fr_core_news_lg / meta.json
adrianeboyd's picture
Update spaCy pipeline
4823964
{
"lang":"fr",
"name":"core_news_lg",
"version":"3.7.0",
"description":"French pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, ner, attribute_ruler, lemmatizer.",
"author":"Explosion",
"email":"[email protected]",
"url":"https://explosion.ai",
"license":"LGPL-LR",
"spacy_version":">=3.7.0,<3.8.0",
"spacy_git_version":"6b4f77441",
"vectors":{
"width":300,
"vectors":500000,
"keys":500000,
"name":"fr_vectors"
},
"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":[
"LOC",
"MISC",
"ORG",
"PER"
]
},
"pipeline":[
"tok2vec",
"morphologizer",
"parser",
"attribute_ruler",
"lemmatizer",
"ner"
],
"components":[
"tok2vec",
"morphologizer",
"parser",
"senter",
"attribute_ruler",
"lemmatizer",
"ner"
],
"disabled":[
"senter"
],
"performance":{
"token_acc":0.997952498,
"token_p":0.9844389844,
"token_r":0.9896058454,
"token_f":0.9870156531,
"pos_acc":0.9734102855,
"morph_acc":0.9674260386,
"morph_micro_p":0.9891344383,
"morph_micro_r":0.9816619959,
"morph_micro_f":0.9853840509,
"morph_per_feat":{
"Definite":{
"p":0.9890350877,
"r":0.9875912409,
"f":0.988312637
},
"Number":{
"p":0.9935149157,
"r":0.9871134021,
"f":0.9903038138
},
"PronType":{
"p":0.9954867827,
"r":0.98784389,
"f":0.9916506101
},
"Gender":{
"p":0.9845559846,
"r":0.9775108612,
"f":0.9810207746
},
"Mood":{
"p":0.9801444043,
"r":0.9644760213,
"f":0.9722470904
},
"Person":{
"p":0.993622449,
"r":0.9798742138,
"f":0.9867004433
},
"Tense":{
"p":0.9834710744,
"r":0.9724208376,
"f":0.9779147406
},
"VerbForm":{
"p":0.9866220736,
"r":0.9768211921,
"f":0.9816971714
},
"NumType":{
"p":1.0,
"r":0.9658703072,
"f":0.9826388889
},
"Reflex":{
"p":0.9777777778,
"r":1.0,
"f":0.9887640449
},
"Voice":{
"p":0.9224137931,
"r":0.9553571429,
"f":0.9385964912
},
"Poss":{
"p":0.9827586207,
"r":1.0,
"f":0.9913043478
},
"Polarity":{
"p":0.9882352941,
"r":0.9882352941,
"f":0.9882352941
}
},
"sents_p":0.8591549296,
"sents_r":0.8926096998,
"sents_f":0.8735083532,
"dep_uas":0.9028935185,
"dep_las":0.8654090962,
"dep_las_per_type":{
"det":{
"p":0.9805982215,
"r":0.9790153349,
"f":0.9798061389
},
"nsubj":{
"p":0.8985148515,
"r":0.8746987952,
"f":0.8864468864
},
"aux:tense":{
"p":0.96,
"r":0.96,
"f":0.96
},
"root":{
"p":0.8700696056,
"r":0.9101941748,
"f":0.8896797153
},
"obj":{
"p":0.8433048433,
"r":0.8783382789,
"f":0.8604651163
},
"cc":{
"p":0.8812785388,
"r":0.8894009217,
"f":0.8853211009
},
"case":{
"p":0.9695121951,
"r":0.9747956403,
"f":0.9721467391
},
"obl:mod":{
"p":0.6866666667,
"r":0.6149253731,
"f":0.6488188976
},
"nmod":{
"p":0.8181818182,
"r":0.8541458541,
"f":0.8357771261
},
"conj":{
"p":0.5809128631,
"r":0.5511811024,
"f":0.5656565657
},
"nummod":{
"p":0.9079754601,
"r":0.875739645,
"f":0.8915662651
},
"amod":{
"p":0.9242144177,
"r":0.9107468124,
"f":0.9174311927
},
"acl":{
"p":0.7076023392,
"r":0.6994219653,
"f":0.7034883721
},
"mark":{
"p":0.8826086957,
"r":0.8942731278,
"f":0.8884026258
},
"xcomp":{
"p":0.8445945946,
"r":0.8278145695,
"f":0.8361204013
},
"flat:name":{
"p":0.9292929293,
"r":0.8761904762,
"f":0.9019607843
},
"cop":{
"p":0.8913043478,
"r":0.9111111111,
"f":0.9010989011
},
"advmod":{
"p":0.8817891374,
"r":0.8652037618,
"f":0.8734177215
},
"obl:arg":{
"p":0.7056074766,
"r":0.6863636364,
"f":0.6958525346
},
"appos":{
"p":0.5222222222,
"r":0.5662650602,
"f":0.5433526012
},
"nsubj:pass":{
"p":0.9024390244,
"r":0.8705882353,
"f":0.8862275449
},
"aux:pass":{
"p":0.9642857143,
"r":0.9642857143,
"f":0.9642857143
},
"acl:relcl":{
"p":0.7341772152,
"r":0.6744186047,
"f":0.703030303
},
"advcl":{
"p":0.5632183908,
"r":0.6282051282,
"f":0.5939393939
},
"fixed":{
"p":0.8,
"r":0.76,
"f":0.7794871795
},
"dep":{
"p":0.3,
"r":0.6206896552,
"f":0.404494382
},
"expl:subj":{
"p":0.8387096774,
"r":0.8125,
"f":0.8253968254
},
"expl:comp":{
"p":0.675,
"r":0.9,
"f":0.7714285714
},
"expl:pass":{
"p":0.3333333333,
"r":0.1428571429,
"f":0.2
},
"ccomp":{
"p":0.8,
"r":0.7843137255,
"f":0.7920792079
},
"parataxis":{
"p":0.55,
"r":0.3928571429,
"f":0.4583333333
},
"iobj":{
"p":0.7222222222,
"r":0.52,
"f":0.6046511628
},
"obl:agent":{
"p":0.8947368421,
"r":0.8095238095,
"f":0.85
},
"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":0.8333333333,
"r":0.625,
"f":0.7142857143
},
"dislocated":{
"p":0.0,
"r":0.0,
"f":0.0
},
"flat:foreign":{
"p":0.5,
"r":0.1428571429,
"f":0.2222222222
},
"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
}
},
"tag_acc":0.9446562919,
"lemma_acc":0.9135840526,
"ents_p":0.8398572946,
"ents_r":0.83869741,
"ents_f":0.8392769516,
"ents_per_type":{
"PER":{
"p":0.9071242337,
"r":0.9223328796,
"f":0.9146653403
},
"LOC":{
"p":0.8418339999,
"r":0.8540533757,
"f":0.8478996657
},
"ORG":{
"p":0.7824390244,
"r":0.7652671756,
"f":0.7737578389
},
"MISC":{
"p":0.7278621126,
"r":0.67108908,
"f":0.6983235986
}
},
"speed":3507.691486558
},
"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"
},
{
"name":"Explosion fastText Vectors (cbow, OSCAR Common Crawl + Wikipedia)",
"url":"https://spacy.io",
"license":"CC0",
"author":"Explosion"
}
],
"requirements":[
]
}