{ "lang":"ja", "name":"core_news_md", "version":"3.4.0", "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":">=3.4.0,<3.5.0", "spacy_git_version":"dd038b536", "vectors":{ "width":300, "vectors":20000, "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":0.9968649485, "token_p":0.9764591282, "token_r":0.9790021974, "token_f":0.9777290092, "pos_acc":0.9733311518, "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":0.9901380671, "sents_r":0.9901380671, "sents_f":0.9901380671, "dep_uas":0.9198487032, "dep_las":0.9061782838, "dep_las_per_type":{ "cc":{ "p":0.7115384615, "r":0.7708333333, "f":0.74 }, "compound":{ "p":0.9336051252, "r":0.9036076663, "f":0.918361501 }, "obl":{ "p":0.8171500631, "r":0.808988764, "f":0.8130489335 }, "case":{ "p":0.9892720307, "r":0.9810030395, "f":0.9851201831 }, "dislocated":{ "p":0.6428571429, "r":0.6923076923, "f":0.6666666667 }, "nsubj":{ "p":0.8233009709, "r":0.8138195777, "f":0.8185328185 }, "nmod":{ "p":0.8746898263, "r":0.8245614035, "f":0.8488862131 }, "root":{ "p":0.9679358717, "r":0.9526627219, "f":0.9602385686 }, "aux":{ "p":0.9787037037, "r":0.9814298979, "f":0.980064905 }, "advcl":{ "p":0.6944444444, "r":0.6741573034, "f":0.6841505131 }, "mark":{ "p":0.9775967413, "r":0.96, "f":0.9687184662 }, "fixed":{ "p":0.9588550984, "r":0.9745454545, "f":0.9666366096 }, "acl":{ "p":0.8315334773, "r":0.8461538462, "f":0.8387799564 }, "obj":{ "p":0.9480122324, "r":0.9365558912, "f":0.9422492401 }, "nummod":{ "p":0.9805194805, "r":0.8934911243, "f":0.9349845201 }, "advmod":{ "p":0.6917293233, "r":0.6571428571, "f":0.673992674 }, "amod":{ "p":0.9642857143, "r":0.7297297297, "f":0.8307692308 }, "cop":{ "p":0.9523809524, "r":0.9302325581, "f":0.9411764706 }, "ccomp":{ "p":0.95, "r":0.8636363636, "f":0.9047619048 }, "det":{ "p":0.9615384615, "r":0.9433962264, "f":0.9523809524 }, "csubj":{ "p":0.7142857143, "r":0.8333333333, "f":0.7692307692 }, "dep":{ "p":0.2, "r":0.1428571429, "f":0.1666666667 } }, "tag_acc":0.9712488769, "lemma_acc":0.9670526831, "ents_p":0.7244623656, "ents_r":0.6779874214, "ents_f":0.7004548408, "ents_per_type":{ "DATE":{ "p":0.9545454545, "r":0.9633027523, "f":0.9589041096 }, "PERSON":{ "p":0.7152777778, "r":0.7410071942, "f":0.7279151943 }, "ORG":{ "p":0.6333333333, "r":0.5547445255, "f":0.5914396887 }, "TITLE_AFFIX":{ "p":0.8333333333, "r":0.6666666667, "f":0.7407407407 }, "GPE":{ "p":0.6741573034, "r":0.6382978723, "f":0.6557377049 }, "PRODUCT":{ "p":0.3636363636, "r":0.2857142857, "f":0.32 }, "TIME":{ "p":0.6666666667, "r":1.0, "f":0.8 }, "QUANTITY":{ "p":0.8194444444, "r":0.8939393939, "f":0.8550724638 }, "NORP":{ "p":0.72, "r":0.5625, "f":0.6315789474 }, "ORDINAL":{ "p":0.5833333333, "r":0.6363636364, "f":0.6086956522 }, "WORK_OF_ART":{ "p":0.6842105263, "r":0.7647058824, "f":0.7222222222 }, "FAC":{ "p":0.6538461538, "r":0.4594594595, "f":0.5396825397 }, "PERCENT":{ "p":1.0, "r":0.2857142857, "f":0.4444444444 }, "EVENT":{ "p":0.7368421053, "r":0.5384615385, "f":0.6222222222 }, "CARDINAL":{ "p":0.0, "r":0.0, "f":0.0 }, "LOC":{ "p":0.6153846154, "r":0.8, "f":0.6956521739 }, "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":7222.6711221355 }, "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" ] }