{ "lang":"en", "name":"core_web_trf_esco_ner", "version":"3.7.3", "description":"English transformer pipeline based on en_core_web_trf plus an entity recognizer based on the ESCO taxonomy. (Transformer(name='roberta-base', piece_encoder='byte-bpe', stride=104, type='roberta', width=768, window=144, vocab_size=50265)). Components: transformer, tagger, parser, ner, attribute_ruler, lemmatizer.", "author":"robipolli@gmail.com", "email":"robipolli@gmail.com", "url":"https://github.com/par-tec/esco-playground", "license":"MIT", "spacy_version":">=3.7.2,<3.8.0", "spacy_git_version":"a89eae928", "vectors":{ "width":0, "vectors":0, "keys":0, "name":null }, "labels":{ "transformer":[ ], "tagger":[ "$", "''", ",", "-LRB-", "-RRB-", ".", ":", "ADD", "AFX", "CC", "CD", "DT", "EX", "FW", "HYPH", "IN", "JJ", "JJR", "JJS", "LS", "MD", "NFP", "NN", "NNP", "NNPS", "NNS", "PDT", "POS", "PRP", "PRP$", "RB", "RBR", "RBS", "RP", "SYM", "TO", "UH", "VB", "VBD", "VBG", "VBN", "VBP", "VBZ", "WDT", "WP", "WP$", "WRB", "XX", "``" ], "parser":[ "ROOT", "acl", "acomp", "advcl", "advmod", "agent", "amod", "appos", "attr", "aux", "auxpass", "case", "cc", "ccomp", "compound", "conj", "csubj", "csubjpass", "dative", "dep", "det", "dobj", "expl", "intj", "mark", "meta", "neg", "nmod", "npadvmod", "nsubj", "nsubjpass", "nummod", "oprd", "parataxis", "pcomp", "pobj", "poss", "preconj", "predet", "prep", "prt", "punct", "quantmod", "relcl", "xcomp" ], "attribute_ruler":[ ], "lemmatizer":[ ], "ner":[ "CARDINAL", "DATE", "EVENT", "FAC", "GPE", "LANGUAGE", "LAW", "LOC", "MONEY", "NORP", "ORDINAL", "ORG", "PERCENT", "PERSON", "PRODUCT", "QUANTITY", "TIME", "WORK_OF_ART" ], "entity_ruler":[ "ESCO" ] }, "pipeline":[ "transformer", "tagger", "parser", "attribute_ruler", "lemmatizer", "ner", "entity_ruler" ], "components":[ "transformer", "tagger", "parser", "attribute_ruler", "lemmatizer", "ner", "entity_ruler" ], "disabled":[ ], "performance":{ "token_acc":0.9986194413, "token_p":0.9956819193, "token_r":0.9957659295, "token_f":0.9957239226, "tag_acc":0.9812819818, "sents_p":0.9489237505, "sents_r":0.8579061943, "sents_f":0.9011225055, "dep_uas":0.9526219812, "dep_las":0.9390746643, "dep_las_per_type":{ "prep":{ "p":0.9223201786, "r":0.9249098843, "f":0.9236132161 }, "det":{ "p":0.990090935, "r":0.9899698279, "f":0.9900303778 }, "pobj":{ "p":0.9835570206, "r":0.9842136265, "f":0.983885214 }, "nsubj":{ "p":0.9807776705, "r":0.979101862, "f":0.9799390498 }, "aux":{ "p":0.9887940235, "r":0.9897623075, "f":0.9892779285 }, "advmod":{ "p":0.9001865672, "r":0.8930674743, "f":0.8966128896 }, "relcl":{ "p":0.8803418803, "r":0.8969521045, "f":0.8885693746 }, "root":{ "p":0.9669463699, "r":0.8742001451, "f":0.9182372506 }, "xcomp":{ "p":0.9461705202, "r":0.94005743, "f":0.9431040691 }, "amod":{ "p":0.9438537344, "r":0.943181082, "f":0.9435172883 }, "compound":{ "p":0.9548618909, "r":0.9472042771, "f":0.9510176694 }, "poss":{ "p":0.9867389994, "r":0.98852657, "f":0.9876319759 }, "ccomp":{ "p":0.8474957794, "r":0.9201629328, "f":0.8823357094 }, "attr":{ "p":0.9543568465, "r":0.9671993272, "f":0.9607351713 }, "case":{ "p":0.9890547264, "r":0.994994995, "f":0.9920159681 }, "mark":{ "p":0.943876213, "r":0.9536301007, "f":0.9487280875 }, "intj":{ "p":0.6127684964, "r":0.7523809524, "f":0.6754357119 }, "advcl":{ "p":0.8114080164, "r":0.7952656762, "f":0.8032557548 }, "cc":{ "p":0.898903195, "r":0.9018060041, "f":0.9003522598 }, "neg":{ "p":0.9633901705, "r":0.9638735575, "f":0.9636318034 }, "conj":{ "p":0.8711377246, "r":0.9156596173, "f":0.8928439917 }, "nsubjpass":{ "p":0.9503797468, "r":0.9625641026, "f":0.956433121 }, "auxpass":{ "p":0.9619516562, "r":0.9790432802, "f":0.9704222172 }, "dobj":{ "p":0.9721071087, "r":0.9720296438, "f":0.9720683747 }, "nummod":{ "p":0.9453538152, "r":0.947979798, "f":0.9466649855 }, "npadvmod":{ "p":0.8455314454, "r":0.81669627, "f":0.8308637514 }, "prt":{ "p":0.8753180662, "r":0.9247311828, "f":0.8993464052 }, "pcomp":{ "p":0.9215277778, "r":0.9292717087, "f":0.9253835425 }, "expl":{ "p":0.9935897436, "r":0.9957173448, "f":0.9946524064 }, "acl":{ "p":0.8507135016, "r":0.8456082924, "f":0.8481532148 }, "agent":{ "p":0.9444444444, "r":0.9749103943, "f":0.9594356261 }, "dative":{ "p":0.8310185185, "r":0.8233944954, "f":0.8271889401 }, "acomp":{ "p":0.9469312413, "r":0.9306122449, "f":0.9387008234 }, "dep":{ "p":0.4040747029, "r":0.3863636364, "f":0.3950207469 }, "csubj":{ "p":0.8882352941, "r":0.8934911243, "f":0.8908554572 }, "quantmod":{ "p":0.8506711409, "r":0.8237205524, "f":0.8369789517 }, "nmod":{ "p":0.8208248817, "r":0.7397928093, "f":0.7782051282 }, "appos":{ "p":0.8061396131, "r":0.831670282, "f":0.8187059577 }, "predet":{ "p":0.8503937008, "r":0.9270386266, "f":0.887063655 }, "preconj":{ "p":0.6631578947, "r":0.7325581395, "f":0.6961325967 }, "oprd":{ "p":0.8792569659, "r":0.847761194, "f":0.8632218845 }, "csubjpass":{ "p":0.8333333333, "r":0.8333333333, "f":0.8333333333 }, "parataxis":{ "p":0.6084452975, "r":0.6876355748, "f":0.6456211813 }, "meta":{ "p":0.3076923077, "r":0.6923076923, "f":0.426035503 } }, "ents_p":0.9008293365, "ents_r":0.9029947917, "ents_f":0.9019107643, "ents_per_type":{ "DATE":{ "p":0.8887152235, "r":0.9025396825, "f":0.8955741062 }, "GPE":{ "p":0.9587454083, "r":0.9464435146, "f":0.9525547445 }, "ORDINAL":{ "p":0.8054711246, "r":0.8229813665, "f":0.8141321045 }, "ORG":{ "p":0.9053191489, "r":0.9024390244, "f":0.9038767924 }, "QUANTITY":{ "p":0.7784431138, "r":0.7142857143, "f":0.7449856734 }, "LOC":{ "p":0.843537415, "r":0.7898089172, "f":0.8157894737 }, "CARDINAL":{ "p":0.860915493, "r":0.872175981, "f":0.8665091553 }, "PERSON":{ "p":0.9385492556, "r":0.9670365535, "f":0.9525799711 }, "NORP":{ "p":0.9271417134, "r":0.9264, "f":0.9267707083 }, "FAC":{ "p":0.5524861878, "r":0.7692307692, "f":0.6430868167 }, "LAW":{ "p":0.5970149254, "r":0.625, "f":0.6106870229 }, "TIME":{ "p":0.7486631016, "r":0.8187134503, "f":0.782122905 }, "PRODUCT":{ "p":0.6411483254, "r":0.63507109, "f":0.6380952381 }, "MONEY":{ "p":0.9220779221, "r":0.9220779221, "f":0.9220779221 }, "EVENT":{ "p":0.842519685, "r":0.6149425287, "f":0.7109634551 }, "WORK_OF_ART":{ "p":0.7151898734, "r":0.5824742268, "f":0.6420454545 }, "PERCENT":{ "p":0.9207606973, "r":0.8897396631, "f":0.9049844237 }, "LANGUAGE":{ "p":1.0, "r":0.75, "f":0.8571428571 } }, "speed":3991.5559399451 }, "sources":[ { "name":"OntoNotes 5", "url":"https://catalog.ldc.upenn.edu/LDC2013T19", "license":"commercial (licensed by Explosion)", "author":"Ralph Weischedel, Martha Palmer, Mitchell Marcus, Eduard Hovy, Sameer Pradhan, Lance Ramshaw, Nianwen Xue, Ann Taylor, Jeff Kaufman, Michelle Franchini, Mohammed El-Bachouti, Robert Belvin, Ann Houston" }, { "name":"ClearNLP Constituent-to-Dependency Conversion", "url":"https://github.com/clir/clearnlp-guidelines/blob/master/md/components/dependency_conversion.md", "license":"Citation provided for reference, no code packaged with model", "author":"Emory University" }, { "name":"WordNet 3.0", "url":"https://wordnet.princeton.edu/", "author":"Princeton University", "license":"WordNet 3.0 License" }, { "name":"roberta-base", "author":"Yinhan Liu and Myle Ott and Naman Goyal and Jingfei Du and Mandar Joshi and Danqi Chen and Omer Levy and Mike Lewis and Luke Zettlemoyer and Veselin Stoyanov", "url":"https://github.com/pytorch/fairseq/tree/master/examples/roberta", "license":"" } ], "requirements":[ "spacy-curated-transformers>=0.2.0,<0.3.0" ] }