ja_core_news_md / meta.json
adrianeboyd's picture
Update spaCy pipeline
e2bbeeb
{
"lang":"ja",
"name":"core_news_md",
"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":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":0.9729199051,
"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":0.9882121807,
"sents_r":0.9921104536,
"sents_f":0.9901574803,
"dep_uas":0.9206249156,
"dep_las":0.9067758481,
"dep_las_per_type":{
"cc":{
"p":0.7872340426,
"r":0.7708333333,
"f":0.7789473684
},
"compound":{
"p":0.9375729288,
"r":0.9058624577,
"f":0.9214449541
},
"obl":{
"p":0.8119551681,
"r":0.8139825218,
"f":0.812967581
},
"case":{
"p":0.990015361,
"r":0.9794832827,
"f":0.9847211612
},
"dislocated":{
"p":0.5384615385,
"r":0.5384615385,
"f":0.5384615385
},
"nsubj":{
"p":0.8181818182,
"r":0.8119001919,
"f":0.8150289017
},
"nmod":{
"p":0.8760842627,
"r":0.8269005848,
"f":0.8507821901
},
"root":{
"p":0.9641434263,
"r":0.9546351085,
"f":0.9593657086
},
"aux":{
"p":0.977818854,
"r":0.982358403,
"f":0.9800833719
},
"advcl":{
"p":0.6826484018,
"r":0.6719101124,
"f":0.6772366931
},
"mark":{
"p":0.9738430584,
"r":0.968,
"f":0.9709127382
},
"fixed":{
"p":0.9553571429,
"r":0.9727272727,
"f":0.963963964
},
"acl":{
"p":0.8264642082,
"r":0.8373626374,
"f":0.8318777293
},
"obj":{
"p":0.9513677812,
"r":0.9456193353,
"f":0.9484848485
},
"nummod":{
"p":0.9868421053,
"r":0.8875739645,
"f":0.9345794393
},
"advmod":{
"p":0.7251908397,
"r":0.6785714286,
"f":0.7011070111
},
"amod":{
"p":0.9032258065,
"r":0.7567567568,
"f":0.8235294118
},
"cop":{
"p":0.9640718563,
"r":0.9360465116,
"f":0.9498525074
},
"ccomp":{
"p":0.9444444444,
"r":0.7727272727,
"f":0.85
},
"det":{
"p":0.9807692308,
"r":0.9622641509,
"f":0.9714285714
},
"csubj":{
"p":0.75,
"r":0.75,
"f":0.75
},
"dep":{
"p":0.2,
"r":0.1428571429,
"f":0.1666666667
}
},
"tag_acc":0.9713305562,
"lemma_acc":0.9670526831,
"ents_p":0.7286295794,
"ents_r":0.6754716981,
"ents_f":0.7010443864,
"ents_per_type":{
"DATE":{
"p":0.9375,
"r":0.9633027523,
"f":0.9502262443
},
"PERSON":{
"p":0.6959459459,
"r":0.7410071942,
"f":0.7177700348
},
"ORG":{
"p":0.6454545455,
"r":0.5182481752,
"f":0.5748987854
},
"GPE":{
"p":0.6956521739,
"r":0.6808510638,
"f":0.688172043
},
"QUANTITY":{
"p":0.8529411765,
"r":0.8787878788,
"f":0.8656716418
},
"TIME":{
"p":0.5714285714,
"r":1.0,
"f":0.7272727273
},
"NORP":{
"p":0.6896551724,
"r":0.625,
"f":0.6557377049
},
"ORDINAL":{
"p":0.6666666667,
"r":0.6363636364,
"f":0.6511627907
},
"TITLE_AFFIX":{
"p":0.8260869565,
"r":0.6333333333,
"f":0.7169811321
},
"PRODUCT":{
"p":0.4642857143,
"r":0.3095238095,
"f":0.3714285714
},
"WORK_OF_ART":{
"p":0.6470588235,
"r":0.6470588235,
"f":0.6470588235
},
"CARDINAL":{
"p":1.0,
"r":0.5,
"f":0.6666666667
},
"PERCENT":{
"p":1.0,
"r":0.2857142857,
"f":0.4444444444
},
"EVENT":{
"p":0.7777777778,
"r":0.5384615385,
"f":0.6363636364
},
"LOC":{
"p":0.5,
"r":0.7,
"f":0.5833333333
},
"FAC":{
"p":0.5483870968,
"r":0.4594594595,
"f":0.5
},
"MOVEMENT":{
"p":0.0,
"r":0.0,
"f":0.0
},
"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":8525.2225414726
},
"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"
]
}