{ "lang":"ja", "name":"core_news_lg", "version":"3.3.0", "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":">=3.3.0.dev0,<3.4.0", "spacy_git_version":"849bef2de", "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=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":0.9968649485, "token_p":0.9764591282, "token_r":0.9790021974, "token_f":0.9777290092, "pos_acc":0.9745981102, "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":0.9823874755, "sents_r":0.9901380671, "sents_f":0.9862475442, "dep_uas":0.9222457341, "dep_las":0.9090090901, "dep_las_per_type":{ "cc":{ "p":0.7755102041, "r":0.7916666667, "f":0.7835051546 }, "compound":{ "p":0.9439906651, "r":0.9120631342, "f":0.9277522936 }, "obl":{ "p":0.8172715895, "r":0.8152309613, "f":0.81625 }, "case":{ "p":0.9900230238, "r":0.9802431611, "f":0.9851088202 }, "dislocated":{ "p":0.7, "r":0.5384615385, "f":0.6086956522 }, "nsubj":{ "p":0.8349514563, "r":0.8253358925, "f":0.8301158301 }, "nmod":{ "p":0.8793532338, "r":0.8269005848, "f":0.8523206751 }, "root":{ "p":0.958250497, "r":0.9506903353, "f":0.9544554455 }, "aux":{ "p":0.9851301115, "r":0.9842154132, "f":0.9846725499 }, "advcl":{ "p":0.693877551, "r":0.6876404494, "f":0.690744921 }, "mark":{ "p":0.9775510204, "r":0.958, "f":0.9676767677 }, "fixed":{ "p":0.9536541889, "r":0.9727272727, "f":0.9630963096 }, "acl":{ "p":0.8409586057, "r":0.8483516484, "f":0.8446389497 }, "obj":{ "p":0.9541284404, "r":0.9425981873, "f":0.9483282675 }, "nummod":{ "p":0.987012987, "r":0.899408284, "f":0.9411764706 }, "advmod":{ "p":0.6904761905, "r":0.6214285714, "f":0.6541353383 }, "amod":{ "p":0.962962963, "r":0.7027027027, "f":0.8125 }, "cop":{ "p":0.9534883721, "r":0.9534883721, "f":0.9534883721 }, "ccomp":{ "p":0.68, "r":0.7727272727, "f":0.7234042553 }, "det":{ "p":1.0, "r":0.9811320755, "f":0.9904761905 }, "csubj":{ "p":0.6923076923, "r":0.75, "f":0.72 }, "dep":{ "p":0.0, "r":0.0, "f":0.0 } }, "tag_acc":0.9712488769, "lemma_acc":0.965013864, "ents_p":0.7611940299, "ents_r":0.7056603774, "ents_f":0.7323759791, "ents_per_type":{ "DATE":{ "p":0.9541284404, "r":0.9541284404, "f":0.9541284404 }, "ORG":{ "p":0.6639344262, "r":0.5912408759, "f":0.6254826255 }, "PERSON":{ "p":0.7714285714, "r":0.7769784173, "f":0.7741935484 }, "GPE":{ "p":0.7272727273, "r":0.6808510638, "f":0.7032967033 }, "PRODUCT":{ "p":0.5, "r":0.4047619048, "f":0.4473684211 }, "TIME":{ "p":0.5714285714, "r":1.0, "f":0.7272727273 }, "QUANTITY":{ "p":0.884057971, "r":0.9242424242, "f":0.9037037037 }, "NORP":{ "p":0.8, "r":0.625, "f":0.701754386 }, "ORDINAL":{ "p":0.7, "r":0.6363636364, "f":0.6666666667 }, "TITLE_AFFIX":{ "p":0.7407407407, "r":0.6666666667, "f":0.701754386 }, "WORK_OF_ART":{ "p":0.8571428571, "r":0.7058823529, "f":0.7741935484 }, "PERCENT":{ "p":1.0, "r":0.2857142857, "f":0.4444444444 }, "EVENT":{ "p":0.75, "r":0.6923076923, "f":0.72 }, "CARDINAL":{ "p":0.0, "r":0.0, "f":0.0 }, "LOC":{ "p":0.5, "r":0.8, "f":0.6153846154 }, "FAC":{ "p":0.6666666667, "r":0.3783783784, "f":0.4827586207 }, "MOVEMENT":{ "p":0.0, "r":0.0, "f":0.0 }, "LAW":{ "p":1.0, "r":0.3333333333, "f":0.5 }, "PET_NAME":{ "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 } }, "speed":9177.2419617522 }, "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" ] }