Update spacy pipeline to 3.4.4

README.md

@@ -14,70 +14,70 @@ model-index:
     metrics:
     - name: NER Precision
       type: precision
-      value: 0.8691184424
+      value: 0.8562160267
     - name: NER Recall
       type: recall
-      value: 0.8475738397
+      value: 0.8584739803
     - name: NER F Score
       type: f_score
-      value: 0.8582109479
+      value: 0.8573435168
   - task:
       name: TAG
       type: token-classification
     metrics:
     - name: TAG (XPOS) Accuracy
       type: accuracy
-      value: 0.9655007417
+      value: 0.9677481099
   - task:
       name: POS
       type: token-classification
     metrics:
     - name: POS (UPOS) Accuracy
       type: accuracy
-      value: 0.9649265515
+      value: 0.9688965451
   - task:
       name: MORPH
       type: token-classification
     metrics:
     - name: Morph (UFeats) Accuracy
       type: accuracy
-      value: 0.9323380228
+      value: 0.9386544167
   - task:
       name: LEMMA
       type: token-classification
     metrics:
     - name: Lemma Accuracy
       type: accuracy
-      value: 0.9721557746
+      value: 0.9746435748
   - task:
       name: UNLABELED_DEPENDENCIES
       type: token-classification
     metrics:
     - name: Unlabeled Attachment Score (UAS)
       type: f_score
-      value: 0.817726787
+      value: 0.8253255501
   - task:
       name: LABELED_DEPENDENCIES
       type: token-classification
     metrics:
     - name: Labeled Attachment Score (LAS)
       type: f_score
-      value: 0.7468226296
+      value: 0.7556129322
   - task:
       name: SENTS
       type: token-classification
     metrics:
     - name: Sentences F-Score
       type: f_score
-      value: 0.9799554566
+      value: 0.9854748603
 ---
 Core Hungarian model for HuSpaCy. Components: tok2vec, senter, tagger, morphologizer, lemmatizer, parser, ner
 
 | Feature | Description |
 | --- | --- |
 | **Name** | `hu_core_news_lg` |
-| **Version** | `3.4.3` |
-| **spaCy** | `>=3.4.1,<3.5.0` |
+| **Version** | `3.4.4` |
+| **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 (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` | 98.00 |
-| `SENTS_R` | 98.00 |
-| `SENTS_F` | 98.00 |
-| `TAG_ACC` | 96.55 |
-| `POS_ACC` | 96.49 |
-| `MORPH_ACC` | 93.23 |
-| `MORPH_MICRO_P` | 96.56 |
-| `MORPH_MICRO_R` | 96.00 |
-| `MORPH_MICRO_F` | 96.28 |
-| `LEMMA_ACC` | 97.22 |
-| `DEP_UAS` | 81.77 |
-| `DEP_LAS` | 74.68 |
-| `ENTS_P` | 86.91 |
-| `ENTS_R` | 84.76 |
-| `ENTS_F` | 85.82 |
+| `SENTS_P` | 98.88 |
+| `SENTS_R` | 98.22 |
+| `SENTS_F` | 98.55 |
+| `TAG_ACC` | 96.77 |
+| `POS_ACC` | 96.89 |
+| `MORPH_ACC` | 93.87 |
+| `MORPH_MICRO_P` | 97.02 |
+| `MORPH_MICRO_R` | 96.36 |
+| `MORPH_MICRO_F` | 96.69 |
+| `LEMMA_ACC` | 97.46 |
+| `DEP_UAS` | 82.53 |
+| `DEP_LAS` | 75.56 |
+| `ENTS_P` | 85.62 |
+| `ENTS_R` | 85.85 |
+| `ENTS_F` | 85.73 |

config.cfg

@@ -1,7 +1,8 @@
 [paths]
-parser_model = "models/hu_core_news_lg-parser-3.4.3/model-best"
-ner_model = "models/hu_core_news_lg-ner-3.4.3/model-best"
-lemmatizer_lookups = "models/hu_core_news_lg-lookup-lemmatizer-3.4.3"
+parser_model = "models/hu_core_news_lg-parser-3.4.4/model-best"
+ner_model = "models/hu_core_news_lg-ner-3.4.4/model-best"
+lemmatizer_lookups = "models/hu_core_news_lg-lookup-lemmatizer-3.4.4"
+tagger_model = "models/hu_core_news_lg-tagger-3.4.4/model-best"
 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:eb17441df69b4263659578eae2620dc78c836c482d0b2ce599785e84adb476d2
-size 401383136
+oid sha256:1172017d4073bae4d8a6dd9cb8409c733dd11103cdca641ffa2bee56abfa02d8
+size 401297480

lemmatizer/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f50f94a424a02435bedd1a0180467018053ff56b97ee540d45264be8cd5a71a
+oid sha256:85daf1dcf02269cbc55eae70063985b855bf0d00bb15fe4736aaae971274442c
 size 61643136

meta.json

@@ -1,13 +1,13 @@
 {
   "lang":"hu",
   "name":"core_news_lg",
-  "version":"3.4.3",
+  "version":"3.4.4",
   "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":300,
@@ -1273,80 +1273,80 @@
     "token_p":0.998565417,
     "token_r":0.9993300153,
     "token_f":0.9989475698,
-    "sents_p":0.9799554566,
-    "sents_r":0.9799554566,
-    "sents_f":0.9799554566,
-    "tag_acc":0.9655007417,
-    "pos_acc":0.9649265515,
-    "morph_acc":0.9323380228,
-    "morph_micro_p":0.9655530103,
-    "morph_micro_r":0.960034379,
-    "morph_micro_f":0.9627857866,
+    "sents_p":0.9887892377,
+    "sents_r":0.9821826281,
+    "sents_f":0.9854748603,
+    "tag_acc":0.9677481099,
+    "pos_acc":0.9688965451,
+    "morph_acc":0.9386544167,
+    "morph_micro_p":0.9702319142,
+    "morph_micro_r":0.9636441771,
+    "morph_micro_f":0.9669268251,
     "morph_per_feat":{
       "Definite":{
-        "p":0.9563239308,
-        "r":0.9808679421,
-        "f":0.9684404515
+        "p":0.968202765,
+        "r":0.9804013066,
+        "f":0.9742638535
       },
       "PronType":{
-        "p":0.9755826859,
-        "r":0.9701986755,
-        "f":0.9728832319
+        "p":0.9784292035,
+        "r":0.9762693157,
+        "f":0.9773480663
       },
       "Case":{
-        "p":0.9743281187,
-        "r":0.9598893499,
-        "f":0.9670548422
+        "p":0.9764940239,
+        "r":0.9685832839,
+        "f":0.9725225672
       },
       "Degree":{
-        "p":0.9259911894,
-        "r":0.8743760399,
-        "f":0.8994437313
+        "p":0.9280639432,
+        "r":0.8693843594,
+        "f":0.897766323
       },
       "Number":{
-        "p":0.9868332208,
-        "r":0.9797218033,
-        "f":0.9832646539
+        "p":0.9873694847,
+        "r":0.9825708061,
+        "f":0.9849643007
       },
       "Mood":{
-        "p":0.919527897,
-        "r":0.9501108647,
-        "f":0.9345692475
+        "p":0.9268558952,
+        "r":0.9412416851,
+        "f":0.9339933993
       },
       "Person":{
-        "p":0.9466776046,
-        "r":0.9490131579,
-        "f":0.9478439425
+        "p":0.9547697368,
+        "r":0.9547697368,
+        "f":0.9547697368
       },
       "Tense":{
-        "p":0.9484978541,
+        "p":0.9650655022,
         "r":0.9767955801,
-        "f":0.9624387588
+        "f":0.9708951126
       },
       "VerbForm":{
-        "p":0.9425758819,
-        "r":0.9214113873,
-        "f":0.9318734793
+        "p":0.9607351713,
+        "r":0.9222133119,
+        "f":0.9410801964
       },
       "Voice":{
-        "p":0.9494047619,
-        "r":0.9785276074,
-        "f":0.9637462236
+        "p":0.9596367306,
+        "r":0.972392638,
+        "f":0.9659725749
       },
       "Number[psor]":{
-        "p":0.9794721408,
-        "r":0.9515669516,
-        "f":0.9653179191
+        "p":0.9754689755,
+        "r":0.962962963,
+        "f":0.9691756272
       },
       "Person[psor]":{
-        "p":0.9780058651,
-        "r":0.9514978602,
-        "f":0.9645697758
+        "p":0.974025974,
+        "r":0.9629101284,
+        "f":0.9684361549
       },
       "NumType":{
-        "p":0.9312039312,
-        "r":0.9243902439,
-        "f":0.9277845777
+        "p":0.9304556355,
+        "r":0.9463414634,
+        "f":0.938331318
       },
       "Poss":{
         "p":0.75,
@@ -1369,114 +1369,114 @@
         "f":0.0
       }
     },
-    "lemma_acc":0.9721557746,
-    "dep_uas":0.817726787,
-    "dep_las":0.7468226296,
+    "lemma_acc":0.9746435748,
+    "dep_uas":0.8253255501,
+    "dep_las":0.7556129322,
     "dep_las_per_type":{
       "det":{
-        "p":0.8741092637,
-        "r":0.8789808917,
-        "f":0.8765383089
+        "p":0.8596625767,
+        "r":0.8925159236,
+        "f":0.87578125
       },
       "amod:att":{
-        "p":0.8474159147,
-        "r":0.8446443173,
-        "f":0.846027846
+        "p":0.8714893617,
+        "r":0.8372853639,
+        "f":0.8540450375
       },
       "nsubj":{
-        "p":0.7521079258,
-        "r":0.696875,
-        "f":0.7234387672
+        "p":0.7471636953,
+        "r":0.7203125,
+        "f":0.7334924423
       },
       "advmod:mode":{
-        "p":0.5654205607,
-        "r":0.5931372549,
-        "f":0.5789473684
+        "p":0.5889423077,
+        "r":0.6004901961,
+        "f":0.5946601942
       },
       "nmod:att":{
-        "p":0.7138599106,
-        "r":0.8118644068,
-        "f":0.7597145123
+        "p":0.7436305732,
+        "r":0.7915254237,
+        "f":0.7668308703
       },
       "obl":{
-        "p":0.7915518825,
-        "r":0.7758775878,
-        "f":0.7836363636
+        "p":0.758828596,
+        "r":0.7929792979,
+        "f":0.775528169
       },
       "obj":{
-        "p":0.8574660633,
-        "r":0.8516853933,
-        "f":0.8545659526
+        "p":0.8697674419,
+        "r":0.8404494382,
+        "f":0.8548571429
       },
       "root":{
-        "p":0.7995545657,
-        "r":0.7995545657,
-        "f":0.7995545657
+        "p":0.8273542601,
+        "r":0.8218262806,
+        "f":0.8245810056
       },
       "cc":{
-        "p":0.7311320755,
-        "r":0.6526315789,
-        "f":0.6896551724
+        "p":0.704595186,
+        "r":0.6778947368,
+        "f":0.6909871245
       },
       "conj":{
-        "p":0.5440806045,
-        "r":0.45,
-        "f":0.4925883694
+        "p":0.5520833333,
+        "r":0.5520833333,
+        "f":0.5520833333
       },
       "advmod":{
-        "p":0.81,
-        "r":0.8526315789,
-        "f":0.8307692308
+        "p":0.79,
+        "r":0.8315789474,
+        "f":0.8102564103
       },
       "flat:name":{
-        "p":0.847826087,
-        "r":0.9112149533,
-        "f":0.8783783784
+        "p":0.8354978355,
+        "r":0.9018691589,
+        "f":0.8674157303
       },
       "appos":{
-        "p":0.35,
-        "r":0.2978723404,
-        "f":0.3218390805
+        "p":0.3529411765,
+        "r":0.3191489362,
+        "f":0.3351955307
       },
       "advcl":{
-        "p":0.3015873016,
-        "r":0.387755102,
-        "f":0.3392857143
+        "p":0.3506493506,
+        "r":0.2755102041,
+        "f":0.3085714286
       },
       "advmod:tlocy":{
-        "p":0.683127572,
-        "r":0.7217391304,
-        "f":0.7019027484
+        "p":0.75,
+        "r":0.6652173913,
+        "f":0.7050691244
       },
       "ccomp:obj":{
-        "p":0.2745098039,
-        "r":0.4242424242,
-        "f":0.3333333333
+        "p":0.2285714286,
+        "r":0.4848484848,
+        "f":0.3106796117
       },
       "mark":{
-        "p":0.7974683544,
-        "r":0.7974683544,
-        "f":0.7974683544
+        "p":0.8238993711,
+        "r":0.8291139241,
+        "f":0.8264984227
       },
       "compound:preverb":{
-        "p":0.9017857143,
-        "r":0.9266055046,
-        "f":0.9140271493
+        "p":0.8849557522,
+        "r":0.9174311927,
+        "f":0.9009009009
       },
       "advmod:locy":{
-        "p":0.8421052632,
-        "r":0.5,
-        "f":0.6274509804
+        "p":0.8095238095,
+        "r":0.53125,
+        "f":0.641509434
       },
       "cop":{
-        "p":0.5106382979,
+        "p":0.6857142857,
         "r":0.5853658537,
-        "f":0.5454545455
+        "f":0.6315789474
       },
       "nmod:obl":{
-        "p":0.1923076923,
-        "r":0.25,
-        "f":0.2173913043
+        "p":0.2941176471,
+        "r":0.125,
+        "f":0.1754385965
       },
       "advmod:to":{
         "p":0.0,
@@ -1484,147 +1484,147 @@
         "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":1.0,
-        "r":0.21875,
-        "f":0.358974359
+        "p":0.3333333333,
+        "r":0.3125,
+        "f":0.3225806452
       },
       "iobj":{
-        "p":0.1666666667,
+        "p":0.2,
         "r":0.2,
-        "f":0.1818181818
-      },
-      "csubj":{
-        "p":0.2909090909,
-        "r":0.4324324324,
-        "f":0.347826087
+        "f":0.2
       },
       "case":{
-        "p":0.9226804124,
-        "r":0.9132653061,
-        "f":0.9179487179
+        "p":0.9494949495,
+        "r":0.9591836735,
+        "f":0.9543147208
+      },
+      "csubj":{
+        "p":0.5789473684,
+        "r":0.2972972973,
+        "f":0.3928571429
       },
       "parataxis":{
-        "p":0.0526315789,
-        "r":0.0136986301,
-        "f":0.0217391304
+        "p":0.25,
+        "r":0.0684931507,
+        "f":0.1075268817
       },
       "xcomp":{
-        "p":0.8815789474,
-        "r":0.9054054054,
-        "f":0.8933333333
+        "p":0.8648648649,
+        "r":0.8648648649,
+        "f":0.8648648649
       },
       "nummod":{
-        "p":0.5480769231,
-        "r":0.6129032258,
-        "f":0.578680203
+        "p":0.5566037736,
+        "r":0.6344086022,
+        "f":0.5929648241
+      },
+      "ccomp:pred":{
+        "p":0.0,
+        "r":0.0,
+        "f":0.0
       },
       "acl":{
-        "p":0.4,
-        "r":0.3333333333,
-        "f":0.3636363636
+        "p":0.4461538462,
+        "r":0.4027777778,
+        "f":0.4233576642
       },
       "advmod:tto":{
-        "p":0.5555555556,
-        "r":0.5,
-        "f":0.5263157895
+        "p":0.5,
+        "r":0.3,
+        "f":0.375
       },
       "nmod":{
-        "p":0.2,
+        "p":0.5,
         "r":0.0909090909,
-        "f":0.125
-      },
-      "orphan":{
-        "p":0.0,
-        "r":0.0,
-        "f":0.0
+        "f":0.1538461538
       },
       "aux":{
-        "p":0.625,
-        "r":0.4166666667,
-        "f":0.5
+        "p":1.0,
+        "r":0.9166666667,
+        "f":0.9565217391
       },
       "advmod:tfrom":{
         "p":0.0,
         "r":0.0,
         "f":0.0
       },
+      "list":{
+        "p":0.25,
+        "r":0.1666666667,
+        "f":0.2
+      },
       "goeswith":{
         "p":0.0,
         "r":0.0,
         "f":0.0
       },
       "compound":{
-        "p":0.975,
+        "p":0.847826087,
         "r":0.975,
-        "f":0.975
+        "f":0.9069767442
+      },
+      "orphan":{
+        "p":0.0,
+        "r":0.0,
+        "f":0.0
       },
       "obl:lvc":{
         "p":0.0,
         "r":0.0,
         "f":0.0
       },
-      "nsubj:lvc":{
+      "ccomp":{
         "p":0.0,
         "r":0.0,
         "f":0.0
       },
-      "list":{
-        "p":0.5,
-        "r":0.1666666667,
-        "f":0.25
+      "nsubj:lvc":{
+        "p":0.0,
+        "r":0.0,
+        "f":0.0
       },
       "dep":{
         "p":0.0,
         "r":0.0,
         "f":0.0
       },
-      "ccomp":{
-        "p":1.0,
-        "r":0.0769230769,
-        "f":0.1428571429
-      },
       "advmod:que":{
         "p":1.0,
         "r":0.75,
         "f":0.8571428571
-      },
-      "ccomp:pred":{
-        "p":0.0,
-        "r":0.0,
-        "f":0.0
       }
     },
-    "ents_p":0.8691184424,
-    "ents_r":0.8475738397,
-    "ents_f":0.8582109479,
+    "ents_p":0.8562160267,
+    "ents_r":0.8584739803,
+    "ents_f":0.8573435168,
     "ents_per_type":{
       "ORG":{
-        "p":0.8996229972,
-        "r":0.8850254984,
-        "f":0.8922645478
+        "p":0.8751135332,
+        "r":0.8933704219,
+        "f":0.8841477403
       },
       "PER":{
-        "p":0.9,
-        "r":0.8817204301,
-        "f":0.8907664454
+        "p":0.8883638512,
+        "r":0.8984468339,
+        "f":0.8933768934
       },
       "LOC":{
-        "p":0.8856358646,
-        "r":0.8402777778,
-        "f":0.8623608018
+        "p":0.8708838821,
+        "r":0.8723958333,
+        "f":0.8716392021
       },
       "MISC":{
-        "p":0.676300578,
-        "r":0.6638297872,
-        "f":0.6700071582
+        "p":0.6834862385,
+        "r":0.6340425532,
+        "f":0.6578366446
       }
     },
-    "speed":697.1804121658
+    "speed":751.1564325647
   },
   "sources":[
     {

morphologizer/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b3624803285648e2e132f8fea933a4d4b26d0565d90a2f32859a52459958b0b
+oid sha256:83cd90052b254ff769760001680ee01a105cd2df39d93e4902a2681164c3465e
 size 1379030

ner/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94a238ac4d4ca961fbaa6f6e2eb43d84c591fe2b5157b30155351449764b8444
+oid sha256:a4f5c6d8cbbfb0934a55fd49de3c53cc7c4b8f70c5e1ffa657460e0a541328cc
 size 56989063

parser/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73f021fc2c0fdb9446c0c2265795ec3349029c7bff0606b639392d571a135d1b
+oid sha256:a57c0fb203857ce6024c445bf9e08aeae8c0c7b1be63309a285f007f4ee9e0ee
 size 26010735

senter/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a6c3ec7f266497f2ad94d6f1e4d7c0116d35f6250c5203d50fc12f29059ef91
+oid sha256:1918abafe131dc988c2f0bc2e2e24bd46db6d3a9366d5ddcc85ea1802ba6c557
 size 2845

tagger/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7afc9d54a8904da0ea469c94e1a1412fb3ed096596b3ead91c3f377bd153f00d
+oid sha256:e233a6f0db6c32b415b6816de93f603a9d036d067e8cef1fc0fb2874437b8783
 size 20905

tok2vec/model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58de33def1393ccc8e96c3521f93399b6ec3714783972913d3ff7fef2961f337
+oid sha256:bf651fc7d357bd69fc9c5895aafbed8dde314daf26b08cd902734146f62aff59
 size 56806299

vocab/strings.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6fb182a7cd7269248b0d702c6b4f2d0a59c00fffa84a484ad9e43a21cbdd3a8
-size 6402737
+oid sha256:5669f47f9ca1920bfa25badab84fffa361b5be9bf289af72cf80b75954ff4ec4
+size 6403407