fr_core_news_sm / meta.json
osanseviero's picture
Update spaCy pipeline
8a8eb44
raw
history blame
18.9 kB
{
"lang":"fr",
"name":"core_news_sm",
"version":"3.2.0",
"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":">=3.2.0,<3.3.0",
"spacy_git_version":"bb26550e2",
"vectors":{
"width":0,
"vectors":0,
"keys":0,
"name":null
},
"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",
"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"
],
"senter":[
"I",
"S"
],
"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":0.9989751998,
"token_p":0.9844389844,
"token_r":0.9896058454,
"token_f":0.9870156531,
"pos_acc":0.9600618397,
"morph_acc":0.9492783505,
"morph_micro_p":0.9765677992,
"morph_micro_r":0.9648470818,
"morph_micro_f":0.9706720603,
"morph_per_feat":{
"Definite":{
"p":0.986100951,
"r":0.9839416058,
"f":0.985020095
},
"Number":{
"p":0.9906838085,
"r":0.9788291605,
"f":0.9847208075
},
"PronType":{
"p":0.992916935,
"r":0.9865642994,
"f":0.9897304236
},
"Gender":{
"p":0.9705502454,
"r":0.9601328904,
"f":0.9653134635
},
"Mood":{
"p":0.9575645756,
"r":0.9218472469,
"f":0.9393665158
},
"Person":{
"p":0.9726205997,
"r":0.9383647799,
"f":0.9551856594
},
"Tense":{
"p":0.936918304,
"r":0.9254341164,
"f":0.9311408016
},
"VerbForm":{
"p":0.9538977368,
"r":0.9420529801,
"f":0.947938359
},
"NumType":{
"p":0.9858156028,
"r":0.9488054608,
"f":0.9669565217
},
"Reflex":{
"p":0.9565217391,
"r":1.0,
"f":0.9777777778
},
"Voice":{
"p":0.8429752066,
"r":0.9107142857,
"f":0.8755364807
},
"Poss":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Polarity":{
"p":0.9880952381,
"r":0.9764705882,
"f":0.9822485207
}
},
"sents_p":0.8658823529,
"sents_r":0.8932038835,
"sents_f":0.8793309438,
"dep_uas":0.8770041095,
"dep_las":0.832561907,
"dep_las_per_type":{
"det":{
"p":0.9724919094,
"r":0.9701372074,
"f":0.9713131313
},
"nsubj":{
"p":0.8618925831,
"r":0.8120481928,
"f":0.8362282878
},
"aux:tense":{
"p":0.9206349206,
"r":0.928,
"f":0.9243027888
},
"root":{
"p":0.853427896,
"r":0.8762135922,
"f":0.8646706587
},
"obj":{
"p":0.8171091445,
"r":0.821958457,
"f":0.8195266272
},
"cc":{
"p":0.869955157,
"r":0.8940092166,
"f":0.8818181818
},
"case":{
"p":0.9600811908,
"r":0.9666212534,
"f":0.9633401222
},
"obl:mod":{
"p":0.6214511041,
"r":0.5880597015,
"f":0.6042944785
},
"nmod":{
"p":0.7838095238,
"r":0.8221778222,
"f":0.8025353486
},
"conj":{
"p":0.5307692308,
"r":0.5433070866,
"f":0.5369649805
},
"nummod":{
"p":0.9210526316,
"r":0.8284023669,
"f":0.8722741433
},
"amod":{
"p":0.8683729433,
"r":0.8652094718,
"f":0.8667883212
},
"acl":{
"p":0.6411764706,
"r":0.6300578035,
"f":0.6355685131
},
"mark":{
"p":0.9052132701,
"r":0.8414096916,
"f":0.8721461187
},
"xcomp":{
"p":0.8,
"r":0.7947019868,
"f":0.7973421927
},
"flat:name":{
"p":0.8482142857,
"r":0.9047619048,
"f":0.8755760369
},
"cop":{
"p":0.8571428571,
"r":0.8,
"f":0.8275862069
},
"advmod":{
"p":0.8338658147,
"r":0.8181818182,
"f":0.8259493671
},
"obl:arg":{
"p":0.6553398058,
"r":0.6136363636,
"f":0.6338028169
},
"appos":{
"p":0.417721519,
"r":0.3975903614,
"f":0.4074074074
},
"nsubj:pass":{
"p":0.7717391304,
"r":0.8352941176,
"f":0.802259887
},
"aux:pass":{
"p":0.9137931034,
"r":0.9464285714,
"f":0.9298245614
},
"acl:relcl":{
"p":0.5714285714,
"r":0.6046511628,
"f":0.5875706215
},
"advcl":{
"p":0.4929577465,
"r":0.4487179487,
"f":0.4697986577
},
"fixed":{
"p":0.691588785,
"r":0.74,
"f":0.7149758454
},
"dep":{
"p":0.2884615385,
"r":0.5172413793,
"f":0.3703703704
},
"expl:subj":{
"p":0.7058823529,
"r":0.75,
"f":0.7272727273
},
"expl:comp":{
"p":0.7428571429,
"r":0.8666666667,
"f":0.8
},
"expl:pass":{
"p":0.4,
"r":0.2857142857,
"f":0.3333333333
},
"obl:agent":{
"p":0.8205128205,
"r":0.7619047619,
"f":0.7901234568
},
"ccomp":{
"p":0.6603773585,
"r":0.6862745098,
"f":0.6730769231
},
"parataxis":{
"p":0.36,
"r":0.3214285714,
"f":0.3396226415
},
"iobj":{
"p":0.7,
"r":0.56,
"f":0.6222222222
},
"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
}
},
"tag_acc":0.9312032981,
"lemma_acc":0.9031031648,
"ents_p":0.8121504727,
"ents_r":0.8080541211,
"ents_f":0.8100971185,
"ents_per_type":{
"PER":{
"p":0.8685030449,
"r":0.8787705094,
"f":0.8736066099
},
"LOC":{
"p":0.8245838668,
"r":0.835104158,
"f":0.8298106698
},
"ORG":{
"p":0.7541699762,
"r":0.7248091603,
"f":0.7391981316
},
"MISC":{
"p":0.6852231509,
"r":0.6334742674,
"f":0.6583333333
}
},
"speed":4222.2093213177
},
"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":[
]
}