ja_core_news_lg / meta.json
osanseviero's picture
osanseviero HF staff
Update spaCy pipeline
822433e
raw history blame
No virus
6.98 kB
{
"lang":"ja",
"name":"core_news_lg",
"version":"3.1.0",
"description":"Japanese pipeline optimized for CPU. Components: tok2vec, parser, senter, ner, attribute_ruler.",
"author":"Explosion",
"email":"contact@explosion.ai",
"url":"https://explosion.ai",
"license":"CC BY-SA 4.0",
"spacy_version":">=3.1.0,<3.2.0",
"spacy_git_version":"caba63b74",
"vectors":{
"width":300,
"vectors":480443,
"keys":480443,
"name":"ja_vectors"
},
"labels":{
"tok2vec":[
],
"parser":[
"ROOT",
"acl",
"advcl",
"advmod",
"amod",
"aux",
"case",
"cc",
"ccomp",
"compound",
"cop",
"csubj",
"dep",
"det",
"dislocated",
"fixed",
"mark",
"nmod",
"nsubj",
"nummod",
"obj",
"obl",
"punct"
],
"senter":[
"I",
"S"
],
"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",
"parser",
"attribute_ruler",
"ner"
],
"components":[
"tok2vec",
"parser",
"senter",
"attribute_ruler",
"ner"
],
"disabled":[
"senter"
],
"performance":{
"token_acc":0.9968965945,
"tag_acc":0.9721899386,
"pos_acc":0.9639755682,
"morph_acc":0.0,
"dep_uas":0.9181002928,
"dep_las":0.8998080263,
"ents_p":0.760989011,
"ents_r":0.7075351213,
"ents_f":0.7332892124,
"sents_p":0.9860557769,
"sents_r":0.9880239521,
"sents_f":0.9870388833,
"speed":11674.7452722222,
"morph_per_feat":{
"Polarity":{
"p":0.0,
"r":0.0,
"f":0.0
}
},
"dep_las_per_type":{
"cc":{
"p":0.7872340426,
"r":0.8043478261,
"f":0.7956989247
},
"nummod":{
"p":0.9770114943,
"r":0.8762886598,
"f":0.9239130435
},
"compound":{
"p":0.9397972117,
"r":0.9205462446,
"f":0.9300721229
},
"obl":{
"p":0.7827102804,
"r":0.8052884615,
"f":0.7938388626
},
"case":{
"p":0.986533282,
"r":0.9789996182,
"f":0.9827520123
},
"dislocated":{
"p":0.5,
"r":0.2105263158,
"f":0.2962962963
},
"nmod":{
"p":0.8676092545,
"r":0.813253012,
"f":0.8395522388
},
"nsubj":{
"p":0.7950819672,
"r":0.8083333333,
"f":0.8016528926
},
"root":{
"p":0.9717171717,
"r":0.9600798403,
"f":0.9658634538
},
"aux":{
"p":0.9625090123,
"r":0.9673913043,
"f":0.9649439827
},
"advcl":{
"p":0.6802884615,
"r":0.6596736597,
"f":0.6698224852
},
"mark":{
"p":0.956,
"r":0.9409448819,
"f":0.9484126984
},
"acl":{
"p":0.7887931034,
"r":0.8061674009,
"f":0.7973856209
},
"obj":{
"p":0.950617284,
"r":0.9390243902,
"f":0.9447852761
},
"fixed":{
"p":0.9421052632,
"r":0.9835164835,
"f":0.9623655914
},
"advmod":{
"p":0.7045454545,
"r":0.4920634921,
"f":0.5794392523
},
"amod":{
"p":0.8888888889,
"r":0.6,
"f":0.7164179104
},
"cop":{
"p":0.9664804469,
"r":0.9505494505,
"f":0.9584487535
},
"ccomp":{
"p":0.9,
"r":0.8181818182,
"f":0.8571428571
},
"det":{
"p":0.9803921569,
"r":0.9803921569,
"f":0.9803921569
},
"dep":{
"p":0.0,
"r":0.0,
"f":0.0
},
"csubj":{
"p":0.8333333333,
"r":0.7692307692,
"f":0.8
}
},
"ents_per_type":{
"DATE":{
"p":0.9626168224,
"r":0.9537037037,
"f":0.9581395349
},
"ORG":{
"p":0.6637931034,
"r":0.5877862595,
"f":0.6234817814
},
"PERSON":{
"p":0.780141844,
"r":0.7913669065,
"f":0.7857142857
},
"GPE":{
"p":0.6956521739,
"r":0.6808510638,
"f":0.688172043
},
"EVENT":{
"p":0.6666666667,
"r":0.6153846154,
"f":0.64
},
"PRODUCT":{
"p":0.5666666667,
"r":0.4146341463,
"f":0.4788732394
},
"TIME":{
"p":0.6666666667,
"r":1.0,
"f":0.8
},
"QUANTITY":{
"p":0.8970588235,
"r":0.9242424242,
"f":0.9104477612
},
"NORP":{
"p":0.7037037037,
"r":0.59375,
"f":0.6440677966
},
"TITLE_AFFIX":{
"p":0.8571428571,
"r":0.6,
"f":0.7058823529
},
"ORDINAL":{
"p":0.65,
"r":0.6842105263,
"f":0.6666666667
},
"WORK_OF_ART":{
"p":0.6875,
"r":0.6470588235,
"f":0.6666666667
},
"FAC":{
"p":0.5769230769,
"r":0.4054054054,
"f":0.4761904762
},
"PERCENT":{
"p":1.0,
"r":0.4285714286,
"f":0.6
},
"LOC":{
"p":0.6,
"r":0.9,
"f":0.72
},
"MOVEMENT":{
"p":0.3333333333,
"r":0.2,
"f":0.25
},
"LAW":{
"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
},
"CARDINAL":{
"p":0.0,
"r":0.0,
"f":0.0
}
}
},
"sources":[
{
"name":"UD Japanese GSD v2.6",
"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 v2.6 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>=0.4.9",
"sudachidict-core>=20200330"
]
}