{ "lang":"ja", "name":"core_news_md", "version":"3.2.0", "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":">=3.2.0,<3.3.0", "spacy_git_version":"bb26550e2", "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=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" ], "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", "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":0.971323379, "morph_acc":0.0040005162, "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":0.9862475442, "sents_r":0.9901380671, "sents_f":0.9881889764, "dep_uas":0.9224188392, "dep_las":0.9075365579, "dep_las_per_type":{ "cc":{ "p":0.7708333333, "r":0.7708333333, "f":0.7708333333 }, "compound":{ "p":0.9421390999, "r":0.908680947, "f":0.925107604 }, "obl":{ "p":0.8222778473, "r":0.8202247191, "f":0.82125 }, "case":{ "p":0.9907763259, "r":0.9794832827, "f":0.9850974398 }, "dislocated":{ "p":0.5833333333, "r":0.5384615385, "f":0.56 }, "nsubj":{ "p":0.8061420345, "r":0.8061420345, "f":0.8061420345 }, "nmod":{ "p":0.88639201, "r":0.8304093567, "f":0.8574879227 }, "root":{ "p":0.9741035857, "r":0.9644970414, "f":0.9692765114 }, "aux":{ "p":0.977818854, "r":0.982358403, "f":0.9800833719 }, "advcl":{ "p":0.6726057906, "r":0.6786516854, "f":0.6756152125 }, "mark":{ "p":0.9599198397, "r":0.958, "f":0.958958959 }, "fixed":{ "p":0.9533213645, "r":0.9654545455, "f":0.9593495935 }, "acl":{ "p":0.8561946903, "r":0.8505494505, "f":0.8533627343 }, "obj":{ "p":0.9695121951, "r":0.9607250755, "f":0.9650986343 }, "nummod":{ "p":0.9868421053, "r":0.8875739645, "f":0.9345794393 }, "advmod":{ "p":0.6323529412, "r":0.6142857143, "f":0.6231884058 }, "amod":{ "p":0.9, "r":0.7297297297, "f":0.8059701493 }, "cop":{ "p":0.9585798817, "r":0.9418604651, "f":0.9501466276 }, "ccomp":{ "p":1.0, "r":0.7272727273, "f":0.8421052632 }, "det":{ "p":0.9615384615, "r":0.9433962264, "f":0.9523809524 }, "csubj":{ "p":0.6923076923, "r":0.75, "f":0.72 }, "dep":{ "p":0.0, "r":0.0, "f":0.0 } }, "tag_acc":0.9715755942, "lemma_acc":0.9659109444, "ents_p":0.737704918, "ents_r":0.679245283, "ents_f":0.7072691552, "ents_per_type":{ "DATE":{ "p":0.9722222222, "r":0.9633027523, "f":0.9677419355 }, "ORG":{ "p":0.6218487395, "r":0.5401459854, "f":0.578125 }, "TITLE_AFFIX":{ "p":0.7727272727, "r":0.5666666667, "f":0.6538461538 }, "PERSON":{ "p":0.7407407407, "r":0.7194244604, "f":0.7299270073 }, "GPE":{ "p":0.6774193548, "r":0.670212766, "f":0.6737967914 }, "PRODUCT":{ "p":0.5806451613, "r":0.4285714286, "f":0.4931506849 }, "TIME":{ "p":0.6666666667, "r":1.0, "f":0.8 }, "QUANTITY":{ "p":0.8382352941, "r":0.8636363636, "f":0.8507462687 }, "NORP":{ "p":0.7407407407, "r":0.625, "f":0.6779661017 }, "ORDINAL":{ "p":0.5357142857, "r":0.6818181818, "f":0.6 }, "WORK_OF_ART":{ "p":0.8, "r":0.7058823529, "f":0.75 }, "FAC":{ "p":0.619047619, "r":0.3513513514, "f":0.4482758621 }, "PERCENT":{ "p":1.0, "r":0.2857142857, "f":0.4444444444 }, "CARDINAL":{ "p":0.0, "r":0.0, "f":0.0 }, "EVENT":{ "p":0.75, "r":0.6923076923, "f":0.72 }, "LOC":{ "p":0.5333333333, "r":0.8, "f":0.64 }, "MOVEMENT":{ "p":0.0, "r":0.0, "f":0.0 }, "LAW":{ "p":1.0, "r":0.3333333333, "f":0.5 }, "MONEY":{ "p":0.875, "r":1.0, "f":0.9333333333 }, "LANGUAGE":{ "p":0.8571428571, "r":1.0, "f":0.9230769231 } }, "speed":4621.4641630782 }, "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>=0.4.9", "sudachidict-core>=20200330" ] }