fr_core_news_md / meta.json
osanseviero's picture
osanseviero HF staff
Update spaCy pipeline
53b5461
raw
history blame
No virus
19.1 kB
{
"lang":"fr",
"name":"core_news_md",
"version":"3.2.0",
"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":">=3.2.0,<3.3.0",
"spacy_git_version":"bb26550e2",
"vectors":{
"width":300,
"vectors":20000,
"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",
"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":0.9734577127,
"morph_acc":0.9646282355,
"morph_micro_p":0.9870385159,
"morph_micro_r":0.9789204338,
"morph_micro_f":0.9829627137,
"morph_per_feat":{
"Definite":{
"p":0.9890270666,
"r":0.9868613139,
"f":0.9879430033
},
"Number":{
"p":0.9940597735,
"r":0.9858247423,
"f":0.9899251317
},
"PronType":{
"p":0.9954896907,
"r":0.9884836852,
"f":0.9919743178
},
"Gender":{
"p":0.9824380165,
"r":0.9721441349,
"f":0.9772639692
},
"Mood":{
"p":0.972972973,
"r":0.9591474245,
"f":0.9660107335
},
"Person":{
"p":0.9897828863,
"r":0.9748427673,
"f":0.9822560203
},
"Tense":{
"p":0.9672131148,
"r":0.9642492339,
"f":0.9657289003
},
"VerbForm":{
"p":0.9816971714,
"r":0.9768211921,
"f":0.979253112
},
"NumType":{
"p":0.9929577465,
"r":0.9624573379,
"f":0.9774696707
},
"Reflex":{
"p":0.9777777778,
"r":1.0,
"f":0.9887640449
},
"Voice":{
"p":0.9224137931,
"r":0.9553571429,
"f":0.9385964912
},
"Poss":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Polarity":{
"p":1.0,
"r":0.9764705882,
"f":0.9880952381
}
},
"sents_p":0.8782816229,
"sents_r":0.8932038835,
"sents_f":0.8856799037,
"dep_uas":0.8967353554,
"dep_las":0.8580193321,
"dep_las_per_type":{
"det":{
"p":0.9805668016,
"r":0.9774011299,
"f":0.9789814066
},
"nsubj":{
"p":0.8762376238,
"r":0.8530120482,
"f":0.8644688645
},
"aux:tense":{
"p":0.9285714286,
"r":0.936,
"f":0.9322709163
},
"root":{
"p":0.8865248227,
"r":0.9101941748,
"f":0.8982035928
},
"obj":{
"p":0.849112426,
"r":0.8516320475,
"f":0.8503703704
},
"cc":{
"p":0.8909090909,
"r":0.9032258065,
"f":0.8970251716
},
"case":{
"p":0.9695740365,
"r":0.9768392371,
"f":0.9731930777
},
"obl:mod":{
"p":0.6749226006,
"r":0.6507462687,
"f":0.6626139818
},
"nmod":{
"p":0.8055028463,
"r":0.8481518482,
"f":0.8262773723
},
"conj":{
"p":0.5241935484,
"r":0.5118110236,
"f":0.5179282869
},
"nummod":{
"p":0.9141104294,
"r":0.8816568047,
"f":0.8975903614
},
"amod":{
"p":0.9235074627,
"r":0.9016393443,
"f":0.9124423963
},
"acl":{
"p":0.6994219653,
"r":0.6994219653,
"f":0.6994219653
},
"mark":{
"p":0.8689956332,
"r":0.8766519824,
"f":0.8728070175
},
"xcomp":{
"p":0.8531468531,
"r":0.8079470199,
"f":0.8299319728
},
"flat:name":{
"p":0.9504950495,
"r":0.9142857143,
"f":0.932038835
},
"cop":{
"p":0.8602150538,
"r":0.8888888889,
"f":0.8743169399
},
"advmod":{
"p":0.8566978193,
"r":0.8620689655,
"f":0.859375
},
"obl:arg":{
"p":0.7562189055,
"r":0.6909090909,
"f":0.7220902613
},
"appos":{
"p":0.4938271605,
"r":0.4819277108,
"f":0.487804878
},
"nsubj:pass":{
"p":0.875,
"r":0.8235294118,
"f":0.8484848485
},
"aux:pass":{
"p":0.9469026549,
"r":0.9553571429,
"f":0.9511111111
},
"acl:relcl":{
"p":0.5764705882,
"r":0.5697674419,
"f":0.5730994152
},
"advcl":{
"p":0.4698795181,
"r":0.5,
"f":0.4844720497
},
"fixed":{
"p":0.8705882353,
"r":0.74,
"f":0.8
},
"dep":{
"p":0.3392857143,
"r":0.6551724138,
"f":0.4470588235
},
"expl:subj":{
"p":0.7647058824,
"r":0.8125,
"f":0.7878787879
},
"expl:comp":{
"p":0.6585365854,
"r":0.9,
"f":0.7605633803
},
"expl:pass":{
"p":0.3333333333,
"r":0.1428571429,
"f":0.2
},
"ccomp":{
"p":0.7058823529,
"r":0.7058823529,
"f":0.7058823529
},
"parataxis":{
"p":0.5,
"r":0.3571428571,
"f":0.4166666667
},
"iobj":{
"p":0.7222222222,
"r":0.52,
"f":0.6046511628
},
"obl:agent":{
"p":0.8684210526,
"r":0.7857142857,
"f":0.825
},
"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":1.0,
"r":0.4285714286,
"f":0.6
},
"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":0.9448023502,
"lemma_acc":0.9070078093,
"ents_p":0.8332265556,
"ents_r":0.8329930747,
"ents_f":0.8331097988,
"ents_per_type":{
"PER":{
"p":0.8976195492,
"r":0.9158845024,
"f":0.9066600468
},
"LOC":{
"p":0.8411137734,
"r":0.8516690371,
"f":0.8463584968
},
"ORG":{
"p":0.763618677,
"r":0.7490458015,
"f":0.7562620424
},
"MISC":{
"p":0.7152963371,
"r":0.6633620061,
"f":0.6883509834
}
},
"speed":4392.7454027339
},
"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":[
]
}