{ "lang":"ja", "name":"core_news_lg", "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":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" ], "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":0.9736163946, "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":0.9862204724, "sents_r":0.9881656805, "sents_f":0.9871921182, "dep_uas":0.9214150689, "dep_las":0.9080930316, "dep_las_per_type":{ "cc":{ "p":0.75, "r":0.75, "f":0.75 }, "compound":{ "p":0.9486581097, "r":0.916572717, "f":0.9323394495 }, "obl":{ "p":0.8233082707, "r":0.8202247191, "f":0.8217636023 }, "case":{ "p":0.9892679187, "r":0.9806231003, "f":0.9849265407 }, "dislocated":{ "p":0.5, "r":0.4615384615, "f":0.48 }, "nsubj":{ "p":0.8281853282, "r":0.8234165067, "f":0.8257940327 }, "nmod":{ "p":0.87875, "r":0.8222222222, "f":0.8495468278 }, "root":{ "p":0.9560878244, "r":0.9447731755, "f":0.9503968254 }, "aux":{ "p":0.9751381215, "r":0.9832869081, "f":0.9791955617 }, "advcl":{ "p":0.6810933941, "r":0.6719101124, "f":0.6764705882 }, "mark":{ "p":0.971659919, "r":0.96, "f":0.9657947686 }, "fixed":{ "p":0.9571428571, "r":0.9745454545, "f":0.9657657658 }, "acl":{ "p":0.8492239468, "r":0.8417582418, "f":0.8454746137 }, "obj":{ "p":0.9662576687, "r":0.9516616314, "f":0.9589041096 }, "nummod":{ "p":0.9806451613, "r":0.899408284, "f":0.9382716049 }, "advmod":{ "p":0.6691729323, "r":0.6357142857, "f":0.652014652 }, "amod":{ "p":0.9310344828, "r":0.7297297297, "f":0.8181818182 }, "cop":{ "p":0.9634146341, "r":0.9186046512, "f":0.9404761905 }, "ccomp":{ "p":0.8571428571, "r":0.8181818182, "f":0.8372093023 }, "csubj":{ "p":0.4444444444, "r":0.6666666667, "f":0.5333333333 }, "det":{ "p":0.9807692308, "r":0.9622641509, "f":0.9714285714 }, "dep":{ "p":0.0769230769, "r":0.1428571429, "f":0.1 } }, "tag_acc":0.9715755942, "lemma_acc":0.9659109444, "ents_p":0.7402422611, "ents_r":0.6918238994, "ents_f":0.7152145644, "ents_per_type":{ "DATE":{ "p":0.9553571429, "r":0.9816513761, "f":0.9683257919 }, "ORG":{ "p":0.5916666667, "r":0.5182481752, "f":0.5525291829 }, "PERSON":{ "p":0.7816901408, "r":0.7985611511, "f":0.7900355872 }, "GPE":{ "p":0.6774193548, "r":0.670212766, "f":0.6737967914 }, "QUANTITY":{ "p":0.8194444444, "r":0.8939393939, "f":0.8550724638 }, "TIME":{ "p":0.6666666667, "r":1.0, "f":0.8 }, "NORP":{ "p":0.7407407407, "r":0.625, "f":0.6779661017 }, "ORDINAL":{ "p":0.56, "r":0.6363636364, "f":0.5957446809 }, "TITLE_AFFIX":{ "p":0.7916666667, "r":0.6333333333, "f":0.7037037037 }, "WORK_OF_ART":{ "p":0.75, "r":0.7058823529, "f":0.7272727273 }, "EVENT":{ "p":0.8823529412, "r":0.5769230769, "f":0.6976744186 }, "PERCENT":{ "p":1.0, "r":0.2857142857, "f":0.4444444444 }, "CARDINAL":{ "p":0.0, "r":0.0, "f":0.0 }, "FAC":{ "p":0.5666666667, "r":0.4594594595, "f":0.5074626866 }, "LOC":{ "p":0.5, "r":0.8, "f":0.6153846154 }, "MOVEMENT":{ "p":0.0, "r":0.0, "f":0.0 }, "PRODUCT":{ "p":0.5384615385, "r":0.3333333333, "f":0.4117647059 }, "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 } }, "speed":4912.7299798978 }, "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" ] }