ja_core_news_sm / meta.json
adrianeboyd's picture
Update spaCy pipeline
9409659
{
"lang":"ja",
"name":"core_news_sm",
"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":0,
"vectors":0,
"keys":0,
"name":null
},
"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":0.9612599714,
"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":0.9803921569,
"sents_r":0.9861932939,
"sents_f":0.9832841691,
"dep_uas":0.9195153808,
"dep_las":0.9047554776,
"dep_las_per_type":{
"cc":{
"p":0.7826086957,
"r":0.75,
"f":0.7659574468
},
"compound":{
"p":0.930875576,
"r":0.9109357384,
"f":0.9207977208
},
"obl":{
"p":0.7995049505,
"r":0.8064918851,
"f":0.8029832194
},
"case":{
"p":0.9881180529,
"r":0.9794832827,
"f":0.983781721
},
"dislocated":{
"p":0.6,
"r":0.4615384615,
"f":0.5217391304
},
"nsubj":{
"p":0.7972972973,
"r":0.792706334,
"f":0.7949951877
},
"nmod":{
"p":0.8895859473,
"r":0.8292397661,
"f":0.8583535109
},
"root":{
"p":0.9741550696,
"r":0.966469428,
"f":0.9702970297
},
"aux":{
"p":0.977818854,
"r":0.982358403,
"f":0.9800833719
},
"advcl":{
"p":0.6787330317,
"r":0.6741573034,
"f":0.6764374295
},
"mark":{
"p":0.9674796748,
"r":0.952,
"f":0.9596774194
},
"fixed":{
"p":0.9569120287,
"r":0.9690909091,
"f":0.962962963
},
"acl":{
"p":0.8515981735,
"r":0.8197802198,
"f":0.8353863382
},
"obj":{
"p":0.9509202454,
"r":0.9365558912,
"f":0.9436834094
},
"nummod":{
"p":0.974025974,
"r":0.8875739645,
"f":0.9287925697
},
"advmod":{
"p":0.7,
"r":0.65,
"f":0.6740740741
},
"amod":{
"p":0.8709677419,
"r":0.7297297297,
"f":0.7941176471
},
"cop":{
"p":0.9761904762,
"r":0.9534883721,
"f":0.9647058824
},
"ccomp":{
"p":0.9047619048,
"r":0.8636363636,
"f":0.8837209302
},
"det":{
"p":0.9803921569,
"r":0.9433962264,
"f":0.9615384615
},
"csubj":{
"p":0.6428571429,
"r":0.75,
"f":0.6923076923
},
"dep":{
"p":0.25,
"r":0.1428571429,
"f":0.1818181818
}
},
"tag_acc":0.9713282143,
"lemma_acc":0.9670499959,
"ents_p":0.7109375,
"ents_r":0.572327044,
"ents_f":0.6341463415,
"ents_per_type":{
"DATE":{
"p":0.962962963,
"r":0.9541284404,
"f":0.9585253456
},
"PERSON":{
"p":0.64,
"r":0.4604316547,
"f":0.5355648536
},
"ORG":{
"p":0.5555555556,
"r":0.4379562044,
"f":0.4897959184
},
"GPE":{
"p":0.6708860759,
"r":0.5638297872,
"f":0.612716763
},
"PRODUCT":{
"p":0.347826087,
"r":0.1904761905,
"f":0.2461538462
},
"TIME":{
"p":0.6666666667,
"r":1.0,
"f":0.8
},
"QUANTITY":{
"p":0.8732394366,
"r":0.9393939394,
"f":0.9051094891
},
"NORP":{
"p":0.75,
"r":0.5625,
"f":0.6428571429
},
"TITLE_AFFIX":{
"p":0.7368421053,
"r":0.4666666667,
"f":0.5714285714
},
"ORDINAL":{
"p":0.5384615385,
"r":0.6363636364,
"f":0.5833333333
},
"WORK_OF_ART":{
"p":0.75,
"r":0.5294117647,
"f":0.6206896552
},
"CARDINAL":{
"p":1.0,
"r":0.5,
"f":0.6666666667
},
"FAC":{
"p":0.6111111111,
"r":0.2972972973,
"f":0.4
},
"EVENT":{
"p":0.7142857143,
"r":0.3846153846,
"f":0.5
},
"PERCENT":{
"p":1.0,
"r":0.2857142857,
"f":0.4444444444
},
"LOC":{
"p":0.6363636364,
"r":0.7,
"f":0.6666666667
},
"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":0.6666666667,
"r":1.0,
"f":0.8
}
},
"speed":8098.5108221259
},
"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"
}
],
"requirements":[
"sudachipy>=0.5.2,!=0.6.1",
"sudachidict-core>=20211220"
]
}