{ "lang": "fr", "name": "core_news_sm", "version": "3.8.0", "description": "French pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, ner, attribute_ruler, lemmatizer.", "author": "Explosion", "email": "contact@explosion.ai", "url": "https://explosion.ai", "license": "LGPL-LR", "spacy_version": ">=3.8.0,<3.9.0", "spacy_git_version": "5010fcbd3", "vectors": { "width": 0, "vectors": 0, "keys": 0, "name": null, "mode": "default" }, "labels": { "tok2vec": [], "morphologizer": [ "POS=PROPN", "Gender=Fem|Number=Sing|POS=DET|PronType=Dem", "Gender=Fem|Number=Sing|POS=NOUN", "Number=Plur|POS=PRON|Person=1", "Mood=Ind|Number=Sing|POS=VERB|Person=3|Tense=Pres|VerbForm=Fin", "POS=SCONJ", "POS=ADP", "Definite=Def|Gender=Masc|Number=Sing|POS=DET|PronType=Art", "NumType=Ord|POS=ADJ", "Gender=Masc|Number=Sing|POS=NOUN", "POS=PUNCT", "Gender=Masc|Number=Sing|POS=PROPN", "Number=Plur|POS=ADJ", "Gender=Masc|Number=Plur|POS=NOUN", "Definite=Ind|Gender=Fem|Number=Sing|POS=DET|PronType=Art", "Number=Sing|POS=ADJ", "Mood=Ind|Number=Sing|POS=VERB|Person=3|Tense=Imp|VerbForm=Fin", "POS=ADV", "Mood=Ind|Number=Sing|POS=AUX|Person=3|Tense=Past|VerbForm=Fin", "Gender=Fem|Number=Sing|POS=VERB|Tense=Past|VerbForm=Part|Voice=Pass", "Definite=Def|Gender=Fem|Number=Sing|POS=DET|PronType=Art", "Gender=Fem|Number=Sing|POS=PROPN", "Definite=Def|Number=Sing|POS=DET|PronType=Art", "NumType=Card|POS=NUM", "Definite=Def|Number=Plur|POS=DET|PronType=Art", "Gender=Masc|Number=Plur|POS=ADJ", "POS=CCONJ", "Gender=Fem|Number=Plur|POS=NOUN", "Mood=Ind|Number=Plur|POS=VERB|Person=3|Tense=Past|VerbForm=Fin", "Gender=Masc|Number=Sing|POS=VERB|Tense=Past|VerbForm=Part", "Gender=Fem|Number=Plur|POS=ADJ", "POS=ADJ", "Mood=Ind|Number=Sing|POS=VERB|Person=3|Tense=Past|VerbForm=Fin", "POS=PRON|PronType=Rel", "Number=Sing|POS=DET|Poss=Yes", "Definite=Def|Gender=Masc|Number=Sing|POS=ADP|PronType=Art", "Definite=Def|Number=Plur|POS=ADP|PronType=Art", "Definite=Ind|Number=Plur|POS=DET|PronType=Art", "Mood=Ind|Number=Plur|POS=AUX|Person=3|Tense=Past|VerbForm=Fin", "Gender=Masc|Number=Plur|POS=VERB|Tense=Past|VerbForm=Part|Voice=Pass", "Mood=Ind|Number=Sing|POS=AUX|Person=3|Tense=Pres|VerbForm=Fin", "POS=VERB|VerbForm=Inf", "Gender=Fem|Number=Sing|POS=ADJ", "Gender=Masc|Number=Sing|POS=PRON|Person=3", "Number=Plur|POS=DET", "Mood=Ind|Number=Plur|POS=AUX|Person=3|Tense=Pres|VerbForm=Fin", "Gender=Masc|Number=Sing|POS=ADJ", "Gender=Masc|Number=Sing|POS=DET|PronType=Dem", "POS=ADV|PronType=Int", "POS=VERB|Tense=Pres|VerbForm=Part", "Gender=Fem|Number=Sing|POS=VERB|Tense=Past|VerbForm=Part", "Definite=Ind|Gender=Masc|Number=Sing|POS=DET|PronType=Art", "Gender=Masc|POS=ADJ", "Mood=Ind|Number=Plur|POS=VERB|Person=3|Tense=Fut|VerbForm=Fin", "Number=Plur|POS=DET|Poss=Yes", "POS=AUX|VerbForm=Inf", "Gender=Masc|Number=Sing|POS=VERB|Tense=Past|VerbForm=Part|Voice=Pass", "Gender=Masc|POS=VERB|Tense=Past|VerbForm=Part", "POS=ADV|Polarity=Neg", "Definite=Ind|Number=Sing|POS=DET|PronType=Art", "Gender=Fem|Number=Sing|POS=PRON|Person=3", "POS=PRON|Person=3|Reflex=Yes", "Gender=Masc|POS=NOUN", "POS=AUX|Tense=Past|VerbForm=Part", "POS=PRON|Person=3", "Number=Plur|POS=NOUN", "NumType=Ord|Number=Sing|POS=ADJ", "POS=VERB|Tense=Past|VerbForm=Part", "POS=AUX|Tense=Pres|VerbForm=Part", "Gender=Masc|Number=Plur|POS=VERB|Tense=Past|VerbForm=Part", "Number=Sing|POS=PRON|Person=3", "Number=Sing|POS=NOUN", "Gender=Masc|Number=Plur|POS=PRON|Person=3", "Mood=Ind|Number=Plur|POS=VERB|Person=3|Tense=Imp|VerbForm=Fin", "Gender=Fem|NumType=Ord|Number=Sing|POS=ADJ", "Number=Plur|POS=PROPN", "Number=Sing|POS=PROPN", "Mood=Ind|Number=Sing|POS=AUX|Person=3|Tense=Imp|VerbForm=Fin", "Mood=Ind|Number=Plur|POS=VERB|Person=3|Tense=Pres|VerbForm=Fin", "Gender=Masc|Number=Plur|POS=PRON|PronType=Dem", "Gender=Masc|Number=Sing|POS=DET", "Gender=Fem|Number=Sing|POS=DET|Poss=Yes", "Gender=Masc|POS=PRON", "POS=NOUN", "Mood=Ind|Number=Sing|POS=VERB|Person=3|Tense=Fut|VerbForm=Fin", "Mood=Ind|Number=Sing|POS=AUX|Person=3|Tense=Fut|VerbForm=Fin", "Mood=Ind|Number=Plur|POS=VERB|Person=1|Tense=Pres|VerbForm=Fin", "Number=Plur|POS=PRON", "Gender=Masc|NumType=Ord|Number=Plur|POS=ADJ", "Mood=Ind|Number=Plur|POS=AUX|Person=3|Tense=Fut|VerbForm=Fin", "Gender=Fem|Number=Plur|POS=VERB|Tense=Past|VerbForm=Part|Voice=Pass", "Number=Sing|POS=PRON", "Number=Sing|POS=PRON|PronType=Dem", "Mood=Ind|POS=VERB|VerbForm=Fin", "Number=Plur|POS=DET|PronType=Dem", "Gender=Masc|Number=Sing|POS=PRON|Person=3|PronType=Prs", "Gender=Masc|Number=Plur|POS=PRON|Person=3|PronType=Prs", "Gender=Masc|Number=Sing|POS=PRON", "Gender=Masc|Number=Sing|POS=PRON|Person=3|PronType=Dem", "Number=Sing|POS=PRON|Person=2|PronType=Prs", "Gender=Masc|Number=Sing|POS=PRON|PronType=Rel", "Mood=Ind|Number=Plur|POS=AUX|Person=3|Tense=Imp|VerbForm=Fin", "Mood=Sub|Number=Sing|POS=AUX|Person=3|Tense=Pres|VerbForm=Fin", "Gender=Masc|NumType=Ord|Number=Sing|POS=ADJ", "POS=PRON", "POS=NUM", "Gender=Fem|POS=NOUN", "POS=SPACE", "Gender=Fem|Number=Plur|POS=PRON", "Number=Plur|POS=PRON|Person=3", "Number=Sing|POS=VERB|Tense=Past|VerbForm=Part", "Number=Sing|POS=PRON|Person=1", "Mood=Ind|Number=Sing|POS=VERB|Person=1|Tense=Pres|VerbForm=Fin", "Mood=Sub|Number=Sing|POS=VERB|Person=3|Tense=Past|VerbForm=Fin", "Gender=Fem|Number=Sing|POS=PRON", "Gender=Fem|Number=Sing|POS=PRON|Person=3|PronType=Prs", "Mood=Sub|Number=Sing|POS=VERB|Person=3|Tense=Pres|VerbForm=Fin", "POS=INTJ", "Number=Plur|POS=PRON|Person=2", "NumType=Card|POS=PRON", "Definite=Ind|Gender=Fem|Number=Plur|POS=DET|PronType=Art", "Gender=Fem|Number=Plur|POS=VERB|Tense=Past|VerbForm=Part", "NumType=Card|POS=NOUN", "POS=PRON|PronType=Int", "Gender=Fem|Number=Plur|POS=PRON|Person=3", "Gender=Fem|Number=Sing|POS=DET", "Mood=Cnd|Number=Sing|POS=AUX|Person=3|Tense=Pres|VerbForm=Fin", "Gender=Fem|Number=Plur|POS=DET", "Mood=Sub|Number=Plur|POS=VERB|Person=3|Tense=Pres|VerbForm=Fin", "Definite=Ind|Gender=Masc|Number=Plur|POS=DET|PronType=Art", "Mood=Cnd|Number=Sing|POS=VERB|Person=3|Tense=Pres|VerbForm=Fin", "Gender=Masc|Number=Sing|POS=PRON|PronType=Dem", "Gender=Masc|Number=Plur|POS=PROPN", "Mood=Cnd|Number=Plur|POS=VERB|Person=3|Tense=Pres|VerbForm=Fin", "Gender=Fem|Number=Sing|POS=PRON|PronType=Dem", "Number=Sing|POS=DET", "Gender=Masc|NumType=Card|Number=Plur|POS=NOUN", "Gender=Fem|Number=Plur|POS=PRON|PronType=Dem", "Mood=Ind|POS=VERB|Person=3|Tense=Pres|VerbForm=Fin", "Gender=Fem|POS=PRON", "Gender=Masc|POS=VERB|Tense=Past|VerbForm=Part|Voice=Pass", "Gender=Fem|Number=Sing|POS=PRON|PronType=Rel", "Mood=Ind|Number=Sing|POS=AUX|Person=1|Tense=Imp|VerbForm=Fin", "Mood=Cnd|Number=Plur|POS=VERB|Person=1|Tense=Pres|VerbForm=Fin", "Mood=Ind|Number=Sing|POS=AUX|Person=1|Tense=Pres|VerbForm=Fin", "Gender=Masc|Number=Sing|POS=AUX|Tense=Past|VerbForm=Part", "POS=X", "POS=SYM", "Mood=Imp|Number=Plur|POS=VERB|Person=2|Tense=Pres|VerbForm=Fin", "Mood=Ind|Number=Plur|POS=VERB|Person=2|Tense=Pres|VerbForm=Fin", "Gender=Masc|Number=Sing|POS=DET|PronType=Int", "Gender=Fem|Number=Plur|POS=DET|PronType=Int", "POS=DET", "Gender=Masc|Number=Plur|POS=PRON", "Mood=Sub|Number=Plur|POS=AUX|Person=3|Tense=Pres|VerbForm=Fin", "Mood=Ind|POS=VERB|Person=3|VerbForm=Fin", "Number=Sing|POS=VERB|Tense=Past|VerbForm=Part|Voice=Pass", "Mood=Cnd|Number=Plur|POS=VERB|Person=2|Tense=Pres|VerbForm=Fin", "Mood=Ind|Number=Plur|POS=AUX|Person=2|Tense=Pres|VerbForm=Fin", "Gender=Fem|Number=Sing|POS=DET|PronType=Int", "Gender=Masc|Number=Plur|POS=DET", "Gender=Fem|Number=Plur|POS=PRON|PronType=Rel", "Number=Plur|POS=VERB|Tense=Past|VerbForm=Part|Voice=Pass", "Gender=Masc|Number=Plur|POS=PRON|PronType=Rel", "POS=VERB|Tense=Past|VerbForm=Part|Voice=Pass", "Gender=Fem|NumType=Ord|Number=Plur|POS=ADJ", "Mood=Ind|Number=Plur|POS=VERB|Person=2|Tense=Fut|VerbForm=Fin", "Mood=Imp|POS=VERB|Tense=Pres|VerbForm=Fin", "Number=Plur|POS=PRON|Person=2|Reflex=Yes", "Mood=Cnd|Number=Sing|POS=VERB|Person=1|Tense=Pres|VerbForm=Fin", "Number=Plur|POS=PRON|Person=1|Reflex=Yes", "Gender=Masc|NumType=Card|Number=Sing|POS=NOUN", "Mood=Ind|Number=Plur|POS=AUX|Person=1|Tense=Pres|VerbForm=Fin", "Mood=Ind|Number=Plur|POS=AUX|Person=1|Tense=Fut|VerbForm=Fin", "Mood=Ind|Number=Plur|POS=VERB|Person=1|Tense=Fut|VerbForm=Fin", "Number=Sing|POS=PRON|Person=1|Reflex=Yes", "Mood=Ind|Number=Plur|POS=VERB|Person=1|Tense=Imp|VerbForm=Fin", "Mood=Ind|Number=Plur|POS=AUX|Person=1|Tense=Imp|VerbForm=Fin", "Mood=Ind|Number=Sing|POS=VERB|Person=1|Tense=Imp|VerbForm=Fin", "Mood=Sub|Number=Sing|POS=VERB|Person=1|Tense=Pres|VerbForm=Fin", "Gender=Masc|POS=PROPN", "Mood=Cnd|Number=Plur|POS=AUX|Person=3|Tense=Pres|VerbForm=Fin", "Number=Plur|POS=PRON|Person=1|PronType=Prs", "Mood=Sub|Number=Sing|POS=AUX|Person=1|Tense=Pres|VerbForm=Fin", "Number=Plur|POS=PRON|Person=2|PronType=Prs", "Mood=Ind|Number=Sing|POS=VERB|Person=1|Tense=Fut|VerbForm=Fin", "Gender=Fem|Number=Plur|POS=PRON|Person=3|PronType=Prs", "Number=Sing|POS=PRON|Person=1|PronType=Prs", "Mood=Cnd|Number=Sing|POS=AUX|Person=1|Tense=Pres|VerbForm=Fin", "Mood=Sub|Number=Plur|POS=AUX|Person=1|Tense=Pres|VerbForm=Fin", "Mood=Imp|Number=Plur|POS=VERB|Person=1|Tense=Pres|VerbForm=Fin", "Mood=Sub|Number=Plur|POS=AUX|Person=2|Tense=Pres|VerbForm=Fin", "Mood=Ind|Number=Plur|POS=VERB|Person=2|Tense=Imp|VerbForm=Fin", "Mood=Ind|Number=Sing|POS=AUX|Person=2|Tense=Imp|VerbForm=Fin", "Number=Plur|POS=VERB|Tense=Past|VerbForm=Part", "Gender=Fem|Number=Plur|POS=PROPN", "Gender=Masc|NumType=Card|POS=NUM" ], "parser": [ "ROOT", "acl", "acl:relcl", "advcl", "advmod", "amod", "appos", "aux:pass", "aux:tense", "case", "cc", "ccomp", "conj", "cop", "dep", "det", "expl:comp", "expl:pass", "expl:subj", "fixed", "flat:foreign", "flat:name", "iobj", "mark", "nmod", "nsubj", "nsubj:pass", "nummod", "obj", "obl:agent", "obl:arg", "obl:mod", "parataxis", "punct", "vocative", "xcomp" ], "attribute_ruler": [], "lemmatizer": [], "ner": [ "ARR", "DEP", "LOC", "MISC", "ORG", "PER", "TEMP", "TRANSPORT" ] }, "pipeline": [ "tok2vec", "morphologizer", "parser", "attribute_ruler", "lemmatizer", "ner" ], "components": [ "tok2vec", "morphologizer", "parser", "senter", "attribute_ruler", "lemmatizer", "ner" ], "disabled": [ "senter" ], "performance": { "sents_p": 0.8848920863, "sents_r": 0.895631068, "sents_f": 0.8902291918, "tag_acc": 0.9336837224, "ents_p": 0.8165865046, "ents_r": 0.8121572395, "ents_f": 0.8143658495, "ents_per_type": { "LOC": { "p": 0.0, "r": 0.0, "f": 0.0 }, "PER": { "p": 0.0, "r": 0.0, "f": 0.0 }, "ORG": { "p": 0.0, "r": 0.0, "f": 0.0 }, "MISC": { "p": 0.0, "r": 0.0, "f": 0.0 } }, "speed": 4299.4529582547, "token_acc": 0.997952498, "token_p": 0.9844389844, "token_r": 0.9896058454, "token_f": 0.9870156531, "pos_acc": 0.9623331787, "morph_acc": 0.9519196083, "morph_micro_p": 0.978972683, "morph_micro_r": 0.9672231022, "morph_micro_f": 0.9730624253, "morph_per_feat": { "Definite": { "p": 0.9810357403, "r": 0.9817518248, "f": 0.981393652 }, "Number": { "p": 0.990685544, "r": 0.9790132548, "f": 0.9848148148 }, "PronType": { "p": 0.9935773924, "r": 0.9897632758, "f": 0.9916666667 }, "Gender": { "p": 0.9718054837, "r": 0.9601328904, "f": 0.9659339247 }, "Mood": { "p": 0.9597806216, "r": 0.9325044405, "f": 0.9459459459 }, "Person": { "p": 0.9818181818, "r": 0.9509433962, "f": 0.9661341853 }, "Tense": { "p": 0.9490114464, "r": 0.9315628192, "f": 0.9402061856 }, "VerbForm": { "p": 0.9663016007, "r": 0.9495033113, "f": 0.95782881 }, "NumType": { "p": 0.9825174825, "r": 0.9590443686, "f": 0.9706390328 }, "Reflex": { "p": 1.0, "r": 1.0, "f": 1.0 }, "Voice": { "p": 0.8803418803, "r": 0.9196428571, "f": 0.8995633188 }, "Poss": { "p": 1.0, "r": 1.0, "f": 1.0 }, "Polarity": { "p": 0.976744186, "r": 0.9882352941, "f": 0.9824561404 } }, "dep_uas": 0.8804121324, "dep_las": 0.8361784619, "dep_las_per_type": { "det": { "p": 0.9754901961, "r": 0.9636803874, "f": 0.9695493301 }, "nsubj": { "p": 0.8381642512, "r": 0.8361445783, "f": 0.8371531966 }, "aux:tense": { "p": 0.9349593496, "r": 0.92, "f": 0.9274193548 }, "root": { "p": 0.84375, "r": 0.8519417476, "f": 0.847826087 }, "obj": { "p": 0.8102409639, "r": 0.7982195846, "f": 0.8041853513 }, "cc": { "p": 0.8944954128, "r": 0.8986175115, "f": 0.8965517241 }, "case": { "p": 0.9571619813, "r": 0.9741144414, "f": 0.9655638082 }, "obl:mod": { "p": 0.6375404531, "r": 0.5880597015, "f": 0.6118012422 }, "nmod": { "p": 0.7817497648, "r": 0.8301698302, "f": 0.8052325581 }, "conj": { "p": 0.564516129, "r": 0.5511811024, "f": 0.5577689243 }, "nummod": { "p": 0.8875, "r": 0.8402366864, "f": 0.8632218845 }, "amod": { "p": 0.8821362799, "r": 0.8724954463, "f": 0.8772893773 }, "acl": { "p": 0.6440677966, "r": 0.6589595376, "f": 0.6514285714 }, "mark": { "p": 0.8733031674, "r": 0.8502202643, "f": 0.8616071429 }, "xcomp": { "p": 0.8111888112, "r": 0.7682119205, "f": 0.7891156463 }, "flat:name": { "p": 0.8703703704, "r": 0.8952380952, "f": 0.882629108 }, "cop": { "p": 0.8279569892, "r": 0.8555555556, "f": 0.8415300546 }, "advmod": { "p": 0.8279220779, "r": 0.7993730408, "f": 0.8133971292 }, "obl:arg": { "p": 0.6682464455, "r": 0.6409090909, "f": 0.6542923434 }, "appos": { "p": 0.4875, "r": 0.4698795181, "f": 0.4785276074 }, "nsubj:pass": { "p": 0.8554216867, "r": 0.8352941176, "f": 0.8452380952 }, "aux:pass": { "p": 0.9380530973, "r": 0.9464285714, "f": 0.9422222222 }, "acl:relcl": { "p": 0.5730337079, "r": 0.5930232558, "f": 0.5828571429 }, "advcl": { "p": 0.4494382022, "r": 0.5128205128, "f": 0.4790419162 }, "fixed": { "p": 0.8823529412, "r": 0.75, "f": 0.8108108108 }, "dep": { "p": 0.2549019608, "r": 0.4482758621, "f": 0.325 }, "expl:subj": { "p": 0.7058823529, "r": 0.75, "f": 0.7272727273 }, "expl:comp": { "p": 0.6666666667, "r": 0.8666666667, "f": 0.7536231884 }, "expl:pass": { "p": 0.3333333333, "r": 0.1428571429, "f": 0.2 }, "ccomp": { "p": 0.7111111111, "r": 0.6274509804, "f": 0.6666666667 }, "obl:agent": { "p": 0.8571428571, "r": 0.8571428571, "f": 0.8571428571 }, "parataxis": { "p": 0.5263157895, "r": 0.3571428571, "f": 0.4255319149 }, "iobj": { "p": 0.6666666667, "r": 0.64, "f": 0.6530612245 }, "nsubj:caus": { "p": 0.0, "r": 0.0, "f": 0.0 }, "aux:caus": { "p": 0.0, "r": 0.0, "f": 0.0 }, "obj:agent": { "p": 0.0, "r": 0.0, "f": 0.0 }, "goeswith": { "p": 0.0, "r": 0.0, "f": 0.0 }, "vocative": { "p": 1.0, "r": 0.625, "f": 0.7692307692 }, "dislocated": { "p": 0.0, "r": 0.0, "f": 0.0 }, "flat:foreign": { "p": 0.0, "r": 0.0, "f": 0.0 }, "orphan": { "p": 0.0, "r": 0.0, "f": 0.0 }, "advcl:cleft": { "p": 0.0, "r": 0.0, "f": 0.0 }, "csubj": { "p": 0.0, "r": 0.0, "f": 0.0 } }, "lemma_acc": 0.9076243321 }, "sources": [ { "name": "UD French Sequoia v2.8", "url": "https://github.com/UniversalDependencies/UD_French-Sequoia", "license": "LGPL-LR", "author": "Candito, Marie; Seddah, Djam\u00e9; Perrier, Guy; Guillaume, Bruno" }, { "name": "WikiNER", "url": "https://figshare.com/articles/Learning_multilingual_named_entity_recognition_from_Wikipedia/5462500", "license": "CC BY 4.0", "author": "Joel Nothman, Nicky Ringland, Will Radford, Tara Murphy, James R Curran" }, { "name": "spaCy lookups data", "author": "Explosion", "url": "https://github.com/explosion/spacy-lookups-data", "license": "MIT" } ], "requirements": [] }