Hugging Face's logo

spacy
/
ja_core_news_lg

Token Classification
spaCy
Japanese
Eval Results
Model card Files Community
ja_core_news_lg / meta.json
adrianeboyd's picture
adrianeboyd
Update spaCy pipeline
7538d68
raw history blame
7.86 kB
{
"lang":"ja",
"name":"core_news_lg",
"version":"3.6.0",
"description":"Japanese pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, ner, attribute_ruler.",
"author":"Explosion",
"email":"contact@explosion.ai",
"url":"https://explosion.ai",
"license":"CC BY-SA 4.0",
"spacy_version":">=3.6.0,<3.7.0",
"spacy_git_version":"cb4fdc83e",
"vectors":{
"width":300,
"vectors":480443,
"keys":480443,
"name":"ja_vectors"
},
"labels":{
"tok2vec":[
],
"morphologizer":[
"POS=NOUN",
"POS=ADP",
"POS=VERB",
"POS=SCONJ",
"POS=AUX",
"POS=PUNCT",
"POS=PART",
"POS=DET",
"POS=NUM",
"POS=ADV",
"POS=PRON",
"POS=ADJ",
"POS=PROPN",
"POS=CCONJ",
"POS=SYM",
"POS=NOUN|Polarity=Neg",
"POS=AUX|Polarity=Neg",
"POS=SPACE",
"POS=INTJ",
"POS=SCONJ|Polarity=Neg"
],
"parser":[
"ROOT",
"acl",
"advcl",
"advmod",
"amod",
"aux",
"case",
"cc",
"ccomp",
"compound",
"cop",
"csubj",
"dep",
"det",
"dislocated",
"fixed",
"mark",
"nmod",
"nsubj",
"nummod",
"obj",
"obl",
"punct"
],
"attribute_ruler":[
],
"ner":[
"CARDINAL",
"DATE",
"EVENT",
"FAC",
"GPE",
"LANGUAGE",
"LAW",
"LOC",
"MONEY",
"MOVEMENT",
"NORP",
"ORDINAL",
"ORG",
"PERCENT",
"PERSON",
"PET_NAME",
"PHONE",
"PRODUCT",
"QUANTITY",
"TIME",
"TITLE_AFFIX",
"WORK_OF_ART"
]
},
"pipeline":[
"tok2vec",
"morphologizer",
"parser",
"attribute_ruler",
"ner"
],
"components":[
"tok2vec",
"morphologizer",
"parser",
"senter",
"attribute_ruler",
"ner"
],
"disabled":[
"senter"
],
"performance":{
"token_acc":0.9937494927,
"token_p":0.9764591282,
"token_r":0.9790021974,
"token_f":0.9777290092,
"pos_acc":0.9730437272,
"morph_acc":0.0,
"morph_micro_p":0.3401360544,
"morph_micro_r":0.9803921569,
"morph_micro_f":0.5050505051,
"morph_per_feat":{
"Polarity":{
"p":1.0,
"r":0.9803921569,
"f":0.9900990099
},
"Inflection":{
"p":0.0,
"r":0.0,
"f":0.0
},
"Reading":{
"p":0.0,
"r":0.0,
"f":0.0
}
},
"sents_p":0.9631782946,
"sents_r":0.9802761341,
"sents_f":0.9716520039,
"dep_uas":0.9221626975,
"dep_las":0.9081013,
"dep_las_per_type":{
"cc":{
"p":0.847826087,
"r":0.8125,
"f":0.829787234
},
"compound":{
"p":0.9406976744,
"r":0.9120631342,
"f":0.9261591299
},
"obl":{
"p":0.8122653317,
"r":0.8102372035,
"f":0.81125
},
"case":{
"p":0.990403071,
"r":0.9802431611,
"f":0.9852969257
},
"dislocated":{
"p":0.5882352941,
"r":0.7692307692,
"f":0.6666666667
},
"nsubj":{
"p":0.8307392996,
"r":0.8195777351,
"f":0.8251207729
},
"nmod":{
"p":0.8955974843,
"r":0.832748538,
"f":0.863030303
},
"root":{
"p":0.9607072692,
"r":0.9644970414,
"f":0.9625984252
},
"aux":{
"p":0.9832713755,
"r":0.982358403,
"f":0.9828146772
},
"advcl":{
"p":0.6614349776,
"r":0.6629213483,
"f":0.6621773288
},
"mark":{
"p":0.9658634538,
"r":0.962,
"f":0.9639278557
},
"fixed":{
"p":0.9550359712,
"r":0.9654545455,
"f":0.9602169982
},
"acl":{
"p":0.8377192982,
"r":0.8395604396,
"f":0.8386388584
},
"obj":{
"p":0.9661538462,
"r":0.9486404834,
"f":0.9573170732
},
"nummod":{
"p":0.9805194805,
"r":0.8934911243,
"f":0.9349845201
},
"advmod":{
"p":0.6474820144,
"r":0.6428571429,
"f":0.6451612903
},
"amod":{
"p":0.9,
"r":0.7297297297,
"f":0.8059701493
},
"cop":{
"p":0.9467455621,
"r":0.9302325581,
"f":0.9384164223
},
"ccomp":{
"p":0.95,
"r":0.8636363636,
"f":0.9047619048
},
"det":{
"p":0.9807692308,
"r":0.9622641509,
"f":0.9714285714
},
"csubj":{
"p":0.6666666667,
"r":0.8333333333,
"f":0.7407407407
},
"dep":{
"p":0.25,
"r":0.1428571429,
"f":0.1818181818
}
},
"tag_acc":0.9713305562,
"lemma_acc":0.9670526831,
"ents_p":0.749661705,
"ents_r":0.6968553459,
"ents_f":0.7222946545,
"ents_per_type":{
"DATE":{
"p":0.9459459459,
"r":0.9633027523,
"f":0.9545454545
},
"ORG":{
"p":0.6209677419,
"r":0.5620437956,
"f":0.5900383142
},
"PERSON":{
"p":0.7622377622,
"r":0.7841726619,
"f":0.7730496454
},
"GPE":{
"p":0.7738095238,
"r":0.6914893617,
"f":0.7303370787
},
"TIME":{
"p":0.5714285714,
"r":1.0,
"f":0.7272727273
},
"QUANTITY":{
"p":0.921875,
"r":0.8939393939,
"f":0.9076923077
},
"NORP":{
"p":0.6785714286,
"r":0.59375,
"f":0.6333333333
},
"TITLE_AFFIX":{
"p":0.72,
"r":0.6,
"f":0.6545454545
},
"ORDINAL":{
"p":0.6,
"r":0.6818181818,
"f":0.6382978723
},
"WORK_OF_ART":{
"p":0.7857142857,
"r":0.6470588235,
"f":0.7096774194
},
"CARDINAL":{
"p":1.0,
"r":0.5,
"f":0.6666666667
},
"PERCENT":{
"p":0.6666666667,
"r":0.2857142857,
"f":0.4
},
"EVENT":{
"p":0.7894736842,
"r":0.5769230769,
"f":0.6666666667
},
"LOC":{
"p":0.5333333333,
"r":0.8,
"f":0.64
},
"FAC":{
"p":0.5862068966,
"r":0.4594594595,
"f":0.5151515152
},
"MOVEMENT":{
"p":0.0,
"r":0.0,
"f":0.0
},
"PRODUCT":{
"p":0.5517241379,
"r":0.380952381,
"f":0.4507042254
},
"LAW":{
"p":0.0,
"r":0.0,
"f":0.0
},
"MONEY":{
"p":1.0,
"r":1.0,
"f":1.0
},
"LANGUAGE":{
"p":1.0,
"r":1.0,
"f":1.0
}
},
"speed":8423.8901639919
},
"sources":[
{
"name":"UD Japanese GSD v2.8",
"url":"https://github.com/UniversalDependencies/UD_Japanese-GSD",
"license":"CC BY-SA 4.0",
"author":"Omura, Mai; Miyao, Yusuke; Kanayama, Hiroshi; Matsuda, Hiroshi; Wakasa, Aya; Yamashita, Kayo; Asahara, Masayuki; Tanaka, Takaaki; Murawaki, Yugo; Matsumoto, Yuji; Mori, Shinsuke; Uematsu, Sumire; McDonald, Ryan; Nivre, Joakim; Zeman, Daniel"
},
{
"name":"UD Japanese GSD v2.8 NER",
"url":"https://github.com/megagonlabs/UD_Japanese-GSD",
"license":"CC BY-SA 4.0",
"author":"Megagon Labs Tokyo"
},
{
"name":"chiVe: Japanese Word Embedding with Sudachi & NWJC (chive-1.1-mc90-500k)",
"url":"https://github.com/WorksApplications/chiVe",
"license":"Apache-2.0",
"author":"Works Applications"
}
],
"requirements":[
"sudachipy>=0.5.2,!=0.6.1",
"sudachidict-core>=20211220"
]
}