ja_core_news_sm / meta.json
osanseviero's picture
Update spaCy pipeline
ce93cd3
raw
history blame
6.79 kB
{
"lang":"ja",
"name":"core_news_sm",
"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":0,
"vectors":0,
"keys":0,
"name":null
},
"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":0.916212877,
"dep_las":0.894130554,
"ents_p":0.7163232964,
"ents_r":0.5772669221,
"ents_f":0.639321075,
"sents_p":0.9860557769,
"sents_r":0.9880239521,
"sents_f":0.9870388833,
"speed":14745.6510174231,
"morph_per_feat":{
"Polarity":{
"p":0.0,
"r":0.0,
"f":0.0
}
},
"dep_las_per_type":{
"cc":{
"p":0.7659574468,
"r":0.7826086957,
"f":0.7741935484
},
"nummod":{
"p":0.9730769231,
"r":0.8694158076,
"f":0.9183303085
},
"compound":{
"p":0.9299242424,
"r":0.9143389199,
"f":0.9220657277
},
"obl":{
"p":0.7782857143,
"r":0.8185096154,
"f":0.7978910369
},
"case":{
"p":0.9808429119,
"r":0.9774723177,
"f":0.9791547141
},
"dislocated":{
"p":0.4285714286,
"r":0.3157894737,
"f":0.3636363636
},
"nmod":{
"p":0.8792650919,
"r":0.8072289157,
"f":0.8417085427
},
"nsubj":{
"p":0.8020833333,
"r":0.8020833333,
"f":0.8020833333
},
"root":{
"p":0.967611336,
"r":0.9540918164,
"f":0.9608040201
},
"aux":{
"p":0.9545454545,
"r":0.9586956522,
"f":0.9566160521
},
"advcl":{
"p":0.6402877698,
"r":0.6223776224,
"f":0.6312056738
},
"mark":{
"p":0.953815261,
"r":0.9350393701,
"f":0.944333996
},
"acl":{
"p":0.8161434978,
"r":0.8017621145,
"f":0.8088888889
},
"obj":{
"p":0.9254658385,
"r":0.9085365854,
"f":0.9169230769
},
"fixed":{
"p":0.9572192513,
"r":0.9835164835,
"f":0.9701897019
},
"advmod":{
"p":0.724137931,
"r":0.5,
"f":0.5915492958
},
"amod":{
"p":0.7941176471,
"r":0.675,
"f":0.7297297297
},
"cop":{
"p":0.9482758621,
"r":0.9065934066,
"f":0.9269662921
},
"ccomp":{
"p":0.9473684211,
"r":0.8181818182,
"f":0.8780487805
},
"det":{
"p":0.9607843137,
"r":0.9607843137,
"f":0.9607843137
},
"csubj":{
"p":0.8333333333,
"r":0.7692307692,
"f":0.8
},
"dep":{
"p":0.0,
"r":0.0,
"f":0.0
}
},
"ents_per_type":{
"DATE":{
"p":0.9272727273,
"r":0.9444444444,
"f":0.9357798165
},
"PERSON":{
"p":0.6464646465,
"r":0.4604316547,
"f":0.5378151261
},
"GPE":{
"p":0.6455696203,
"r":0.5425531915,
"f":0.5895953757
},
"PRODUCT":{
"p":0.55,
"r":0.2682926829,
"f":0.3606557377
},
"TIME":{
"p":0.6666666667,
"r":1.0,
"f":0.8
},
"QUANTITY":{
"p":0.9090909091,
"r":0.9090909091,
"f":0.9090909091
},
"NORP":{
"p":0.7826086957,
"r":0.5625,
"f":0.6545454545
},
"ORDINAL":{
"p":0.5909090909,
"r":0.6842105263,
"f":0.6341463415
},
"TITLE_AFFIX":{
"p":0.7647058824,
"r":0.4333333333,
"f":0.5531914894
},
"ORG":{
"p":0.504950495,
"r":0.3893129771,
"f":0.4396551724
},
"WORK_OF_ART":{
"p":0.7222222222,
"r":0.7647058824,
"f":0.7428571429
},
"PERCENT":{
"p":1.0,
"r":0.4285714286,
"f":0.6
},
"EVENT":{
"p":0.7619047619,
"r":0.6153846154,
"f":0.6808510638
},
"LOC":{
"p":0.6363636364,
"r":0.7,
"f":0.6666666667
},
"FAC":{
"p":0.6315789474,
"r":0.3243243243,
"f":0.4285714286
},
"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
},
"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"
}
],
"requirements":[
"sudachipy>=0.4.9",
"sudachidict-core>=20200330"
]
}