nb_core_news_md / meta.json
Adriane Boyd
Update spaCy pipeline
26f494b
raw history blame
No virus
19.5 kB
{
"lang":"nb",
"name":"core_news_md",
"version":"3.4.0",
"description":"Norwegian (Bokm\u00e5l) pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, lemmatizer (trainable_lemmatizer), senter, ner, attribute_ruler.",
"author":"Explosion",
"email":"contact@explosion.ai",
"url":"https://explosion.ai",
"license":"MIT",
"spacy_version":">=3.4.0,<3.5.0",
"spacy_git_version":"dd038b536",
"vectors":{
"width":300,
"vectors":20000,
"keys":500000,
"name":"nb_vectors"
},
"labels":{
"tok2vec":[
],
"morphologizer":[
"Definite=Ind|Gender=Neut|Number=Sing|POS=NOUN",
"POS=CCONJ",
"Definite=Ind|Gender=Masc|Number=Sing|POS=NOUN",
"POS=SCONJ",
"Definite=Def|Gender=Masc|Number=Sing|POS=NOUN",
"Definite=Ind|Gender=Neut|Number=Plur|POS=NOUN",
"POS=PUNCT",
"Mood=Ind|POS=VERB|Tense=Past|VerbForm=Fin",
"POS=ADP",
"Gender=Masc|Number=Sing|POS=DET|PronType=Dem",
"Definite=Def|Degree=Pos|Number=Sing|POS=ADJ",
"POS=PROPN",
"POS=X",
"Mood=Ind|POS=VERB|Tense=Pres|VerbForm=Fin",
"Definite=Def|Gender=Neut|Number=Sing|POS=NOUN",
"POS=PRON|PronType=Rel",
"Mood=Ind|POS=AUX|Tense=Pres|VerbForm=Fin",
"Definite=Ind|Gender=Neut|Number=Sing|POS=ADJ|VerbForm=Part",
"Definite=Ind|Degree=Pos|Number=Sing|POS=ADJ",
"Definite=Ind|Gender=Fem|Number=Sing|POS=NOUN",
"Number=Plur|POS=ADJ|VerbForm=Part",
"Definite=Ind|Gender=Fem|Number=Plur|POS=NOUN",
"POS=ADV",
"Gender=Neut|Number=Sing|POS=PRON|Person=3|PronType=Prs",
"Definite=Ind|Number=Sing|POS=ADJ|VerbForm=Part",
"POS=VERB|VerbForm=Part",
"Definite=Ind|Gender=Masc|Number=Plur|POS=NOUN",
"Definite=Ind|Degree=Pos|Gender=Neut|Number=Sing|POS=ADJ",
"Degree=Pos|Number=Plur|POS=ADJ",
"NumType=Card|Number=Plur|POS=NUM",
"Definite=Def|Gender=Masc|Number=Plur|POS=NOUN",
"Case=Acc|POS=PRON|PronType=Prs|Reflex=Yes",
"Case=Gen|Definite=Ind|Gender=Neut|Number=Sing|POS=NOUN",
"POS=PART",
"POS=VERB|VerbForm=Inf",
"Case=Nom|Number=Plur|POS=PRON|Person=3|PronType=Prs",
"Mood=Ind|POS=AUX|Tense=Past|VerbForm=Fin",
"Gender=Fem|POS=PROPN",
"POS=NOUN",
"Gender=Masc|POS=PROPN",
"Gender=Neut|Number=Sing|POS=DET|PronType=Dem",
"Gender=Masc|Number=Sing|POS=DET|PronType=Art",
"Case=Gen|Definite=Def|Gender=Masc|Number=Sing|POS=NOUN",
"Abbr=Yes|POS=PROPN",
"POS=PART|Polarity=Neg",
"Number=Plur|POS=PRON|Poss=Yes|PronType=Prs",
"Case=Gen|Definite=Ind|Gender=Neut|Number=Plur|POS=NOUN",
"Case=Gen|POS=PROPN",
"Gender=Fem|Number=Sing|POS=DET|PronType=Dem",
"Gender=Masc|Number=Sing|POS=PRON|Poss=Yes|PronType=Prs",
"Definite=Def|Degree=Sup|POS=ADJ",
"Case=Gen|Gender=Fem|POS=PROPN",
"Number=Plur|POS=DET|PronType=Dem",
"Case=Gen|Definite=Def|Gender=Neut|Number=Sing|POS=NOUN",
"Definite=Ind|Degree=Sup|POS=ADJ",
"Definite=Def|Gender=Fem|Number=Plur|POS=NOUN",
"Gender=Neut|POS=PROPN",
"Number=Plur|POS=DET|PronType=Int",
"Definite=Def|Gender=Neut|Number=Plur|POS=NOUN",
"Definite=Def|POS=DET|PronType=Dem",
"Gender=Neut|Number=Sing|POS=DET|PronType=Art",
"Mood=Ind|POS=VERB|Tense=Pres|VerbForm=Fin|Voice=Pass",
"Abbr=Yes|Case=Gen|POS=PROPN",
"Animacy=Hum|Case=Nom|Gender=Masc|Number=Sing|POS=PRON|Person=3|PronType=Prs",
"Degree=Cmp|POS=ADJ",
"POS=ADJ|VerbForm=Part",
"Gender=Neut|Number=Sing|POS=PRON|Poss=Yes|PronType=Prs",
"Abbr=Yes|POS=ADP",
"Definite=Ind|Gender=Neut|Number=Sing|POS=DET|PronType=Prs",
"Case=Gen|Definite=Def|Gender=Neut|Number=Plur|POS=NOUN",
"POS=AUX|VerbForm=Part",
"POS=PRON|PronType=Int",
"Gender=Fem|Number=Sing|POS=PRON|Poss=Yes|PronType=Prs",
"Number=Plur|POS=PRON|Person=3|PronType=Ind,Prs",
"Number=Plur|POS=DET|PronType=Ind",
"Degree=Pos|POS=ADJ",
"Animacy=Hum|Case=Nom|Number=Plur|POS=PRON|Person=1|PronType=Prs",
"POS=VERB|VerbForm=Inf|Voice=Pass",
"Definite=Ind|Gender=Fem|Number=Sing|POS=DET|PronType=Dem",
"Gender=Neut|Number=Sing|POS=DET|PronType=Ind",
"Animacy=Hum|Case=Acc|Gender=Masc|Number=Sing|POS=PRON|Person=3|PronType=Prs",
"Animacy=Hum|Case=Nom|Number=Sing|POS=PRON|Person=1|PronType=Prs",
"Number=Plur|POS=DET|Polarity=Neg|PronType=Neg",
"NumType=Card|POS=NUM",
"Gender=Masc|Number=Sing|POS=DET|PronType=Ind",
"POS=DET|PronType=Prs",
"Gender=Fem|Number=Sing|POS=DET|PronType=Ind",
"Case=Gen|Gender=Neut|POS=PROPN",
"Gender=Masc|Number=Sing|POS=DET|Polarity=Neg|PronType=Neg",
"Definite=Def|Number=Sing|POS=ADJ|VerbForm=Part",
"Gender=Fem,Masc|Number=Sing|POS=PRON|Person=3|PronType=Prs",
"POS=AUX|VerbForm=Inf",
"Case=Acc|Number=Plur|POS=PRON|Person=3|PronType=Prs",
"Case=Gen|Degree=Pos|Number=Plur|POS=ADJ",
"Number=Plur|POS=DET|PronType=Tot",
"Case=Gen|Gender=Masc|Number=Sing|POS=DET|PronType=Dem",
"Number=Plur|POS=DET|PronType=Prs",
"POS=SYM",
"Gender=Neut|NumType=Card|Number=Sing|POS=NUM",
"Animacy=Hum|Case=Nom|Number=Sing|POS=PRON|PronType=Prs",
"Definite=Ind|Gender=Masc|Number=Sing|POS=DET|PronType=Prs",
"Case=Gen|Definite=Ind|Gender=Masc|Number=Sing|POS=NOUN",
"Abbr=Yes|POS=ADV",
"Definite=Ind|Gender=Neut|Number=Sing|POS=DET|PronType=Dem",
"Gender=Masc|Number=Sing|POS=DET|PronType=Tot",
"Definite=Def|POS=DET|PronType=Prs",
"Animacy=Hum|Case=Nom|Gender=Fem|Number=Sing|POS=PRON|Person=3|PronType=Prs",
"Gender=Neut|POS=NOUN",
"Gender=Neut|Number=Sing|POS=DET|PronType=Int",
"Definite=Def|NumType=Card|POS=NUM",
"Mood=Imp|POS=VERB|VerbForm=Fin",
"Definite=Ind|Number=Plur|POS=NOUN",
"Gender=Neut|Number=Sing|POS=DET|PronType=Tot",
"Gender=Fem|Number=Sing|POS=DET|PronType=Tot",
"Animacy=Hum|Case=Acc|Number=Plur|POS=PRON|Person=1|PronType=Prs",
"Gender=Fem,Masc|Number=Sing|POS=PRON|Person=3|Polarity=Neg|PronType=Neg,Prs",
"Number=Plur|POS=PRON|Person=3|Polarity=Neg|PronType=Neg,Prs",
"Definite=Def|NumType=Card|Number=Sing|POS=NUM",
"Gender=Masc|NumType=Card|Number=Sing|POS=NUM",
"Definite=Ind|Gender=Masc|Number=Sing|POS=DET|PronType=Dem",
"Case=Gen|Definite=Def|Gender=Fem|Number=Plur|POS=NOUN",
"Case=Gen|Gender=Neut|Number=Sing|POS=DET|PronType=Dem",
"POS=SPACE",
"Animacy=Hum|Number=Sing|POS=PRON|PronType=Art,Prs",
"Mood=Imp|POS=AUX|VerbForm=Fin",
"Number=Plur|POS=PRON|Person=3|PronType=Prs,Tot",
"Number=Plur|POS=ADJ",
"Gender=Masc|POS=NOUN",
"Abbr=Yes|POS=NOUN",
"Case=Gen|Definite=Ind|Gender=Masc|Number=Plur|POS=NOUN",
"Gender=Neut|Number=Sing|POS=PRON|Person=3|PronType=Ind,Prs",
"POS=INTJ",
"Animacy=Hum|Case=Nom|Number=Sing|POS=PRON|Person=2|PronType=Prs",
"Animacy=Hum|Case=Acc|Number=Sing|POS=PRON|Person=1|PronType=Prs",
"Case=Gen|Definite=Def|Gender=Masc|Number=Plur|POS=NOUN",
"POS=ADJ",
"Animacy=Hum|Case=Acc|Gender=Fem|Number=Sing|POS=PRON|Person=3|PronType=Prs",
"Animacy=Hum|Case=Acc|Number=Sing|POS=PRON|Person=2|PronType=Prs",
"Definite=Def|Gender=Fem|Number=Sing|POS=NOUN",
"Number=Sing|POS=PRON|Polarity=Neg|PronType=Neg",
"Case=Gen|POS=NOUN",
"Definite=Ind|Number=Sing|POS=ADJ",
"Case=Gen|Gender=Masc|POS=PROPN",
"Animacy=Hum|Number=Plur|POS=PRON|PronType=Rcp",
"Case=Gen|Definite=Ind|Gender=Fem|Number=Sing|POS=NOUN",
"Number=Plur|POS=PRON|Person=3|PronType=Prs",
"Gender=Fem,Masc|Number=Sing|POS=PRON|Person=3|PronType=Ind,Prs",
"Definite=Ind|Gender=Fem|Number=Sing|POS=DET|PronType=Prs",
"Case=Gen|Definite=Def|Gender=Fem|Number=Sing|POS=NOUN",
"Gender=Fem|Number=Sing|POS=DET|PronType=Art",
"Case=Gen|Definite=Def|Degree=Pos|Number=Sing|POS=ADJ",
"Gender=Masc|Number=Sing|POS=DET|PronType=Int",
"NumType=Card|Number=Sing|POS=NUM",
"Animacy=Hum|Case=Acc|Number=Plur|POS=PRON|Person=2|PronType=Prs",
"Animacy=Hum|Case=Nom|Number=Plur|POS=PRON|Person=2|PronType=Prs",
"Case=Gen|Definite=Ind|Degree=Pos|Gender=Neut|Number=Sing|POS=ADJ",
"Degree=Sup|POS=ADJ",
"Animacy=Hum|POS=PRON|PronType=Int",
"POS=DET|PronType=Ind",
"Definite=Def|Number=Sing|POS=DET|PronType=Dem",
"Gender=Fem|POS=NOUN",
"Case=Gen|Number=Plur|POS=DET|PronType=Dem",
"Gender=Fem,Masc|Number=Sing|POS=PRON|Person=3|PronType=Prs,Tot",
"Case=Gen|Definite=Ind|Gender=Fem|Number=Plur|POS=NOUN",
"Gender=Neut|Number=Sing|POS=DET|Polarity=Neg|PronType=Neg",
"Number=Plur|POS=NOUN",
"POS=PRON|PronType=Prs",
"Case=Gen|Definite=Ind|Degree=Pos|Number=Sing|POS=ADJ",
"Definite=Ind|Number=Sing|POS=VERB|VerbForm=Part",
"Case=Gen|Definite=Def|Number=Sing|POS=ADJ|VerbForm=Part",
"Mood=Ind|POS=VERB|Tense=Past|VerbForm=Fin|Voice=Pass",
"Gender=Neut|Number=Sing|POS=DET|PronType=Dem,Ind",
"Animacy=Hum|POS=PRON|Poss=Yes|PronType=Int",
"Abbr=Yes|POS=ADJ",
"Case=Gen|Gender=Masc|Number=Sing|POS=DET|PronType=Art",
"Abbr=Yes|Definite=Def,Ind|Gender=Masc|Number=Sing|POS=NOUN",
"Case=Gen|Gender=Fem|Number=Sing|POS=DET|PronType=Dem",
"Number=Plur|POS=PRON|Poss=Yes|PronType=Rcp",
"Definite=Ind|Degree=Pos|POS=ADJ",
"Number=Plur|POS=DET|PronType=Art",
"Case=Gen|NumType=Card|Number=Plur|POS=NUM",
"Abbr=Yes|Definite=Def,Ind|Gender=Neut|Number=Plur,Sing|POS=NOUN",
"Case=Gen|Number=Plur|POS=DET|PronType=Tot",
"Abbr=Yes|Definite=Def,Ind|Gender=Masc|Number=Plur,Sing|POS=NOUN",
"Gender=Fem|Number=Sing|POS=DET|PronType=Int",
"Definite=Ind|Gender=Neut|Number=Sing|POS=ADJ",
"Case=Gen|Definite=Ind|Gender=Masc|Number=Sing|POS=DET|PronType=Dem",
"Gender=Fem|Number=Sing|POS=DET|PronType=Prs",
"Animacy=Hum|Case=Gen,Nom|Number=Sing|POS=PRON|PronType=Art,Prs",
"Definite=Def|Degree=Pos|Gender=Masc|Number=Sing|POS=ADJ",
"Animacy=Hum|Case=Gen|Number=Sing|POS=PRON|PronType=Art,Prs",
"Gender=Fem|NumType=Card|Number=Sing|POS=NUM",
"Definite=Ind|Gender=Masc|POS=NOUN",
"Definite=Def|Number=Plur|POS=NOUN",
"Number=Sing|POS=ADJ|VerbForm=Part",
"Definite=Ind|Gender=Masc|Number=Sing|POS=ADJ|VerbForm=Part",
"Abbr=Yes|Gender=Masc|POS=NOUN",
"Abbr=Yes|Case=Gen|POS=NOUN",
"Abbr=Yes|Mood=Ind|POS=VERB|Tense=Pres|VerbForm=Fin",
"Abbr=Yes|Degree=Pos|POS=ADJ",
"Case=Gen|Gender=Fem|POS=NOUN",
"Case=Gen|Degree=Cmp|POS=ADJ",
"Definite=Ind|Degree=Pos|Gender=Masc|Number=Sing|POS=ADJ",
"Gender=Masc|Number=Sing|POS=NOUN"
],
"parser":[
"ROOT",
"acl",
"acl:cleft",
"acl:relcl",
"advcl",
"advmod",
"amod",
"appos",
"aux",
"aux:pass",
"case",
"cc",
"ccomp",
"compound",
"compound:prt",
"conj",
"cop",
"csubj",
"dep",
"det",
"discourse",
"expl",
"flat:foreign",
"flat:name",
"iobj",
"mark",
"nmod",
"nsubj",
"nsubj:pass",
"nummod",
"obj",
"obl",
"orphan",
"parataxis",
"punct",
"xcomp"
],
"attribute_ruler":[
],
"ner":[
"DRV",
"EVT",
"GPE_LOC",
"GPE_ORG",
"LOC",
"MISC",
"ORG",
"PER",
"PROD"
]
},
"pipeline":[
"tok2vec",
"morphologizer",
"parser",
"lemmatizer",
"attribute_ruler",
"ner"
],
"components":[
"tok2vec",
"morphologizer",
"parser",
"lemmatizer",
"senter",
"attribute_ruler",
"ner"
],
"disabled":[
"senter"
],
"performance":{
"token_acc":0.9990350152,
"token_p":0.997080292,
"token_r":0.9953256895,
"token_f":0.9962022181,
"pos_acc":0.9726155711,
"morph_acc":0.9588648574,
"morph_micro_p":0.9762975408,
"morph_micro_r":0.9677851253,
"morph_micro_f":0.9720226967,
"morph_per_feat":{
"Definite":{
"p":0.9811364159,
"r":0.9674492458,
"f":0.9742447604
},
"Gender":{
"p":0.9491493022,
"r":0.9418571564,
"f":0.9454891692
},
"Number":{
"p":0.9778305034,
"r":0.9662246318,
"f":0.9719929245
},
"Mood":{
"p":0.985434455,
"r":0.9812453113,
"f":0.9833354216
},
"Tense":{
"p":0.9850897144,
"r":0.9816167212,
"f":0.9833501514
},
"VerbForm":{
"p":0.9756774404,
"r":0.9740873533,
"f":0.9748817485
},
"Degree":{
"p":0.9691934926,
"r":0.9618687736,
"f":0.9655172414
},
"PronType":{
"p":0.9909130247,
"r":0.9879206212,
"f":0.9894145604
},
"Poss":{
"p":0.9960159363,
"r":0.9881422925,
"f":0.9920634921
},
"Case":{
"p":0.9916294643,
"r":0.9839424142,
"f":0.9877709839
},
"Reflex":{
"p":1.0,
"r":1.0,
"f":1.0
},
"NumType":{
"p":0.9977375566,
"r":0.9074074074,
"f":0.9504310345
},
"Polarity":{
"p":0.9937106918,
"r":1.0,
"f":0.9968454259
},
"Person":{
"p":0.99191631,
"r":0.9900332226,
"f":0.9909738717
},
"Animacy":{
"p":0.9982935154,
"r":0.996592845,
"f":0.9974424552
},
"Voice":{
"p":0.9485294118,
"r":0.9347826087,
"f":0.9416058394
},
"Abbr":{
"p":0.9851851852,
"r":0.83125,
"f":0.9016949153
}
},
"sents_p":0.9284245167,
"sents_r":0.9369032794,
"sents_f":0.9326446281,
"dep_uas":0.8923091347,
"dep_las":0.8610490461,
"dep_las_per_type":{
"nmod":{
"p":0.7902772198,
"r":0.8071399261,
"f":0.7986195696
},
"nsubj":{
"p":0.8889232673,
"r":0.8853620955,
"f":0.8871391076
},
"flat:name":{
"p":0.8865814696,
"r":0.8937198068,
"f":0.8901363272
},
"root":{
"p":0.9037344398,
"r":0.904109589,
"f":0.9039219755
},
"advmod":{
"p":0.8367541766,
"r":0.8411708253,
"f":0.8389566882
},
"mark":{
"p":0.9274958171,
"r":0.924916574,
"f":0.9262043999
},
"advcl":{
"p":0.7152658662,
"r":0.7152658662,
"f":0.7152658662
},
"obj":{
"p":0.8852459016,
"r":0.9044665012,
"f":0.8947529917
},
"case":{
"p":0.9379042691,
"r":0.935483871,
"f":0.9366925065
},
"det":{
"p":0.9658444023,
"r":0.9664556962,
"f":0.9661499525
},
"obl":{
"p":0.7677725118,
"r":0.7330316742,
"f":0.75
},
"aux":{
"p":0.9400715564,
"r":0.9511312217,
"f":0.9455690508
},
"acl:relcl":{
"p":0.8079470199,
"r":0.8243243243,
"f":0.8160535117
},
"iobj":{
"p":0.75,
"r":0.6136363636,
"f":0.675
},
"xcomp":{
"p":0.7074829932,
"r":0.7074829932,
"f":0.7074829932
},
"cc":{
"p":0.9115593483,
"r":0.9059367772,
"f":0.9087393658
},
"conj":{
"p":0.7390050469,
"r":0.7443718228,
"f":0.7416787265
},
"amod":{
"p":0.9309090909,
"r":0.9303452453,
"f":0.9306270827
},
"nummod":{
"p":0.9147286822,
"r":0.9632653061,
"f":0.9383697813
},
"compound:prt":{
"p":0.8175182482,
"r":0.8086642599,
"f":0.8130671506
},
"cop":{
"p":0.8709677419,
"r":0.8688915375,
"f":0.869928401
},
"appos":{
"p":0.2643678161,
"r":0.23,
"f":0.2459893048
},
"ccomp":{
"p":0.8051470588,
"r":0.8622047244,
"f":0.8326996198
},
"expl":{
"p":0.6959798995,
"r":0.7486486486,
"f":0.7213541667
},
"csubj":{
"p":0.696,
"r":0.6350364964,
"f":0.6641221374
},
"nsubj:pass":{
"p":0.9100529101,
"r":0.7962962963,
"f":0.849382716
},
"aux:pass":{
"p":0.9464285714,
"r":0.8833333333,
"f":0.9137931034
},
"parataxis":{
"p":0.8541666667,
"r":0.6542553191,
"f":0.7409638554
},
"acl":{
"p":0.6740088106,
"r":0.6169354839,
"f":0.6442105263
},
"acl:cleft":{
"p":0.4285714286,
"r":0.3333333333,
"f":0.375
},
"orphan":{
"p":0.0,
"r":0.0,
"f":0.0
},
"dep":{
"p":0.0,
"r":0.0,
"f":0.0
},
"reparandum":{
"p":0.0,
"r":0.0,
"f":0.0
},
"compound":{
"p":0.9090909091,
"r":0.243902439,
"f":0.3846153846
},
"flat:foreign":{
"p":0.8214285714,
"r":0.7419354839,
"f":0.7796610169
},
"discourse":{
"p":0.7272727273,
"r":0.347826087,
"f":0.4705882353
},
"csubj:pass":{
"p":0.0,
"r":0.0,
"f":0.0
}
},
"lemma_acc":0.9712137072,
"tag_acc":0.9726155711,
"ents_p":0.8307228916,
"ents_r":0.816943128,
"ents_f":0.8237753883,
"ents_per_type":{
"PER":{
"p":0.9011532125,
"r":0.8952536825,
"f":0.8981937603
},
"ORG":{
"p":0.8111888112,
"r":0.8613861386,
"f":0.8355342137
},
"GPE_LOC":{
"p":0.8587360595,
"r":0.8918918919,
"f":0.875
},
"PROD":{
"p":0.6492537313,
"r":0.537037037,
"f":0.5878378378
},
"LOC":{
"p":0.7931034483,
"r":0.6330275229,
"f":0.7040816327
},
"DRV":{
"p":0.7714285714,
"r":0.6835443038,
"f":0.7248322148
},
"GPE_ORG":{
"p":0.6666666667,
"r":0.6909090909,
"f":0.6785714286
},
"EVT":{
"p":0.7142857143,
"r":0.5555555556,
"f":0.625
}
},
"speed":9847.9572403325
},
"sources":[
{
"name":"UD Norwegian Bokmaal v2.8",
"url":"https://github.com/UniversalDependencies/UD_Norwegian-Bokmaal",
"license":"Public Domain (CC0)",
"author":"\u00d8vrelid, Lilja; J\u00f8rgensen, Fredrik; Hohle, Petter"
},
{
"name":"NorNE: Norwegian Named Entities (commit: bd311de5)",
"url":"https://github.com/ltgoslo/norne",
"license":"Public Domain (CC0)",
"author":"Language Technology Group (University of Oslo)"
},
{
"name":"Explosion fastText Vectors (cbow, OSCAR Common Crawl + Wikipedia)",
"url":"https://spacy.io",
"license":"CC0",
"author":"Explosion"
}
],
"requirements":[
]
}