ja_core_news_md / meta.json
adrianeboyd's picture
Update spaCy pipeline
0e768a3
{
"lang":"ja",
"name":"core_news_md",
"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":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":0.9936678032,
"token_p":0.9763760351,
"token_r":0.9788394238,
"token_f":0.9776061776,
"pos_acc":0.9712018326,
"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":0.9630350195,
"sents_r":0.9763313609,
"sents_f":0.9696376102,
"dep_uas":0.9221346544,
"dep_las":0.9092381767,
"dep_las_per_type":{
"cc":{
"p":0.8913043478,
"r":0.8541666667,
"f":0.8723404255
},
"compound":{
"p":0.938372093,
"r":0.9098083427,
"f":0.9238694906
},
"obl":{
"p":0.822418136,
"r":0.8152309613,
"f":0.8188087774
},
"case":{
"p":0.9896353167,
"r":0.9794832827,
"f":0.9845331297
},
"dislocated":{
"p":0.5833333333,
"r":0.5384615385,
"f":0.56
},
"nsubj":{
"p":0.8243243243,
"r":0.8195777351,
"f":0.8219441771
},
"nmod":{
"p":0.8804483188,
"r":0.8269005848,
"f":0.8528347407
},
"root":{
"p":0.9625246548,
"r":0.9625246548,
"f":0.9625246548
},
"aux":{
"p":0.9796484736,
"r":0.9832869081,
"f":0.9814643188
},
"advcl":{
"p":0.7050691244,
"r":0.6876404494,
"f":0.6962457338
},
"mark":{
"p":0.9738955823,
"r":0.97,
"f":0.9719438878
},
"fixed":{
"p":0.9589285714,
"r":0.9763636364,
"f":0.9675675676
},
"acl":{
"p":0.8373626374,
"r":0.8373626374,
"f":0.8373626374
},
"obj":{
"p":0.9452887538,
"r":0.9395770393,
"f":0.9424242424
},
"nummod":{
"p":0.987012987,
"r":0.899408284,
"f":0.9411764706
},
"advmod":{
"p":0.6917293233,
"r":0.6571428571,
"f":0.673992674
},
"amod":{
"p":0.875,
"r":0.7567567568,
"f":0.8115942029
},
"cop":{
"p":0.9695121951,
"r":0.9244186047,
"f":0.9464285714
},
"ccomp":{
"p":0.9473684211,
"r":0.8181818182,
"f":0.8780487805
},
"det":{
"p":0.9803921569,
"r":0.9433962264,
"f":0.9615384615
},
"csubj":{
"p":0.6153846154,
"r":0.6666666667,
"f":0.64
},
"dep":{
"p":0.4,
"r":0.2857142857,
"f":0.3333333333
}
},
"tag_acc":0.9713282143,
"lemma_acc":0.9670499959,
"ents_p":0.7266576455,
"ents_r":0.6754716981,
"ents_f":0.7001303781,
"ents_per_type":{
"DATE":{
"p":0.954954955,
"r":0.9724770642,
"f":0.9636363636
},
"ORG":{
"p":0.6315789474,
"r":0.5255474453,
"f":0.5737051793
},
"TITLE_AFFIX":{
"p":0.7391304348,
"r":0.5666666667,
"f":0.641509434
},
"PERSON":{
"p":0.7163120567,
"r":0.726618705,
"f":0.7214285714
},
"GPE":{
"p":0.6534653465,
"r":0.7021276596,
"f":0.6769230769
},
"PRODUCT":{
"p":0.5555555556,
"r":0.3571428571,
"f":0.4347826087
},
"TIME":{
"p":0.6666666667,
"r":1.0,
"f":0.8
},
"QUANTITY":{
"p":0.8529411765,
"r":0.8787878788,
"f":0.8656716418
},
"NORP":{
"p":0.7142857143,
"r":0.625,
"f":0.6666666667
},
"ORDINAL":{
"p":0.5909090909,
"r":0.5909090909,
"f":0.5909090909
},
"WORK_OF_ART":{
"p":0.6111111111,
"r":0.6470588235,
"f":0.6285714286
},
"CARDINAL":{
"p":0.0,
"r":0.0,
"f":0.0
},
"PERCENT":{
"p":1.0,
"r":0.2857142857,
"f":0.4444444444
},
"EVENT":{
"p":0.6666666667,
"r":0.6153846154,
"f":0.64
},
"LOC":{
"p":0.5384615385,
"r":0.7,
"f":0.6086956522
},
"FAC":{
"p":0.652173913,
"r":0.4054054054,
"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":0.8571428571,
"r":1.0,
"f":0.9230769231
}
},
"speed":7926.2334345884
},
"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"
]
}