nb_core_news_md / meta.json
EC2 Default User
Update spaCy pipeline
113f397
raw history blame
No virus
19.5 kB
{
"lang":"nb",
"name":"core_news_md",
"version":"3.3.0",
"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":">=3.3.0.dev0,<3.4.0",
"spacy_git_version":"849bef2de",
"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",
"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":0.9737451099,
"morph_acc":0.9592638003,
"morph_micro_p":0.9765452448,
"morph_micro_r":0.9673769287,
"morph_micro_f":0.971939466,
"morph_per_feat":{
"Definite":{
"p":0.9810039143,
"r":0.9664284904,
"f":0.973661658
},
"Gender":{
"p":0.9486150907,
"r":0.9420468557,
"f":0.9453195641
},
"Number":{
"p":0.9766441759,
"r":0.9650523848,
"f":0.9708136792
},
"Mood":{
"p":0.9866498741,
"r":0.9794948737,
"f":0.983059355
},
"Tense":{
"p":0.9870853381,
"r":0.9816167212,
"f":0.9843434343
},
"VerbForm":{
"p":0.9761203795,
"r":0.9726205997,
"f":0.9743673469
},
"Degree":{
"p":0.9705065926,
"r":0.9608381999,
"f":0.9656481961
},
"PronType":{
"p":0.9924226023,
"r":0.988783434,
"f":0.9905996759
},
"Poss":{
"p":0.9960474308,
"r":0.9960474308,
"f":0.9960474308
},
"Case":{
"p":0.9927536232,
"r":0.9861572536,
"f":0.9894444444
},
"Reflex":{
"p":1.0,
"r":1.0,
"f":1.0
},
"NumType":{
"p":0.995505618,
"r":0.9115226337,
"f":0.9516648765
},
"Polarity":{
"p":0.9968454259,
"r":1.0,
"f":0.9984202212
},
"Person":{
"p":0.9928741093,
"r":0.9919316564,
"f":0.9924026591
},
"Animacy":{
"p":0.9991452991,
"r":0.9957410562,
"f":0.997440273
},
"Voice":{
"p":0.9847328244,
"r":0.9347826087,
"f":0.9591078067
},
"Abbr":{
"p":1.0,
"r":0.84375,
"f":0.9152542373
}
},
"sents_p":0.9463617464,
"sents_r":0.9447903694,
"sents_f":0.9455754051,
"dep_uas":0.8943254651,
"dep_las":0.8639894956,
"dep_las_per_type":{
"nmod":{
"p":0.7818897638,
"r":0.8149363972,
"f":0.7980711272
},
"nsubj":{
"p":0.8936567164,
"r":0.8856702619,
"f":0.8896455657
},
"flat:name":{
"p":0.8613707165,
"r":0.8904991948,
"f":0.8756927949
},
"root":{
"p":0.9095060191,
"r":0.9095060191,
"f":0.9095060191
},
"advmod":{
"p":0.8416267943,
"r":0.844049904,
"f":0.8428366076
},
"mark":{
"p":0.9289311696,
"r":0.9232480534,
"f":0.9260808926
},
"advcl":{
"p":0.7150259067,
"r":0.7101200686,
"f":0.7125645439
},
"obj":{
"p":0.8902513795,
"r":0.9007444169,
"f":0.89546716
},
"case":{
"p":0.9364057673,
"r":0.9385806452,
"f":0.9374919448
},
"det":{
"p":0.9626582278,
"r":0.9626582278,
"f":0.9626582278
},
"obl":{
"p":0.7758702909,
"r":0.736199095,
"f":0.7555142791
},
"aux":{
"p":0.9513513514,
"r":0.9556561086,
"f":0.9534988713
},
"acl:relcl":{
"p":0.7921225383,
"r":0.8153153153,
"f":0.8035516093
},
"iobj":{
"p":0.8115942029,
"r":0.6363636364,
"f":0.7133757962
},
"xcomp":{
"p":0.7305936073,
"r":0.7256235828,
"f":0.7281001138
},
"cc":{
"p":0.9164733179,
"r":0.9136468774,
"f":0.9150579151
},
"conj":{
"p":0.7287043665,
"r":0.7392883079,
"f":0.7339581831
},
"amod":{
"p":0.9394865526,
"r":0.9309509388,
"f":0.9351992699
},
"nummod":{
"p":0.9073359073,
"r":0.9591836735,
"f":0.9325396825
},
"compound:prt":{
"p":0.8237547893,
"r":0.7761732852,
"f":0.7992565056
},
"cop":{
"p":0.8704358068,
"r":0.8808104887,
"f":0.8755924171
},
"appos":{
"p":0.2816901408,
"r":0.2,
"f":0.2339181287
},
"ccomp":{
"p":0.7867132867,
"r":0.8858267717,
"f":0.8333333333
},
"expl":{
"p":0.7329974811,
"r":0.7864864865,
"f":0.7588005215
},
"csubj":{
"p":0.7272727273,
"r":0.700729927,
"f":0.7137546468
},
"nsubj:pass":{
"p":0.890625,
"r":0.7916666667,
"f":0.8382352941
},
"aux:pass":{
"p":0.9159663866,
"r":0.9083333333,
"f":0.9121338912
},
"acl":{
"p":0.7198067633,
"r":0.6008064516,
"f":0.6549450549
},
"acl:cleft":{
"p":0.4782608696,
"r":0.4074074074,
"f":0.44
},
"orphan":{
"p":0.25,
"r":0.0384615385,
"f":0.0666666667
},
"dep":{
"p":0.0,
"r":0.0,
"f":0.0
},
"reparandum":{
"p":0.0,
"r":0.0,
"f":0.0
},
"parataxis":{
"p":0.8661971831,
"r":0.6542553191,
"f":0.7454545455
},
"compound":{
"p":0.8,
"r":0.1951219512,
"f":0.3137254902
},
"flat:foreign":{
"p":0.9655172414,
"r":0.9032258065,
"f":0.9333333333
},
"discourse":{
"p":0.7777777778,
"r":0.3043478261,
"f":0.4375
},
"csubj:pass":{
"p":0.0,
"r":0.0,
"f":0.0
}
},
"lemma_acc":0.9709106936,
"tag_acc":0.9737451099,
"ents_p":0.8236700538,
"ents_r":0.8163507109,
"ents_f":0.8199940494,
"ents_per_type":{
"PER":{
"p":0.8894230769,
"r":0.9083469722,
"f":0.8987854251
},
"PROD":{
"p":0.7,
"r":0.5185185185,
"f":0.5957446809
},
"GPE_LOC":{
"p":0.8243727599,
"r":0.888030888,
"f":0.8550185874
},
"ORG":{
"p":0.8143851508,
"r":0.8688118812,
"f":0.8407185629
},
"LOC":{
"p":0.7875,
"r":0.5779816514,
"f":0.6666666667
},
"DRV":{
"p":0.7466666667,
"r":0.7088607595,
"f":0.7272727273
},
"EVT":{
"p":0.3571428571,
"r":0.5555555556,
"f":0.4347826087
},
"GPE_ORG":{
"p":0.68,
"r":0.6181818182,
"f":0.6476190476
}
},
"speed":11180.6759357661
},
"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":[
]
}