ja_core_news_md / meta.json
EC2 Default User
Update spaCy pipeline
102bb34
raw history blame
No virus
7.89 kB
{
"lang":"ja",
"name":"core_news_md",
"version":"3.3.0",
"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":">=3.3.0.dev0,<3.4.0",
"spacy_git_version":"849bef2de",
"vectors":{
"width":300,
"vectors":20000,
"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=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":0.9968649485,
"token_p":0.9764591282,
"token_r":0.9790021974,
"token_f":0.9777290092,
"pos_acc":0.9708372531,
"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":0.9940828402,
"sents_r":0.9940828402,
"sents_f":0.9940828402,
"dep_uas":0.9211237169,
"dep_las":0.9075282365,
"dep_las_per_type":{
"cc":{
"p":0.8125,
"r":0.8125,
"f":0.8125
},
"compound":{
"p":0.9490930369,
"r":0.9143179256,
"f":0.9313809934
},
"obl":{
"p":0.80875,
"r":0.8077403246,
"f":0.808244847
},
"case":{
"p":0.9884925201,
"r":0.9791033435,
"f":0.9837755297
},
"dislocated":{
"p":0.6666666667,
"r":0.4615384615,
"f":0.5454545455
},
"nsubj":{
"p":0.8146718147,
"r":0.8099808061,
"f":0.812319538
},
"nmod":{
"p":0.8869565217,
"r":0.8350877193,
"f":0.8602409639
},
"root":{
"p":0.966,
"r":0.9526627219,
"f":0.959285005
},
"aux":{
"p":0.9768732655,
"r":0.9805013928,
"f":0.9786839666
},
"advcl":{
"p":0.6876404494,
"r":0.6876404494,
"f":0.6876404494
},
"mark":{
"p":0.9696969697,
"r":0.96,
"f":0.9648241206
},
"fixed":{
"p":0.9566003617,
"r":0.9618181818,
"f":0.9592021759
},
"acl":{
"p":0.8278867102,
"r":0.8351648352,
"f":0.8315098468
},
"obj":{
"p":0.9456193353,
"r":0.9456193353,
"f":0.9456193353
},
"nummod":{
"p":0.9325153374,
"r":0.899408284,
"f":0.9156626506
},
"advmod":{
"p":0.7054263566,
"r":0.65,
"f":0.6765799257
},
"amod":{
"p":0.9642857143,
"r":0.7297297297,
"f":0.8307692308
},
"cop":{
"p":0.9700598802,
"r":0.9418604651,
"f":0.9557522124
},
"ccomp":{
"p":0.95,
"r":0.8636363636,
"f":0.9047619048
},
"det":{
"p":0.9807692308,
"r":0.9622641509,
"f":0.9714285714
},
"csubj":{
"p":0.6153846154,
"r":0.6666666667,
"f":0.64
},
"dep":{
"p":0.0,
"r":0.0,
"f":0.0
}
},
"tag_acc":0.9712488769,
"lemma_acc":0.965013864,
"ents_p":0.7384196185,
"ents_r":0.6817610063,
"ents_f":0.7089601046,
"ents_per_type":{
"DATE":{
"p":0.9722222222,
"r":0.9633027523,
"f":0.9677419355
},
"ORG":{
"p":0.6097560976,
"r":0.5474452555,
"f":0.5769230769
},
"TITLE_AFFIX":{
"p":0.8636363636,
"r":0.6333333333,
"f":0.7307692308
},
"PERSON":{
"p":0.762962963,
"r":0.7410071942,
"f":0.7518248175
},
"GPE":{
"p":0.7282608696,
"r":0.7127659574,
"f":0.7204301075
},
"PRODUCT":{
"p":0.4375,
"r":0.3333333333,
"f":0.3783783784
},
"TIME":{
"p":0.6666666667,
"r":1.0,
"f":0.8
},
"QUANTITY":{
"p":0.8769230769,
"r":0.8636363636,
"f":0.8702290076
},
"NORP":{
"p":0.72,
"r":0.5625,
"f":0.6315789474
},
"ORDINAL":{
"p":0.5172413793,
"r":0.6818181818,
"f":0.5882352941
},
"WORK_OF_ART":{
"p":0.5789473684,
"r":0.6470588235,
"f":0.6111111111
},
"FAC":{
"p":0.625,
"r":0.4054054054,
"f":0.4918032787
},
"PERCENT":{
"p":1.0,
"r":0.2857142857,
"f":0.4444444444
},
"EVENT":{
"p":0.7619047619,
"r":0.6153846154,
"f":0.6808510638
},
"CARDINAL":{
"p":0.0,
"r":0.0,
"f":0.0
},
"LOC":{
"p":0.5384615385,
"r":0.7,
"f":0.6086956522
},
"MOVEMENT":{
"p":0.0,
"r":0.0,
"f":0.0
},
"LAW":{
"p":1.0,
"r":0.3333333333,
"f":0.5
},
"PET_NAME":{
"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":8044.6200194392
},
"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"
]
}