ja_core_news_lg / meta.json
adrianeboyd's picture
Update spaCy pipeline
7069fb2
raw
history blame
No virus
7.94 kB
{
"lang":"ja",
"name":"core_news_lg",
"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":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":0.9937494927,
"token_p":0.9764591282,
"token_r":0.9790021974,
"token_f":0.9777290092,
"pos_acc":0.9749672775,
"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":0.9233540485,
"dep_las":0.9101052821,
"dep_las_per_type":{
"cc":{
"p":0.7826086957,
"r":0.75,
"f":0.7659574468
},
"compound":{
"p":0.9399066511,
"r":0.9081172492,
"f":0.9237385321
},
"obl":{
"p":0.8310038119,
"r":0.8164794007,
"f":0.8236775819
},
"case":{
"p":0.9907940161,
"r":0.9813829787,
"f":0.9860660431
},
"dislocated":{
"p":0.5454545455,
"r":0.4615384615,
"f":0.5
},
"nsubj":{
"p":0.8359073359,
"r":0.8310940499,
"f":0.833493744
},
"nmod":{
"p":0.8835192069,
"r":0.8339181287,
"f":0.8580024067
},
"root":{
"p":0.9569471624,
"r":0.9644970414,
"f":0.9607072692
},
"aux":{
"p":0.9796672828,
"r":0.9842154132,
"f":0.9819360815
},
"advcl":{
"p":0.6888888889,
"r":0.6966292135,
"f":0.6927374302
},
"mark":{
"p":0.9777777778,
"r":0.968,
"f":0.9728643216
},
"fixed":{
"p":0.9621621622,
"r":0.9709090909,
"f":0.9665158371
},
"acl":{
"p":0.8422222222,
"r":0.832967033,
"f":0.8375690608
},
"obj":{
"p":0.9476923077,
"r":0.9305135952,
"f":0.9390243902
},
"nummod":{
"p":0.9805194805,
"r":0.8934911243,
"f":0.9349845201
},
"advmod":{
"p":0.6739130435,
"r":0.6642857143,
"f":0.6690647482
},
"amod":{
"p":0.8709677419,
"r":0.7297297297,
"f":0.7941176471
},
"cop":{
"p":0.9640718563,
"r":0.9360465116,
"f":0.9498525074
},
"ccomp":{
"p":1.0,
"r":0.9545454545,
"f":0.976744186
},
"det":{
"p":1.0,
"r":0.9811320755,
"f":0.9904761905
},
"csubj":{
"p":0.6153846154,
"r":0.6666666667,
"f":0.64
},
"dep":{
"p":0.25,
"r":0.1428571429,
"f":0.1818181818
}
},
"tag_acc":0.9712488769,
"lemma_acc":0.9670526831,
"ents_p":0.754691689,
"ents_r":0.7081761006,
"ents_f":0.7306943543,
"ents_per_type":{
"DATE":{
"p":0.9363636364,
"r":0.9449541284,
"f":0.9406392694
},
"ORG":{
"p":0.6456692913,
"r":0.598540146,
"f":0.6212121212
},
"PERSON":{
"p":0.7666666667,
"r":0.8273381295,
"f":0.7958477509
},
"GPE":{
"p":0.7386363636,
"r":0.6914893617,
"f":0.7142857143
},
"TIME":{
"p":0.5,
"r":1.0,
"f":0.6666666667
},
"QUANTITY":{
"p":0.8923076923,
"r":0.8787878788,
"f":0.8854961832
},
"NORP":{
"p":0.7037037037,
"r":0.59375,
"f":0.6440677966
},
"TITLE_AFFIX":{
"p":0.8,
"r":0.6666666667,
"f":0.7272727273
},
"ORDINAL":{
"p":0.5652173913,
"r":0.5909090909,
"f":0.5777777778
},
"WORK_OF_ART":{
"p":0.75,
"r":0.7058823529,
"f":0.7272727273
},
"CARDINAL":{
"p":0.5,
"r":0.5,
"f":0.5
},
"FAC":{
"p":0.6666666667,
"r":0.4324324324,
"f":0.5245901639
},
"EVENT":{
"p":0.6956521739,
"r":0.6153846154,
"f":0.6530612245
},
"PERCENT":{
"p":1.0,
"r":0.2857142857,
"f":0.4444444444
},
"LOC":{
"p":0.75,
"r":0.9,
"f":0.8181818182
},
"PRODUCT":{
"p":0.5384615385,
"r":0.3333333333,
"f":0.4117647059
},
"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
},
"PET_NAME":{
"p":0.0,
"r":0.0,
"f":0.0
}
},
"speed":9928.6122863321
},
"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"
]
}