fr_core_news_md / meta.json
adrianeboyd's picture
Update spaCy pipeline
45238ee
raw
history blame
19.1 kB
{
"lang":"fr",
"name":"core_news_md",
"version":"3.7.0",
"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":">=3.7.0,<3.8.0",
"spacy_git_version":"6b4f77441",
"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",
"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":0.9737221764,
"morph_acc":0.9648987166,
"morph_micro_p":0.9868073879,
"morph_micro_r":0.9797733642,
"morph_micro_f":0.9832777965,
"morph_per_feat":{
"Definite":{
"p":0.9890430972,
"r":0.9883211679,
"f":0.9886820007
},
"Number":{
"p":0.9927751019,
"r":0.9865611193,
"f":0.9896583564
},
"PronType":{
"p":0.9954954955,
"r":0.9897632758,
"f":0.99262111
},
"Gender":{
"p":0.9822164948,
"r":0.9739330437,
"f":0.9780572308
},
"Mood":{
"p":0.9712230216,
"r":0.9591474245,
"f":0.9651474531
},
"Person":{
"p":0.9897959184,
"r":0.9761006289,
"f":0.98290057
},
"Tense":{
"p":0.9691358025,
"r":0.962206333,
"f":0.9656586366
},
"VerbForm":{
"p":0.9849498328,
"r":0.9751655629,
"f":0.9800332779
},
"NumType":{
"p":1.0,
"r":0.9658703072,
"f":0.9826388889
},
"Reflex":{
"p":0.9777777778,
"r":1.0,
"f":0.9887640449
},
"Voice":{
"p":0.906779661,
"r":0.9553571429,
"f":0.9304347826
},
"Poss":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Polarity":{
"p":0.9882352941,
"r":0.9882352941,
"f":0.9882352941
}
},
"sents_p":0.8819277108,
"sents_r":0.8946497306,
"sents_f":0.8851269649,
"dep_uas":0.8947398877,
"dep_las":0.8562998959,
"dep_las_per_type":{
"det":{
"p":0.9790153349,
"r":0.9790153349,
"f":0.9790153349
},
"nsubj":{
"p":0.8663484487,
"r":0.8746987952,
"f":0.8705035971
},
"aux:tense":{
"p":0.952,
"r":0.952,
"f":0.952
},
"root":{
"p":0.8671497585,
"r":0.8713592233,
"f":0.8692493947
},
"obj":{
"p":0.8450292398,
"r":0.8575667656,
"f":0.8512518409
},
"cc":{
"p":0.8858447489,
"r":0.8940092166,
"f":0.8899082569
},
"case":{
"p":0.9687712152,
"r":0.9720708447,
"f":0.9704182251
},
"obl:mod":{
"p":0.6698412698,
"r":0.6298507463,
"f":0.6492307692
},
"nmod":{
"p":0.812319538,
"r":0.8431568432,
"f":0.8274509804
},
"conj":{
"p":0.5533596838,
"r":0.5511811024,
"f":0.5522682446
},
"nummod":{
"p":0.9141104294,
"r":0.8816568047,
"f":0.8975903614
},
"amod":{
"p":0.9189686924,
"r":0.9089253188,
"f":0.9139194139
},
"acl":{
"p":0.7100591716,
"r":0.6936416185,
"f":0.701754386
},
"mark":{
"p":0.8883928571,
"r":0.8766519824,
"f":0.8824833703
},
"xcomp":{
"p":0.8620689655,
"r":0.8278145695,
"f":0.8445945946
},
"flat:name":{
"p":0.8952380952,
"r":0.8952380952,
"f":0.8952380952
},
"cop":{
"p":0.8681318681,
"r":0.8777777778,
"f":0.8729281768
},
"advmod":{
"p":0.8553054662,
"r":0.8338557994,
"f":0.8444444444
},
"obl:arg":{
"p":0.6772727273,
"r":0.6772727273,
"f":0.6772727273
},
"appos":{
"p":0.5227272727,
"r":0.5542168675,
"f":0.5380116959
},
"nsubj:pass":{
"p":0.8604651163,
"r":0.8705882353,
"f":0.865497076
},
"aux:pass":{
"p":0.9557522124,
"r":0.9642857143,
"f":0.96
},
"acl:relcl":{
"p":0.6329113924,
"r":0.5813953488,
"f":0.6060606061
},
"advcl":{
"p":0.4756097561,
"r":0.5,
"f":0.4875
},
"fixed":{
"p":0.8202247191,
"r":0.73,
"f":0.7724867725
},
"dep":{
"p":0.25,
"r":0.4827586207,
"f":0.3294117647
},
"expl:subj":{
"p":0.7647058824,
"r":0.8125,
"f":0.7878787879
},
"expl:comp":{
"p":0.6666666667,
"r":0.9333333333,
"f":0.7777777778
},
"expl:pass":{
"p":0.4,
"r":0.2857142857,
"f":0.3333333333
},
"ccomp":{
"p":0.7037037037,
"r":0.7450980392,
"f":0.7238095238
},
"parataxis":{
"p":0.6875,
"r":0.3928571429,
"f":0.5
},
"iobj":{
"p":0.7857142857,
"r":0.44,
"f":0.5641025641
},
"obl:agent":{
"p":0.8974358974,
"r":0.8333333333,
"f":0.8641975309
},
"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":0.2857142857,
"f":0.4444444444
},
"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":0.9450741962,
"lemma_acc":0.9134812988,
"ents_p":0.8317031703,
"ents_r":0.8322525119,
"ents_f":0.8319777504,
"ents_per_type":{
"PER":{
"p":0.8970691842,
"r":0.9123020706,
"f":0.9046215055
},
"LOC":{
"p":0.8359820952,
"r":0.8515435456,
"f":0.8436910707
},
"ORG":{
"p":0.767491717,
"r":0.7515267176,
"f":0.7594253206
},
"MISC":{
"p":0.7205253996,
"r":0.6637993877,
"f":0.6910001518
}
},
"speed":3829.6929086605
},
"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":[
]
}