nb_core_news_md / meta.json
osanseviero's picture
Update spaCy pipeline
be9cea1
raw
history blame
19.4 kB
{
"lang":"nb",
"name":"core_news_md",
"version":"3.1.0",
"description":"Norwegian (Bokm\u00e5l) pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, ner, attribute_ruler, lemmatizer.",
"author":"Explosion",
"email":"[email protected]",
"url":"https://explosion.ai",
"license":"MIT",
"spacy_version":">=3.1.0,<3.2.0",
"spacy_git_version":"caba63b74",
"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",
"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":0.9713020031,
"pos_acc":0.9725329219,
"morph_acc":0.9585353758,
"lemma_acc":0.7670927222,
"dep_uas":0.8928487837,
"dep_las":0.8629696667,
"ents_p":0.8454221165,
"ents_r":0.8399291199,
"ents_f":0.8426666667,
"sents_p":0.9275123558,
"sents_r":0.9328914664,
"sents_f":0.9301941347,
"speed":11023.0847447595,
"morph_per_feat":{
"Definite":{
"p":0.9795308188,
"r":0.9660882386,
"f":0.9727630903
},
"Gender":{
"p":0.9482346187,
"r":0.9399601631,
"f":0.9440792607
},
"Number":{
"p":0.9761269276,
"r":0.9646127921,
"f":0.970335704
},
"Mood":{
"p":0.9869149472,
"r":0.9807451863,
"f":0.9838203938
},
"Tense":{
"p":0.9878511769,
"r":0.9828758499,
"f":0.985357233
},
"VerbForm":{
"p":0.9754420432,
"r":0.9709908735,
"f":0.9732113688
},
"Degree":{
"p":0.9651844192,
"r":0.9618687736,
"f":0.963523744
},
"PronType":{
"p":0.9913363656,
"r":0.9872735116,
"f":0.9893007673
},
"Poss":{
"p":0.9803921569,
"r":0.9881422925,
"f":0.9842519685
},
"Case":{
"p":0.9944134078,
"r":0.9856035437,
"f":0.9899888765
},
"Reflex":{
"p":1.0,
"r":1.0,
"f":1.0
},
"NumType":{
"p":0.9977477477,
"r":0.9115226337,
"f":0.952688172
},
"Polarity":{
"p":0.9968454259,
"r":1.0,
"f":0.9984202212
},
"Person":{
"p":0.9919278253,
"r":0.9914570479,
"f":0.9916923807
},
"Animacy":{
"p":0.9982949702,
"r":0.9974446337,
"f":0.9978696208
},
"Voice":{
"p":0.9481481481,
"r":0.9275362319,
"f":0.9377289377
},
"Abbr":{
"p":0.9856115108,
"r":0.85625,
"f":0.9163879599
}
},
"dep_las_per_type":{
"nmod":{
"p":0.791230893,
"r":0.805817288,
"f":0.7984574792
},
"nsubj":{
"p":0.8978125,
"r":0.884544335,
"f":0.8911290323
},
"flat:name":{
"p":0.8628659476,
"r":0.9032258065,
"f":0.8825847124
},
"root":{
"p":0.9039101498,
"r":0.9001657001,
"f":0.902034039
},
"advmod":{
"p":0.8374642517,
"r":0.8422818792,
"f":0.8398661568
},
"mark":{
"p":0.922863485,
"r":0.924916574,
"f":0.9238888889
},
"advcl":{
"p":0.7326203209,
"r":0.704974271,
"f":0.7185314685
},
"obj":{
"p":0.8860606061,
"r":0.9069478908,
"f":0.8963825874
},
"case":{
"p":0.9372894532,
"r":0.9322164948,
"f":0.9347460912
},
"det":{
"p":0.9690851735,
"r":0.9709228824,
"f":0.9700031576
},
"obl":{
"p":0.769015399,
"r":0.7457013575,
"f":0.757178957
},
"aux":{
"p":0.9434977578,
"r":0.9503161698,
"f":0.9468946895
},
"acl:relcl":{
"p":0.8167420814,
"r":0.8130630631,
"f":0.8148984199
},
"iobj":{
"p":0.8378378378,
"r":0.7045454545,
"f":0.7654320988
},
"xcomp":{
"p":0.7213483146,
"r":0.7278911565,
"f":0.7246049661
},
"cc":{
"p":0.9218870843,
"r":0.9183359014,
"f":0.9201080664
},
"conj":{
"p":0.7308238636,
"r":0.7461928934,
"f":0.7384284177
},
"amod":{
"p":0.9412844037,
"r":0.9310344828,
"f":0.9361313869
},
"nummod":{
"p":0.9471544715,
"r":0.9510204082,
"f":0.9490835031
},
"compound:prt":{
"p":0.8287937743,
"r":0.7661870504,
"f":0.7962616822
},
"cop":{
"p":0.8684834123,
"r":0.8726190476,
"f":0.8705463183
},
"appos":{
"p":0.3164556962,
"r":0.25,
"f":0.2793296089
},
"ccomp":{
"p":0.8071428571,
"r":0.8897637795,
"f":0.8464419476
},
"expl":{
"p":0.7417721519,
"r":0.7918918919,
"f":0.7660130719
},
"csubj":{
"p":0.7666666667,
"r":0.6715328467,
"f":0.7159533074
},
"nsubj:pass":{
"p":0.9166666667,
"r":0.8148148148,
"f":0.862745098
},
"aux:pass":{
"p":0.9304347826,
"r":0.8916666667,
"f":0.9106382979
},
"acl":{
"p":0.632,
"r":0.6370967742,
"f":0.6345381526
},
"acl:cleft":{
"p":0.4615384615,
"r":0.4444444444,
"f":0.4528301887
},
"orphan":{
"p":0.0,
"r":0.0,
"f":0.0
},
"dep":{
"p":0.0,
"r":0.0,
"f":0.0
},
"parataxis":{
"p":0.8310810811,
"r":0.6507936508,
"f":0.7299703264
},
"goeswith":{
"p":0.0,
"r":0.0,
"f":0.0
},
"compound":{
"p":0.8571428571,
"r":0.2553191489,
"f":0.393442623
},
"flat:foreign":{
"p":0.75,
"r":0.5806451613,
"f":0.6545454545
},
"discourse":{
"p":0.75,
"r":0.3913043478,
"f":0.5142857143
},
"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":0.9149277689,
"r":0.931372549,
"f":0.9230769231
},
"MISC":{
"p":0.6880733945,
"r":0.6,
"f":0.641025641
},
"LOC":{
"p":0.8926553672,
"r":0.8586956522,
"f":0.8753462604
},
"ORG":{
"p":0.7926078029,
"r":0.8391304348,
"f":0.8152059134
},
"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"
},
{
"name":"Explosion fastText Vectors (cbow, OSCAR Common Crawl + Wikipedia)",
"url":"https://spacy.io",
"license":"CC0",
"author":"Explosion"
}
],
"requirements":[
]
}