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
fafa09c
raw history blame
No virus
7.96 kB
{
"lang":"ja",
"name":"core_news_lg",
"version":"3.7.0",
"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":">=3.7.0,<3.8.0",
"spacy_git_version":"6b4f77441",
"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":0.9936678032,
"token_p":0.9763760351,
"token_r":0.9788394238,
"token_f":0.9776061776,
"pos_acc":0.9742268041,
"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":0.9555984556,
"sents_r":0.9763313609,
"sents_f":0.9658536585,
"dep_uas":0.9212481426,
"dep_las":0.9089518668,
"dep_las_per_type":{
"cc":{
"p":0.7777777778,
"r":0.7291666667,
"f":0.752688172
},
"compound":{
"p":0.942206655,
"r":0.9098083427,
"f":0.9257241182
},
"obl":{
"p":0.840357599,
"r":0.8214731586,
"f":0.8308080808
},
"case":{
"p":0.9892638037,
"r":0.9802431611,
"f":0.9847328244
},
"dislocated":{
"p":0.5384615385,
"r":0.5384615385,
"f":0.5384615385
},
"nsubj":{
"p":0.8027079304,
"r":0.7965451056,
"f":0.7996146435
},
"nmod":{
"p":0.8683886839,
"r":0.8257309942,
"f":0.8465227818
},
"root":{
"p":0.9607843137,
"r":0.966469428,
"f":0.9636184857
},
"aux":{
"p":0.9814986124,
"r":0.9851439183,
"f":0.9833178869
},
"advcl":{
"p":0.698630137,
"r":0.6876404494,
"f":0.6930917327
},
"mark":{
"p":0.9776876268,
"r":0.964,
"f":0.970795569
},
"fixed":{
"p":0.9501779359,
"r":0.9709090909,
"f":0.9604316547
},
"acl":{
"p":0.825708061,
"r":0.832967033,
"f":0.829321663
},
"obj":{
"p":0.9571865443,
"r":0.9456193353,
"f":0.9513677812
},
"nummod":{
"p":0.9934210526,
"r":0.8934911243,
"f":0.9408099688
},
"advmod":{
"p":0.7050359712,
"r":0.7,
"f":0.7025089606
},
"amod":{
"p":0.935483871,
"r":0.7837837838,
"f":0.8529411765
},
"cop":{
"p":0.9761904762,
"r":0.9534883721,
"f":0.9647058824
},
"ccomp":{
"p":0.95,
"r":0.8636363636,
"f":0.9047619048
},
"det":{
"p":1.0,
"r":0.9433962264,
"f":0.9708737864
},
"csubj":{
"p":0.7333333333,
"r":0.9166666667,
"f":0.8148148148
},
"dep":{
"p":0.3333333333,
"r":0.1428571429,
"f":0.2
}
},
"tag_acc":0.9713282143,
"lemma_acc":0.9670499959,
"ents_p":0.7388362652,
"ents_r":0.6867924528,
"ents_f":0.7118644068,
"ents_per_type":{
"DATE":{
"p":0.9626168224,
"r":0.9449541284,
"f":0.9537037037
},
"ORG":{
"p":0.6090225564,
"r":0.5912408759,
"f":0.6
},
"PERSON":{
"p":0.7883211679,
"r":0.7769784173,
"f":0.7826086957
},
"GPE":{
"p":0.6666666667,
"r":0.6595744681,
"f":0.6631016043
},
"PRODUCT":{
"p":0.5769230769,
"r":0.3571428571,
"f":0.4411764706
},
"TIME":{
"p":0.5714285714,
"r":1.0,
"f":0.7272727273
},
"QUANTITY":{
"p":0.8823529412,
"r":0.9090909091,
"f":0.8955223881
},
"NORP":{
"p":0.6206896552,
"r":0.5625,
"f":0.5901639344
},
"TITLE_AFFIX":{
"p":0.7727272727,
"r":0.5666666667,
"f":0.6538461538
},
"ORDINAL":{
"p":0.56,
"r":0.6363636364,
"f":0.5957446809
},
"WORK_OF_ART":{
"p":0.8461538462,
"r":0.6470588235,
"f":0.7333333333
},
"FAC":{
"p":0.64,
"r":0.4324324324,
"f":0.5161290323
},
"EVENT":{
"p":0.6315789474,
"r":0.4615384615,
"f":0.5333333333
},
"PERCENT":{
"p":1.0,
"r":0.2857142857,
"f":0.4444444444
},
"CARDINAL":{
"p":0.0,
"r":0.0,
"f":0.0
},
"LOC":{
"p":0.6666666667,
"r":0.8,
"f":0.7272727273
},
"PET_NAME":{
"p":0.0,
"r":0.0,
"f":0.0
},
"MOVEMENT":{
"p":0.2,
"r":0.2,
"f":0.2
},
"LAW":{
"p":1.0,
"r":0.3333333333,
"f":0.5
},
"MONEY":{
"p":1.0,
"r":1.0,
"f":1.0
},
"LANGUAGE":{
"p":1.0,
"r":1.0,
"f":1.0
}
},
"speed":8472.2177519611
},
"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"
]
}