nb_core_news_sm / meta.json
osanseviero's picture
osanseviero HF staff
Update spaCy pipeline
04ca1fc
raw history blame
No virus
19.2 kB
{
"lang":"nb",
"name":"core_news_sm",
"version":"3.1.0",
"description":"Norwegian (Bokm\u00e5l) pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, ner, attribute_ruler, lemmatizer.",
"author":"Explosion",
"email":"contact@explosion.ai",
"url":"https://explosion.ai",
"license":"MIT",
"spacy_version":">=3.1.0,<3.2.0",
"spacy_git_version":"caba63b74",
"vectors":{
"width":0,
"vectors":0,
"keys":0,
"name":null
},
"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",
"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",
"POS=PRON|PronType=Prs",
"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"
],
"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":0.9990350152,
"tag_acc":0.9658825148,
"pos_acc":0.9671065319,
"morph_acc":0.9523770164,
"lemma_acc":0.7638422126,
"dep_uas":0.8816590207,
"dep_las":0.8478474574,
"ents_p":0.7798165138,
"ents_r":0.7531010041,
"ents_f":0.7662259615,
"sents_p":0.9229183842,
"sents_r":0.9275062138,
"sents_f":0.9252066116,
"speed":12089.2312132138,
"morph_per_feat":{
"Definite":{
"p":0.972459092,
"r":0.9571282749,
"f":0.9647327808
},
"Gender":{
"p":0.9395857307,
"r":0.9293370009,
"f":0.934433265
},
"Number":{
"p":0.9704791574,
"r":0.958605026,
"f":0.9645055472
},
"Mood":{
"p":0.9804511278,
"r":0.9782445611,
"f":0.9793466016
},
"Tense":{
"p":0.9808660624,
"r":0.9811130698,
"f":0.9809895505
},
"VerbForm":{
"p":0.9688061408,
"r":0.9667535854,
"f":0.9677787748
},
"Degree":{
"p":0.961950882,
"r":0.9553418069,
"f":0.9586349535
},
"PronType":{
"p":0.9900303424,
"r":0.9853321829,
"f":0.9876756757
},
"Poss":{
"p":0.996031746,
"r":0.9920948617,
"f":0.9940594059
},
"Case":{
"p":0.9927130045,
"r":0.980620155,
"f":0.9866295265
},
"Reflex":{
"p":1.0,
"r":1.0,
"f":1.0
},
"NumType":{
"p":0.9932735426,
"r":0.9115226337,
"f":0.9506437768
},
"Polarity":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Person":{
"p":0.9904942966,
"r":0.9890840057,
"f":0.9897886488
},
"Animacy":{
"p":0.9974380871,
"r":0.9948892675,
"f":0.9961620469
},
"Voice":{
"p":0.9485294118,
"r":0.9347826087,
"f":0.9416058394
},
"Abbr":{
"p":0.9776119403,
"r":0.81875,
"f":0.8911564626
}
},
"dep_las_per_type":{
"nmod":{
"p":0.7713709677,
"r":0.7836952069,
"f":0.7774842512
},
"nsubj":{
"p":0.877843565,
"r":0.8673029557,
"f":0.8725414279
},
"flat:name":{
"p":0.8354632588,
"r":0.8435483871,
"f":0.8394863563
},
"root":{
"p":0.8954166667,
"r":0.8902236951,
"f":0.8928126298
},
"advmod":{
"p":0.8278335725,
"r":0.8298178332,
"f":0.8288245152
},
"mark":{
"p":0.9202453988,
"r":0.9176863181,
"f":0.9189640769
},
"advcl":{
"p":0.6954954955,
"r":0.6620926244,
"f":0.6783831283
},
"obj":{
"p":0.8562801932,
"r":0.8796526055,
"f":0.8678090575
},
"case":{
"p":0.9334365325,
"r":0.9324742268,
"f":0.9329551315
},
"det":{
"p":0.9569892473,
"r":0.9563843236,
"f":0.9566866899
},
"obl":{
"p":0.7530459231,
"r":0.7271493213,
"f":0.7398710866
},
"aux":{
"p":0.9316546763,
"r":0.935862692,
"f":0.9337539432
},
"acl:relcl":{
"p":0.7814569536,
"r":0.7972972973,
"f":0.7892976589
},
"iobj":{
"p":0.7727272727,
"r":0.5795454545,
"f":0.6623376623
},
"xcomp":{
"p":0.6943231441,
"r":0.7210884354,
"f":0.7074527253
},
"cc":{
"p":0.9171826625,
"r":0.9129429892,
"f":0.9150579151
},
"conj":{
"p":0.6975265018,
"r":0.7157360406,
"f":0.7065139585
},
"amod":{
"p":0.9138034961,
"r":0.9171203872,
"f":0.9154589372
},
"nummod":{
"p":0.9362549801,
"r":0.9591836735,
"f":0.9475806452
},
"compound:prt":{
"p":0.8473282443,
"r":0.7985611511,
"f":0.8222222222
},
"cop":{
"p":0.8485915493,
"r":0.8607142857,
"f":0.8546099291
},
"appos":{
"p":0.2564102564,
"r":0.2,
"f":0.2247191011
},
"ccomp":{
"p":0.8086642599,
"r":0.8818897638,
"f":0.8436911488
},
"acl":{
"p":0.6428571429,
"r":0.6169354839,
"f":0.6296296296
},
"expl":{
"p":0.709273183,
"r":0.7648648649,
"f":0.7360208062
},
"csubj":{
"p":0.6796875,
"r":0.6350364964,
"f":0.6566037736
},
"nsubj:pass":{
"p":0.8787878788,
"r":0.8055555556,
"f":0.8405797101
},
"aux:pass":{
"p":0.947826087,
"r":0.9083333333,
"f":0.9276595745
},
"acl:cleft":{
"p":0.5714285714,
"r":0.5925925926,
"f":0.5818181818
},
"orphan":{
"p":0.1111111111,
"r":0.0384615385,
"f":0.0571428571
},
"dep":{
"p":0.0,
"r":0.0,
"f":0.0
},
"goeswith":{
"p":0.0,
"r":0.0,
"f":0.0
},
"parataxis":{
"p":0.8187919463,
"r":0.6455026455,
"f":0.7218934911
},
"compound":{
"p":0.8823529412,
"r":0.3191489362,
"f":0.46875
},
"flat:foreign":{
"p":0.5384615385,
"r":0.2258064516,
"f":0.3181818182
},
"discourse":{
"p":0.4166666667,
"r":0.2173913043,
"f":0.2857142857
},
"csubj:pass":{
"p":0.0,
"r":0.0,
"f":0.0
},
"neg":{
"p":0.0,
"r":0.0,
"f":0.0
},
"dobj":{
"p":0.0,
"r":0.0,
"f":0.0
},
"name":{
"p":0.0,
"r":0.0,
"f":0.0
}
},
"ents_per_type":{
"PER":{
"p":0.8318584071,
"r":0.7679738562,
"f":0.7986406117
},
"MISC":{
"p":0.670995671,
"r":0.62,
"f":0.6444906445
},
"LOC":{
"p":0.8294797688,
"r":0.7798913043,
"f":0.8039215686
},
"ORG":{
"p":0.7363083164,
"r":0.7891304348,
"f":0.7618048269
},
"GPE_LOC":{
"p":0.0,
"r":0.0,
"f":0.0
}
}
},
"sources":[
{
"name":"UD Norwegian Bokmaal (from NorNE)",
"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: 5e4059dc)",
"url":"https://github.com/ltgoslo/norne",
"license":"Public Domain (CC0)",
"author":"Language Technology Group (University of Oslo)"
},
{
"name":"Norsk Ordbank in Norwegian Bokm\u00e5l",
"url":"https://www.nb.no/sprakbanken/show?serial=oai%3Anb.no%3Asbr-5&lang=en",
"license":"CC BY 4.0",
"author":"CLARINO NB - Spr\u00e5kbanken, Nasjonalbiblioteket, Norway"
}
],
"requirements":[
]
}