ja_core_news_md / meta.json
adrianeboyd's picture
Update spaCy pipeline
6084989
raw history blame
No virus
7.95 kB
{
"lang":"ja",
"name":"core_news_md",
"version":"3.5.0",
"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":">=3.5.0,<3.6.0",
"spacy_git_version":"9e0322de1",
"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=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":0.9721881391,
"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":0.9708171206,
"sents_r":0.9842209073,
"sents_f":0.9774730656,
"dep_uas":0.9203675345,
"dep_las":0.9074140723,
"dep_las_per_type":{
"cc":{
"p":0.829787234,
"r":0.8125,
"f":0.8210526316
},
"compound":{
"p":0.9382284382,
"r":0.9075535513,
"f":0.9226361032
},
"obl":{
"p":0.8116480793,
"r":0.8177278402,
"f":0.8146766169
},
"case":{
"p":0.9888632873,
"r":0.978343465,
"f":0.9835752483
},
"dislocated":{
"p":0.5384615385,
"r":0.5384615385,
"f":0.5384615385
},
"nsubj":{
"p":0.8103448276,
"r":0.8119001919,
"f":0.8111217641
},
"nmod":{
"p":0.8861076345,
"r":0.8280701754,
"f":0.8561064087
},
"root":{
"p":0.9703557312,
"r":0.9684418146,
"f":0.9693978282
},
"aux":{
"p":0.9823747681,
"r":0.9832869081,
"f":0.9828306265
},
"advcl":{
"p":0.6825396825,
"r":0.6764044944,
"f":0.6794582393
},
"mark":{
"p":0.967611336,
"r":0.956,
"f":0.9617706237
},
"fixed":{
"p":0.946714032,
"r":0.9690909091,
"f":0.957771788
},
"acl":{
"p":0.8470066519,
"r":0.8395604396,
"f":0.8432671082
},
"obj":{
"p":0.9569230769,
"r":0.9395770393,
"f":0.9481707317
},
"nummod":{
"p":0.987012987,
"r":0.899408284,
"f":0.9411764706
},
"advmod":{
"p":0.6715328467,
"r":0.6571428571,
"f":0.6642599278
},
"amod":{
"p":0.962962963,
"r":0.7027027027,
"f":0.8125
},
"cop":{
"p":0.9704142012,
"r":0.9534883721,
"f":0.9618768328
},
"ccomp":{
"p":0.95,
"r":0.8636363636,
"f":0.9047619048
},
"det":{
"p":0.9807692308,
"r":0.9622641509,
"f":0.9714285714
},
"csubj":{
"p":0.7272727273,
"r":0.6666666667,
"f":0.6956521739
},
"dep":{
"p":0.25,
"r":0.1428571429,
"f":0.1818181818
}
},
"tag_acc":0.9712488769,
"lemma_acc":0.9670526831,
"ents_p":0.7121418827,
"ents_r":0.6566037736,
"ents_f":0.6832460733,
"ents_per_type":{
"DATE":{
"p":0.954954955,
"r":0.9724770642,
"f":0.9636363636
},
"ORG":{
"p":0.5675675676,
"r":0.4598540146,
"f":0.5080645161
},
"TITLE_AFFIX":{
"p":0.8181818182,
"r":0.6,
"f":0.6923076923
},
"PERSON":{
"p":0.7410071942,
"r":0.7410071942,
"f":0.7410071942
},
"GPE":{
"p":0.6875,
"r":0.7021276596,
"f":0.6947368421
},
"TIME":{
"p":0.6666666667,
"r":1.0,
"f":0.8
},
"QUANTITY":{
"p":0.8695652174,
"r":0.9090909091,
"f":0.8888888889
},
"NORP":{
"p":0.6785714286,
"r":0.59375,
"f":0.6333333333
},
"ORDINAL":{
"p":0.619047619,
"r":0.5909090909,
"f":0.6046511628
},
"WORK_OF_ART":{
"p":0.6666666667,
"r":0.5882352941,
"f":0.625
},
"CARDINAL":{
"p":1.0,
"r":0.5,
"f":0.6666666667
},
"FAC":{
"p":0.5384615385,
"r":0.3783783784,
"f":0.4444444444
},
"PERCENT":{
"p":1.0,
"r":0.2857142857,
"f":0.4444444444
},
"EVENT":{
"p":0.9285714286,
"r":0.5,
"f":0.65
},
"LOC":{
"p":0.4117647059,
"r":0.7,
"f":0.5185185185
},
"MOVEMENT":{
"p":0.0,
"r":0.0,
"f":0.0
},
"PRODUCT":{
"p":0.2857142857,
"r":0.2380952381,
"f":0.2597402597
},
"LAW":{
"p":0.0,
"r":0.0,
"f":0.0
},
"MONEY":{
"p":1.0,
"r":1.0,
"f":1.0
},
"LANGUAGE":{
"p":0.75,
"r":1.0,
"f":0.8571428571
},
"PET_NAME":{
"p":0.0,
"r":0.0,
"f":0.0
}
},
"speed":9629.4441452948
},
"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"
]
}