{ "lang":"ja", "name":"core_news_trf", "version":"3.7.2", "description":"Japanese transformer pipeline (Transformer(name='cl-tohoku/bert-base-japanese-char-v2', piece_encoder='char', stride=160, type='bert', width=768, window=216, vocab_size=6144)). Components: transformer, morphologizer, parser, ner.", "author":"Explosion", "email":"contact@explosion.ai", "url":"https://explosion.ai", "license":"CC BY-SA 3.0", "spacy_version":">=3.7.0,<3.8.0", "spacy_git_version":"6b4f77441", "vectors":{ "width":0, "vectors":0, "keys":0, "name":null }, "labels":{ "transformer":[ ], "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":[ "transformer", "morphologizer", "parser", "attribute_ruler", "ner" ], "components":[ "transformer", "morphologizer", "parser", "attribute_ruler", "ner" ], "disabled":[ ], "performance":{ "token_acc":0.9936678032, "token_p":0.9763760351, "token_r":0.9788394238, "token_f":0.9776061776, "pos_acc":0.979409718, "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":0.9318181818, "sents_r":0.9704142012, "sents_f":0.9507246377, "dep_uas":0.9304880245, "dep_las":0.9178365731, "dep_las_per_type":{ "cc":{ "p":0.8723404255, "r":0.8541666667, "f":0.8631578947 }, "compound":{ "p":0.9507125891, "r":0.9024802706, "f":0.9259687681 }, "obl":{ "p":0.8445273632, "r":0.847690387, "f":0.846105919 }, "case":{ "p":0.9813048455, "r":0.9772036474, "f":0.9792499524 }, "dislocated":{ "p":0.5454545455, "r":0.4615384615, "f":0.5 }, "nsubj":{ "p":0.8700787402, "r":0.8483685221, "f":0.8590864917 }, "nmod":{ "p":0.8964241677, "r":0.8502923977, "f":0.8727490996 }, "root":{ "p":0.9300567108, "r":0.9704142012, "f":0.9498069498 }, "aux":{ "p":0.9747663551, "r":0.9684308264, "f":0.9715882627 }, "advcl":{ "p":0.7568807339, "r":0.7415730337, "f":0.7491486947 }, "mark":{ "p":0.9757575758, "r":0.966, "f":0.9708542714 }, "fixed":{ "p":0.9661921708, "r":0.9872727273, "f":0.976618705 }, "acl":{ "p":0.8711790393, "r":0.8769230769, "f":0.874041621 }, "obj":{ "p":0.9630769231, "r":0.9456193353, "f":0.9542682927 }, "nummod":{ "p":0.987012987, "r":0.899408284, "f":0.9411764706 }, "advmod":{ "p":0.7352941176, "r":0.7142857143, "f":0.7246376812 }, "amod":{ "p":0.9090909091, "r":0.8108108108, "f":0.8571428571 }, "cop":{ "p":0.9647058824, "r":0.9534883721, "f":0.9590643275 }, "ccomp":{ "p":0.9, "r":0.8181818182, "f":0.8571428571 }, "det":{ "p":1.0, "r":0.9622641509, "f":0.9807692308 }, "csubj":{ "p":0.7857142857, "r":0.9166666667, "f":0.8461538462 }, "dep":{ "p":0.2857142857, "r":0.2857142857, "f":0.2857142857 } }, "tag_acc":0.9713282143, "lemma_acc":0.9670499959, "ents_p":0.8227383863, "ents_r":0.8465408805, "ents_f":0.8344699318, "ents_per_type":{ "DATE":{ "p":0.9464285714, "r":0.9724770642, "f":0.9592760181 }, "ORG":{ "p":0.6918238994, "r":0.802919708, "f":0.7432432432 }, "TITLE_AFFIX":{ "p":0.8181818182, "r":0.9, "f":0.8571428571 }, "PERSON":{ "p":0.9270072993, "r":0.9136690647, "f":0.9202898551 }, "GPE":{ "p":0.84375, "r":0.8617021277, "f":0.8526315789 }, "PRODUCT":{ "p":0.5869565217, "r":0.6428571429, "f":0.6136363636 }, "TIME":{ "p":0.8, "r":1.0, "f":0.8888888889 }, "QUANTITY":{ "p":0.8630136986, "r":0.9545454545, "f":0.9064748201 }, "NORP":{ "p":0.6666666667, "r":0.625, "f":0.6451612903 }, "ORDINAL":{ "p":0.6538461538, "r":0.7727272727, "f":0.7083333333 }, "WORK_OF_ART":{ "p":0.8461538462, "r":0.6470588235, "f":0.7333333333 }, "CARDINAL":{ "p":1.0, "r":0.5, "f":0.6666666667 }, "PERCENT":{ "p":1.0, "r":0.8571428571, "f":0.9230769231 }, "EVENT":{ "p":0.9583333333, "r":0.8846153846, "f":0.92 }, "FAC":{ "p":0.9285714286, "r":0.7027027027, "f":0.8 }, "LOC":{ "p":0.8, "r":0.8, "f":0.8 }, "MOVEMENT":{ "p":0.3333333333, "r":0.2, "f":0.25 }, "LAW":{ "p":0.6666666667, "r":0.6666666667, "f":0.6666666667 }, "MONEY":{ "p":1.0, "r":1.0, "f":1.0 }, "LANGUAGE":{ "p":1.0, "r":1.0, "f":1.0 } }, "speed":567.0833083438 }, "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":"cl-tohoku/bert-base-japanese-char-v2", "author":"Inui Laboratory, Tohoku University", "url":"https://huggingface.co/cl-tohoku/bert-base-japanese-char-v2", "license":"CC BY-SA 3.0" } ], "requirements":[ "spacy-curated-transformers>=0.2.0,<0.3.0", "sudachipy>=0.5.2,!=0.6.1", "sudachidict-core>=20211220" ] }