+| `POS_ACC` | 96.19 |
+| `MORPH_ACC` | 92.79 |
+| `MORPH_MICRO_P` | 96.70 |
+| `MORPH_MICRO_R` | 95.63 |
+| `MORPH_MICRO_F` | 96.16 |
+| `LEMMA_ACC` | 97.17 |
+| `DEP_UAS` | 81.07 |
+| `DEP_LAS` | 74.08 |
+| `ENTS_P` | 85.39 |
+| `ENTS_R` | 84.14 |
+| `ENTS_F` | 84.76 |

config.cfg

@@ -1,7 +1,8 @@
 [paths]
-parser_model = "models/hu_core_news_md-parser-3.4.1/model-best"
-ner_model = "models/hu_core_news_md-ner-3.4.1/model-best"
-lemmatizer_lookups = "models/hu_core_news_md-lookup-lemmatizer-3.4.1"
+parser_model = "models/hu_core_news_md-parser-3.4.2/model-best"
+ner_model = "models/hu_core_news_md-ner-3.4.2/model-best"
+lemmatizer_lookups = "models/hu_core_news_md-lookup-lemmatizer-3.4.2"
+tagger_model = "models/hu_core_news_md-tagger-3.4.2/model-best"
 train = null
 dev = null
 vectors = null

hu_core_news_md-any-py3-none-any.whl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31c6616e5a9ec75cb89ecdf7cd2afa9c59c4da9216a473ba2521214569bf30a4
-size 126879563
+oid sha256:0d6611579b8ba5ec465664b775dc0b062d232c0b604543c4d3dc8ffba5db1ebf
+size 126867520

lemmatizer/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff81fbcf693a5ef331aa452f4346a68508e1a756f8527ac0625d676b9d0455b4
+oid sha256:6108321bcd19de12818c34a9b8451d4486c15232f6c95412d34530f38235ced6
 size 11282980

meta.json

@@ -1,13 +1,13 @@
 {
   "lang":"hu",
   "name":"core_news_md",
-  "version":"3.4.1",
+  "version":"3.4.2",
   "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":">=3.4.1,<3.5.0",
+  "spacy_version":">=3.4.0,<3.5.0",
   "spacy_git_version":"Unknown",
   "vectors":{
     "width":100,
@@ -1273,80 +1273,80 @@
     "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":0.96286726,
-    "pos_acc":0.9636328835,
-    "morph_acc":0.9306153699,
-    "morph_micro_p":0.9670844356,
-    "morph_micro_r":0.9583154276,
-    "morph_micro_f":0.9626799629,
+    "sents_p":0.979638009,
+    "sents_r":0.9643652561,
+    "sents_f":0.9719416386,
+    "tag_acc":0.9619102306,
+    "pos_acc":0.9619102306,
+    "morph_acc":0.9279356876,
+    "morph_micro_p":0.9669751879,
+    "morph_micro_r":0.9562956596,
+    "morph_micro_f":0.9616057732,
     "morph_per_feat":{
       "Definite":{
-        "p":0.9619789281,
-        "r":0.979934671,
-        "f":0.9708737864
+        "p":0.9629290618,
+        "r":0.9818012133,
+        "f":0.9722735675
       },
       "PronType":{
-        "p":0.9745293466,
-        "r":0.9713024283,
-        "f":0.9729132117
+        "p":0.9679734953,
+        "r":0.9674392936,
+        "f":0.9677063207
       },
       "Case":{
-        "p":0.9748,
-        "r":0.9630507805,
-        "f":0.9688897724
+        "p":0.974205159,
+        "r":0.9626556017,
+        "f":0.9683959451
       },
       "Degree":{
-        "p":0.9275362319,
-        "r":0.8519134775,
-        "f":0.8881179532
+        "p":0.9305936073,
+        "r":0.8477537438,
+        "f":0.8872442316
       },
       "Number":{
-        "p":0.985313977,
-        "r":0.9782135076,
-        "f":0.981750904
+        "p":0.9839309878,
+        "r":0.9748617396,
+        "f":0.9793753683
       },
       "Mood":{
-        "p":0.9215686275,
-        "r":0.9379157428,
-        "f":0.9296703297
+        "p":0.9295154185,
+        "r":0.9356984479,
+        "f":0.9325966851
       },
       "Person":{
-        "p":0.9521452145,
-        "r":0.9490131579,
-        "f":0.9505766063
+        "p":0.9565217391,
+        "r":0.9407894737,
+        "f":0.9485903814
       },
       "Tense":{
-        "p":0.9608269859,
-        "r":0.9756906077,
-        "f":0.9682017544
+        "p":0.9669603524,
+        "r":0.9701657459,
+        "f":0.9685603971
       },
       "VerbForm":{
-        "p":0.9513602638,
-        "r":0.9254210104,
-        "f":0.9382113821
+        "p":0.9504467912,
+        "r":0.9382518043,
+        "f":0.9443099274
       },
       "Voice":{
-        "p":0.9548192771,
-        "r":0.972392638,
-        "f":0.9635258359
+        "p":0.9634517766,
+        "r":0.9703476483,
+        "f":0.9668874172
       },
       "Number[psor]":{
-        "p":0.9750367107,
-        "r":0.9458689459,
-        "f":0.9602313811
+        "p":0.9662756598,
+        "r":0.9387464387,
+        "f":0.9523121387
       },
       "Person[psor]":{
-        "p":0.9765051395,
-        "r":0.9486447932,
-        "f":0.9623733719
+        "p":0.9677419355,
+        "r":0.9415121255,
+        "f":0.9544468547
       },
       "NumType":{
-        "p":0.9174757282,
-        "r":0.9219512195,
-        "f":0.9197080292
+        "p":0.9189189189,
+        "r":0.912195122,
+        "f":0.9155446756
       },
       "Reflex":{
         "p":1.0,
@@ -1369,114 +1369,114 @@
         "f":1.0
       }
     },
-    "lemma_acc":0.9714859822,
-    "dep_uas":0.8216374269,
-    "dep_las":0.7502951926,
+    "lemma_acc":0.9716773514,
+    "dep_uas":0.8106528823,
+    "dep_las":0.7407573885,
     "dep_las_per_type":{
       "det":{
-        "p":0.865073246,
-        "r":0.8933121019,
-        "f":0.8789659224
+        "p":0.8752959747,
+        "r":0.8829617834,
+        "f":0.8791121681
       },
       "amod:att":{
-        "p":0.8651202749,
-        "r":0.8233851186,
-        "f":0.8437369083
+        "p":0.8394758395,
+        "r":0.8381030253,
+        "f":0.8387888707
       },
       "nsubj":{
-        "p":0.748844376,
-        "r":0.759375,
-        "f":0.7540729247
+        "p":0.7318611987,
+        "r":0.725,
+        "f":0.7284144427
       },
       "advmod:mode":{
-        "p":0.597260274,
-        "r":0.5343137255,
-        "f":0.5640362225
+        "p":0.5843230404,
+        "r":0.6029411765,
+        "f":0.5934861279
       },
       "nmod:att":{
-        "p":0.7573770492,
-        "r":0.7830508475,
-        "f":0.77
+        "p":0.7541528239,
+        "r":0.7694915254,
+        "f":0.7617449664
       },
       "obl":{
-        "p":0.7748161765,
-        "r":0.7587758776,
-        "f":0.7667121419
+        "p":0.7632042254,
+        "r":0.7803780378,
+        "f":0.7716955941
       },
       "obj":{
-        "p":0.8656036446,
-        "r":0.8539325843,
-        "f":0.8597285068
+        "p":0.866359447,
+        "r":0.8449438202,
+        "f":0.8555176337
       },
       "root":{
-        "p":0.7928730512,
-        "r":0.7928730512,
-        "f":0.7928730512
+        "p":0.8031674208,
+        "r":0.7906458797,
+        "f":0.7968574635
       },
       "cc":{
-        "p":0.7205882353,
-        "r":0.7221052632,
-        "f":0.7213459516
+        "p":0.7052154195,
+        "r":0.6547368421,
+        "f":0.6790393013
       },
       "conj":{
-        "p":0.5389473684,
-        "r":0.5333333333,
-        "f":0.5361256545
+        "p":0.4448669202,
+        "r":0.4875,
+        "f":0.4652087475
       },
       "advmod":{
-        "p":0.738317757,
+        "p":0.7745098039,
         "r":0.8315789474,
-        "f":0.7821782178
+        "f":0.8020304569
       },
       "flat:name":{
-        "p":0.8347826087,
-        "r":0.8971962617,
-        "f":0.8648648649
+        "p":0.7782426778,
+        "r":0.8691588785,
+        "f":0.821192053
       },
       "appos":{
-        "p":0.3089430894,
-        "r":0.4042553191,
-        "f":0.3502304147
+        "p":0.3620689655,
+        "r":0.2234042553,
+        "f":0.2763157895
       },
       "advcl":{
-        "p":0.3015873016,
-        "r":0.193877551,
-        "f":0.2360248447
+        "p":0.2857142857,
+        "r":0.2448979592,
+        "f":0.2637362637
       },
       "advmod:tlocy":{
-        "p":0.6281588448,
-        "r":0.7565217391,
-        "f":0.6863905325
+        "p":0.6680497925,
+        "r":0.7,
+        "f":0.6836518047
       },
       "ccomp:obj":{
-        "p":0.3243243243,
-        "r":0.3636363636,
-        "f":0.3428571429
+        "p":0.2592592593,
+        "r":0.2121212121,
+        "f":0.2333333333
       },
       "mark":{
-        "p":0.8227848101,
-        "r":0.8227848101,
-        "f":0.8227848101
+        "p":0.825,
+        "r":0.835443038,
+        "f":0.8301886792
       },
       "compound:preverb":{
-        "p":0.8869565217,
-        "r":0.9357798165,
-        "f":0.9107142857
+        "p":0.9528301887,
+        "r":0.9266055046,
+        "f":0.9395348837
       },
       "advmod:locy":{
-        "p":0.6842105263,
-        "r":0.40625,
-        "f":0.5098039216
+        "p":0.7368421053,
+        "r":0.4375,
+        "f":0.5490196078
       },
       "cop":{
-        "p":0.7777777778,
-        "r":0.512195122,
-        "f":0.6176470588
+        "p":0.8709677419,
+        "r":0.6585365854,
+        "f":0.75
       },
       "nmod:obl":{
-        "p":0.1904761905,
-        "r":0.1,
-        "f":0.131147541
+        "p":0.0967741935,
+        "r":0.075,
+        "f":0.0845070423
       },
       "advmod:to":{
         "p":0.0,
@@ -1484,86 +1484,86 @@
         "f":0.0
       },
       "obj:lvc":{
-        "p":0.3333333333,
+        "p":0.2,
         "r":0.0833333333,
-        "f":0.1333333333
+        "f":0.1176470588
       },
       "ccomp:obl":{
-        "p":0.3783783784,
-        "r":0.4375,
-        "f":0.4057971014
+        "p":0.4137931034,
+        "r":0.375,
+        "f":0.393442623
       },
       "iobj":{
         "p":0.2222222222,
         "r":0.2666666667,
         "f":0.2424242424
       },
-      "csubj":{
-        "p":0.4545454545,
-        "r":0.4054054054,
-        "f":0.4285714286
-      },
       "case":{
         "p":0.9384615385,
         "r":0.9336734694,
         "f":0.9360613811
       },
+      "csubj":{
+        "p":0.5263157895,
+        "r":0.2702702703,
+        "f":0.3571428571
+      },
       "parataxis":{
-        "p":0.1304347826,
+        "p":0.0967741935,
         "r":0.0410958904,
-        "f":0.0625
+        "f":0.0576923077
       },
       "xcomp":{
-        "p":0.8051948052,
-        "r":0.8378378378,
-        "f":0.821192053
+        "p":0.8309859155,
+        "r":0.7972972973,
+        "f":0.8137931034
       },
       "nummod":{
-        "p":0.5825242718,
-        "r":0.6451612903,
-        "f":0.612244898
+        "p":0.5151515152,
+        "r":0.5483870968,
+        "f":0.53125
       },
       "acl":{
-        "p":0.4418604651,
-        "r":0.2638888889,
-        "f":0.3304347826
+        "p":0.35,
+        "r":0.2916666667,
+        "f":0.3181818182
       },
       "advmod:tto":{
-        "p":1.0,
+        "p":0.3333333333,
         "r":0.2,
-        "f":0.3333333333
+        "f":0.25
       },
       "nmod":{
-        "p":0.6666666667,
-        "r":0.1818181818,
-        "f":0.2857142857
+        "p":0.0,
+        "r":0.0,
+        "f":0.0
       },
-      "ccomp":{
+      "orphan":{
         "p":0.0,
         "r":0.0,
         "f":0.0
       },
       "aux":{
-        "p":0.9,
+        "p":0.6923076923,
         "r":0.75,
-        "f":0.8181818182
+        "f":0.72
       },
       "advmod:tfrom":{
         "p":0.0,
         "r":0.0,
         "f":0.0
       },
-      "dep":{
+      "goeswith":{
         "p":0.0,
         "r":0.0,
         "f":0.0
       },
       "compound":{
-        "p":0.8863636364,
-        "r":0.975,
-        "f":0.9285714286
+        "p":1.0,
+        "r":0.95,
+        "f":0.9743589744
       },
-      "goeswith":{
+      "dep":{
         "p":0.0,
         "r":0.0,
         "f":0.0
@@ -1573,7 +1573,7 @@
         "r":0.0,
         "f":0.0
       },
-      "orphan":{
+      "ccomp:pred":{
         "p":0.0,
         "r":0.0,
         "f":0.0
@@ -1584,47 +1584,47 @@
         "f":0.0
       },
       "list":{
-        "p":0.5,
+        "p":0.3333333333,
         "r":0.1666666667,
-        "f":0.25
+        "f":0.2222222222
       },
-      "advmod:que":{
-        "p":1.0,
-        "r":0.25,
-        "f":0.4
-      },
-      "ccomp:pred":{
+      "ccomp":{
         "p":0.0,
         "r":0.0,
         "f":0.0
+      },
+      "advmod:que":{
+        "p":1.0,
+        "r":0.5,
+        "f":0.6666666667
       }
     },
-    "ents_p":0.8497702368,
-    "ents_r":0.8452883263,
-    "ents_f":0.8475233562,
+    "ents_p":0.8538804639,
+    "ents_r":0.8414205345,
+    "ents_f":0.8476047109,
     "ents_per_type":{
       "ORG":{
-        "p":0.8752844788,
-        "r":0.8915159944,
-        "f":0.8833256775
+        "p":0.8906616612,
+        "r":0.8799258229,
+        "f":0.885261194
       },
       "PER":{
-        "p":0.8858858859,
-        "r":0.8811230585,
-        "f":0.8834980533
+        "p":0.8780343398,
+        "r":0.8859020311,
+        "f":0.8819506393
       },
       "LOC":{
-        "p":0.8506044905,
-        "r":0.8550347222,
-        "f":0.8528138528
+        "p":0.8319467554,
+        "r":0.8680555556,
+        "f":0.849617672
       },
       "MISC":{
-        "p":0.6661442006,
-        "r":0.6028368794,
-        "f":0.6329113924
+        "p":0.6946826758,
+        "r":0.5744680851,
+        "f":0.6288819876
       }
     },
-    "speed":1259.7239901425
+    "speed":1647.1163178561
   },
   "sources":[
     {

morphologizer/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dedb9053d0bc36e144f994933de534c747fd86c85180a8a88e49937199a5bf01
+oid sha256:fb55fe1dc3128f37f28a20a0dd8b70829df283d3123285c7c16d068471b87d7c
 size 463022

ner/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bb93284bf257b90b22ab66c5a53090e2e1c3fd2260d90f97f15a1832040d78f
+oid sha256:451ca0c6fb687947ed78301c4fa5c5403d0e665d2012ee0779fcf32baffd2dde
 size 9791307

parser/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b127e01a46ede8b47e10b5c113c1fd9303620c9df77658b0befdfeb5b3a6709
+oid sha256:44b4d0897ca9b8e73a03e395a6c36e6131671ce42531a363bb4c3d4f5baf19e6
 size 25601129

senter/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0b654a70ba202d8fb813f136f3d703ae902fd0646602e82f0293120e73b48fa
+oid sha256:650ef98af60d6d6a69e4d7cfae24d716e01be29f57e5577efee49ef446e53836
 size 1237

tagger/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9ae0fafff0e8bffef80c9045ed55b54b49586797481092703e3e6708d38b63c
+oid sha256:dd64ac2ddafb228f96f78de78c204016c066ee1c9165271a046cc0f4eb4ff349
 size 7297

tok2vec/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcc2edbad2d63cf63e8f258ce543502136db2d1072d2ef4d896bf878b2240297
+oid sha256:2543454af11f0309d8befc666384792d14d4f37f62e4a5353c02082d679caf4e
 size 9659749

vocab/strings.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b16206bb3621439af10ddc4edb47e8104e001dbea66ff839f8d2c472862148d
-size 6405644
+oid sha256:2fbe693d307c0dfb4d1d6fda2e585ae1a7ebdac732f78590d3e281a4aa5c340f
+size 6404704