fr_core_news_lg / meta.json
osanseviero's picture
osanseviero HF staff
Update spaCy pipeline
185a1e4
raw
history blame
19 kB
{
"lang":"fr",
"name":"core_news_lg",
"version":"3.1.0",
"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":">=3.1.0,<3.2.0",
"spacy_git_version":"caba63b74",
"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",
"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",
"POS=PART",
"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",
"Gender=Fem|POS=ADV",
"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,
"tag_acc":0.947357577,
"pos_acc":0.9760997219,
"morph_acc":0.968569662,
"lemma_acc":0.9091282684,
"dep_uas":0.897142196,
"dep_las":0.8595222948,
"sents_p":0.8521126761,
"sents_r":0.9029253272,
"sents_f":0.8715586104,
"speed":5335.1974335443,
"morph_per_feat":{
"Definite":{
"p":0.9904901244,
"r":0.9876002918,
"f":0.9890430972
},
"Number":{
"p":0.9934725849,
"r":0.9872127502,
"f":0.9903327756
},
"PronType":{
"p":0.9967845659,
"r":0.9910485934,
"f":0.9939083039
},
"Gender":{
"p":0.9865040228,
"r":0.9821705426,
"f":0.9843325133
},
"Mood":{
"p":0.9711711712,
"r":0.9573712256,
"f":0.9642218247
},
"Person":{
"p":0.9872935197,
"r":0.9761306533,
"f":0.9816803538
},
"Tense":{
"p":0.9702868852,
"r":0.9673135853,
"f":0.968797954
},
"VerbForm":{
"p":0.9833610649,
"r":0.9784768212,
"f":0.9809128631
},
"NumType":{
"p":1.0,
"r":0.9620689655,
"f":0.9806678383
},
"Reflex":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Voice":{
"p":0.9380530973,
"r":0.9464285714,
"f":0.9422222222
},
"Poss":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Polarity":{
"p":1.0,
"r":0.9882352941,
"f":0.9940828402
}
},
"dep_las_per_type":{
"det":{
"p":0.9813614263,
"r":0.9774011299,
"f":0.9793772746
},
"nsubj":{
"p":0.8704156479,
"r":0.8578313253,
"f":0.8640776699
},
"aux:tense":{
"p":0.9365079365,
"r":0.944,
"f":0.9402390438
},
"root":{
"p":0.8558139535,
"r":0.8932038835,
"f":0.8741092637
},
"obj":{
"p":0.8504398827,
"r":0.8605341246,
"f":0.8554572271
},
"cc":{
"p":0.8801843318,
"r":0.8801843318,
"f":0.8801843318
},
"case":{
"p":0.9669142471,
"r":0.9754768392,
"f":0.9711766701
},
"obl:mod":{
"p":0.678807947,
"r":0.6101190476,
"f":0.6426332288
},
"nmod":{
"p":0.8216007715,
"r":0.8502994012,
"f":0.8357037764
},
"conj":{
"p":0.5275590551,
"r":0.5275590551,
"f":0.5275590551
},
"nummod":{
"p":0.8950617284,
"r":0.8630952381,
"f":0.8787878788
},
"amod":{
"p":0.9237918216,
"r":0.9069343066,
"f":0.9152854512
},
"acl":{
"p":0.702247191,
"r":0.7225433526,
"f":0.7122507123
},
"mark":{
"p":0.8711111111,
"r":0.8634361233,
"f":0.8672566372
},
"xcomp":{
"p":0.8698630137,
"r":0.8410596026,
"f":0.8552188552
},
"flat:name":{
"p":0.8888888889,
"r":0.9142857143,
"f":0.9014084507
},
"cop":{
"p":0.8602150538,
"r":0.8888888889,
"f":0.8743169399
},
"advmod":{
"p":0.8935483871,
"r":0.868338558,
"f":0.8807631161
},
"obl:arg":{
"p":0.7104072398,
"r":0.7136363636,
"f":0.7120181406
},
"appos":{
"p":0.5857142857,
"r":0.4939759036,
"f":0.5359477124
},
"nsubj:pass":{
"p":0.8846153846,
"r":0.8117647059,
"f":0.8466257669
},
"aux:pass":{
"p":0.954954955,
"r":0.9464285714,
"f":0.9506726457
},
"acl:relcl":{
"p":0.6987951807,
"r":0.6744186047,
"f":0.6863905325
},
"advcl":{
"p":0.5256410256,
"r":0.5256410256,
"f":0.5256410256
},
"fixed":{
"p":0.8539325843,
"r":0.7524752475,
"f":0.8
},
"dep":{
"p":0.3230769231,
"r":0.6774193548,
"f":0.4375
},
"expl:subj":{
"p":0.8,
"r":0.75,
"f":0.7741935484
},
"expl:comp":{
"p":0.6428571429,
"r":0.9,
"f":0.75
},
"expl:pass":{
"p":0.3333333333,
"r":0.1428571429,
"f":0.2
},
"obl:agent":{
"p":0.8085106383,
"r":0.9047619048,
"f":0.8539325843
},
"ccomp":{
"p":0.7547169811,
"r":0.7843137255,
"f":0.7692307692
},
"parataxis":{
"p":0.4333333333,
"r":0.4642857143,
"f":0.4482758621
},
"iobj":{
"p":0.75,
"r":0.48,
"f":0.5853658537
},
"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":0.6666666667,
"r":0.2857142857,
"f":0.4
},
"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
}
},
"ents_p":0.8431266739,
"ents_r":0.8443416997,
"ents_f":0.8437337493,
"ents_per_type":{
"PER":{
"p":0.907275021,
"r":0.9274915813,
"f":0.9172719221
},
"LOC":{
"p":0.8427331441,
"r":0.8569396804,
"f":0.8497770403
},
"ORG":{
"p":0.7912621359,
"r":0.7776717557,
"f":0.7844080847
},
"MISC":{
"p":0.7418741081,
"r":0.6821694125,
"f":0.7107701656
}
}
},
"sources":[
{
"name":"UD French Sequoia v2.5",
"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":[
]
}