da_core_news_md / meta.json
osanseviero's picture
Update spaCy pipeline
c58aec4
raw
history blame
17.2 kB
{
"lang":"da",
"name":"core_news_md",
"version":"3.2.0",
"description":"Danish pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, ner, attribute_ruler, lemmatizer.",
"author":"Explosion",
"email":"contact@explosion.ai",
"url":"https://explosion.ai",
"license":"CC BY-SA 4.0",
"spacy_version":">=3.2.0,<3.3.0",
"spacy_git_version":"bb26550e2",
"vectors":{
"width":300,
"vectors":20000,
"keys":500000,
"name":"da_vectors"
},
"labels":{
"tok2vec":[
],
"morphologizer":[
"AdpType=Prep|POS=ADP",
"Definite=Ind|Gender=Com|Number=Sing|POS=NOUN",
"Mood=Ind|POS=AUX|Tense=Pres|VerbForm=Fin|Voice=Act",
"POS=PROPN",
"Definite=Ind|Number=Sing|POS=VERB|Tense=Past|VerbForm=Part",
"Definite=Def|Gender=Neut|Number=Sing|POS=NOUN",
"POS=SCONJ",
"Definite=Def|Gender=Com|Number=Sing|POS=NOUN",
"Mood=Ind|POS=VERB|Tense=Pres|VerbForm=Fin|Voice=Act",
"POS=ADV",
"Number=Plur|POS=DET|PronType=Dem",
"Degree=Pos|Number=Plur|POS=ADJ",
"Definite=Ind|Gender=Com|Number=Plur|POS=NOUN",
"POS=PUNCT",
"POS=CCONJ",
"Definite=Ind|Degree=Cmp|Number=Sing|POS=ADJ",
"Degree=Cmp|POS=ADJ",
"POS=PRON|PartType=Inf",
"Gender=Com|Number=Sing|POS=DET|PronType=Ind",
"Definite=Ind|Degree=Pos|Number=Sing|POS=ADJ",
"Case=Acc|Gender=Neut|Number=Sing|POS=PRON|Person=3|PronType=Prs",
"Definite=Ind|Gender=Neut|Number=Plur|POS=NOUN",
"Definite=Def|Degree=Pos|Number=Sing|POS=ADJ",
"Gender=Neut|Number=Sing|POS=DET|PronType=Dem",
"Degree=Pos|POS=ADV",
"Definite=Def|Number=Sing|POS=VERB|Tense=Past|VerbForm=Part",
"Definite=Ind|Gender=Neut|Number=Sing|POS=NOUN",
"POS=PRON|PronType=Dem",
"NumType=Card|POS=NUM",
"Definite=Ind|Degree=Pos|Gender=Neut|Number=Sing|POS=ADJ",
"Case=Acc|Gender=Com|Number=Sing|POS=PRON|Person=3|PronType=Prs",
"Degree=Pos|Gender=Com|Number=Sing|POS=ADJ",
"Case=Nom|Gender=Com|Number=Sing|POS=PRON|Person=3|PronType=Prs",
"NumType=Ord|POS=ADJ",
"Gender=Com|Number=Sing|Number[psor]=Sing|POS=DET|Person=3|Poss=Yes|PronType=Prs|Reflex=Yes",
"Mood=Ind|POS=AUX|Tense=Past|VerbForm=Fin|Voice=Act",
"POS=VERB|VerbForm=Inf|Voice=Act",
"Mood=Ind|POS=VERB|Tense=Past|VerbForm=Fin|Voice=Act",
"POS=NOUN",
"Mood=Ind|POS=VERB|Tense=Pres|VerbForm=Fin|Voice=Pass",
"POS=ADP|PartType=Inf",
"Degree=Pos|POS=ADJ",
"Definite=Def|Gender=Com|Number=Plur|POS=NOUN",
"Number[psor]=Sing|POS=DET|Person=3|Poss=Yes|PronType=Prs",
"Case=Gen|Definite=Def|Gender=Com|Number=Sing|POS=NOUN",
"POS=AUX|VerbForm=Inf|Voice=Act",
"Definite=Ind|Degree=Pos|Gender=Com|Number=Sing|POS=ADJ",
"Gender=Com|Number=Sing|POS=DET|PronType=Dem",
"Number=Plur|POS=DET|PronType=Ind",
"Gender=Com|Number=Sing|POS=PRON|PronType=Ind",
"Case=Acc|POS=PRON|Person=3|PronType=Prs|Reflex=Yes",
"POS=PART|PartType=Inf",
"Gender=Neut|Number=Sing|POS=DET|PronType=Ind",
"Case=Acc|Number=Plur|POS=PRON|Person=3|PronType=Prs",
"Case=Gen|Definite=Def|Gender=Neut|Number=Sing|POS=NOUN",
"Case=Nom|Number=Plur|POS=PRON|Person=3|PronType=Prs",
"Case=Nom|Gender=Com|Number=Sing|POS=PRON|Person=1|PronType=Prs",
"Case=Nom|Gender=Com|POS=PRON|PronType=Ind",
"Gender=Neut|Number=Sing|POS=PRON|PronType=Ind",
"Mood=Imp|POS=VERB",
"Gender=Com|Number=Sing|Number[psor]=Sing|POS=DET|Person=1|Poss=Yes|PronType=Prs",
"Definite=Ind|Number=Sing|POS=AUX|Tense=Past|VerbForm=Part",
"POS=X",
"Case=Nom|Gender=Com|Number=Plur|POS=PRON|Person=1|PronType=Prs",
"Case=Gen|Definite=Def|Gender=Com|Number=Plur|POS=NOUN",
"POS=VERB|Tense=Pres|VerbForm=Part",
"Number=Plur|POS=PRON|PronType=Int,Rel",
"POS=VERB|VerbForm=Inf|Voice=Pass",
"Case=Gen|Definite=Ind|Gender=Com|Number=Sing|POS=NOUN",
"Degree=Cmp|POS=ADV",
"POS=ADV|PartType=Inf",
"Degree=Sup|POS=ADV",
"Number=Plur|POS=PRON|PronType=Dem",
"Number=Plur|POS=PRON|PronType=Ind",
"Definite=Def|Gender=Neut|Number=Plur|POS=NOUN",
"Case=Acc|Gender=Com|Number=Sing|POS=PRON|Person=1|PronType=Prs",
"Case=Gen|POS=PROPN",
"POS=ADP",
"Degree=Cmp|Number=Plur|POS=ADJ",
"Definite=Def|Degree=Sup|POS=ADJ",
"Gender=Neut|Number=Sing|Number[psor]=Sing|POS=DET|Person=1|Poss=Yes|PronType=Prs",
"Degree=Pos|Number=Sing|POS=ADJ",
"Number=Plur|Number[psor]=Sing|POS=DET|Person=3|Poss=Yes|PronType=Prs|Reflex=Yes",
"Gender=Com|Number=Sing|Number[psor]=Plur|POS=DET|Person=1|Poss=Yes|PronType=Prs|Style=Form",
"Number=Plur|POS=PRON|PronType=Rcp",
"Case=Gen|Degree=Cmp|POS=ADJ",
"Case=Gen|Definite=Def|Gender=Neut|Number=Plur|POS=NOUN",
"Number[psor]=Plur|POS=DET|Person=3|Poss=Yes|PronType=Prs",
"POS=INTJ",
"Number=Plur|Number[psor]=Sing|POS=DET|Person=1|Poss=Yes|PronType=Prs",
"Degree=Pos|Gender=Neut|Number=Sing|POS=ADJ",
"Gender=Neut|Number=Sing|Number[psor]=Plur|POS=DET|Person=1|Poss=Yes|PronType=Prs|Style=Form",
"Case=Acc|Gender=Com|Number=Sing|POS=PRON|Person=2|PronType=Prs",
"Gender=Com|Number=Sing|Number[psor]=Sing|POS=DET|Person=2|Poss=Yes|PronType=Prs",
"Case=Gen|Definite=Ind|Gender=Neut|Number=Plur|POS=NOUN",
"Number=Sing|POS=PRON|PronType=Int,Rel",
"Number=Plur|Number[psor]=Plur|POS=DET|Person=1|Poss=Yes|PronType=Prs|Style=Form",
"Gender=Neut|Number=Sing|POS=PRON|PronType=Int,Rel",
"Definite=Def|Degree=Sup|Number=Plur|POS=ADJ",
"Case=Nom|Gender=Com|Number=Sing|POS=PRON|Person=2|PronType=Prs",
"Gender=Neut|Number=Sing|Number[psor]=Sing|POS=DET|Person=3|Poss=Yes|PronType=Prs|Reflex=Yes",
"Definite=Ind|Number=Sing|POS=NOUN",
"Number=Plur|POS=VERB|Tense=Past|VerbForm=Part",
"Number=Plur|Number[psor]=Sing|POS=PRON|Person=3|Poss=Yes|PronType=Prs|Reflex=Yes",
"POS=SYM",
"Case=Nom|Gender=Com|POS=PRON|Person=2|Polite=Form|PronType=Prs",
"Degree=Sup|POS=ADJ",
"Number=Plur|POS=DET|PronType=Ind|Style=Arch",
"Case=Gen|Gender=Com|Number=Sing|POS=DET|PronType=Dem",
"Foreign=Yes|POS=X",
"POS=DET|Person=2|Polite=Form|Poss=Yes|PronType=Prs",
"Gender=Neut|Number=Sing|POS=PRON|PronType=Dem",
"Case=Acc|Gender=Com|Number=Plur|POS=PRON|Person=1|PronType=Prs",
"Case=Gen|Definite=Ind|Gender=Neut|Number=Sing|POS=NOUN",
"Case=Gen|POS=PRON|PronType=Int,Rel",
"Gender=Com|Number=Sing|POS=PRON|PronType=Dem",
"Abbr=Yes|POS=X",
"Case=Gen|Definite=Ind|Gender=Com|Number=Plur|POS=NOUN",
"Definite=Def|Degree=Abs|POS=ADJ",
"Definite=Ind|Degree=Sup|Number=Sing|POS=ADJ",
"Definite=Ind|POS=NOUN",
"Gender=Com|Number=Plur|POS=NOUN",
"Number[psor]=Plur|POS=DET|Person=1|Poss=Yes|PronType=Prs",
"Gender=Com|POS=PRON|PronType=Int,Rel",
"Case=Nom|Gender=Com|Number=Plur|POS=PRON|Person=2|PronType=Prs",
"Degree=Abs|POS=ADV",
"POS=VERB|VerbForm=Ger",
"POS=VERB|Tense=Past|VerbForm=Part",
"Definite=Def|Degree=Sup|Number=Sing|POS=ADJ",
"Number=Plur|Number[psor]=Plur|POS=PRON|Person=1|Poss=Yes|PronType=Prs|Style=Form",
"Case=Gen|Definite=Def|Degree=Pos|Number=Sing|POS=ADJ",
"Case=Gen|Degree=Pos|Number=Plur|POS=ADJ",
"Case=Acc|Gender=Com|POS=PRON|Person=2|Polite=Form|PronType=Prs",
"Gender=Com|Number=Sing|POS=PRON|PronType=Int,Rel",
"POS=VERB|Tense=Pres",
"Case=Gen|Number=Plur|POS=DET|PronType=Ind",
"Number[psor]=Plur|POS=DET|Person=2|Poss=Yes|PronType=Prs",
"POS=PRON|Person=2|Polite=Form|Poss=Yes|PronType=Prs",
"Gender=Neut|Number=Sing|Number[psor]=Sing|POS=DET|Person=2|Poss=Yes|PronType=Prs",
"POS=AUX|Tense=Pres|VerbForm=Part",
"Mood=Ind|POS=VERB|Tense=Past|VerbForm=Fin|Voice=Pass",
"Gender=Com|Number=Sing|Number[psor]=Sing|POS=PRON|Person=3|Poss=Yes|PronType=Prs|Reflex=Yes",
"Degree=Sup|Number=Plur|POS=ADJ",
"Case=Acc|Gender=Com|Number=Plur|POS=PRON|Person=2|PronType=Prs",
"Gender=Neut|Number=Sing|Number[psor]=Sing|POS=PRON|Person=3|Poss=Yes|PronType=Prs|Reflex=Yes",
"Definite=Ind|Number=Plur|POS=NOUN",
"Case=Gen|Number=Plur|POS=VERB|Tense=Past|VerbForm=Part",
"Mood=Imp|POS=AUX",
"Gender=Com|Number=Sing|Number[psor]=Sing|POS=PRON|Person=1|Poss=Yes|PronType=Prs",
"Number[psor]=Sing|POS=PRON|Person=3|Poss=Yes|PronType=Prs",
"Definite=Def|Gender=Com|Number=Sing|POS=VERB|Tense=Past|VerbForm=Part",
"Number=Plur|Number[psor]=Sing|POS=DET|Person=2|Poss=Yes|PronType=Prs",
"Case=Gen|Gender=Com|Number=Sing|POS=DET|PronType=Ind",
"Case=Gen|POS=NOUN",
"Number[psor]=Plur|POS=PRON|Person=3|Poss=Yes|PronType=Prs",
"POS=DET|PronType=Dem",
"Definite=Def|Number=Plur|POS=NOUN"
],
"parser":[
"ROOT",
"acl:relcl",
"advcl",
"advmod",
"advmod:lmod",
"amod",
"appos",
"aux",
"case",
"cc",
"ccomp",
"compound:prt",
"conj",
"cop",
"dep",
"det",
"expl",
"fixed",
"flat",
"iobj",
"list",
"mark",
"nmod",
"nmod:poss",
"nsubj",
"nummod",
"obj",
"obl",
"obl:lmod",
"obl:tmod",
"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":0.9994672349,
"token_p":0.9977732598,
"token_r":0.9974835463,
"token_f":0.997628382,
"pos_acc":0.962905569,
"morph_acc":0.9487651332,
"morph_micro_p":0.9664501066,
"morph_micro_r":0.9611327041,
"morph_micro_f":0.9637840711,
"morph_per_feat":{
"Mood":{
"p":0.9789674952,
"r":0.9761677788,
"f":0.9775656325
},
"Tense":{
"p":0.9698340875,
"r":0.968373494,
"f":0.9691032404
},
"VerbForm":{
"p":0.9631449631,
"r":0.9596083231,
"f":0.9613733906
},
"Voice":{
"p":0.9782934132,
"r":0.9768310912,
"f":0.9775617053
},
"Definite":{
"p":0.9633027523,
"r":0.9541683129,
"f":0.9587137753
},
"Gender":{
"p":0.9459098497,
"r":0.9415088069,
"f":0.9437041972
},
"Number":{
"p":0.9618621778,
"r":0.9538341158,
"f":0.9578313253
},
"AdpType":{
"p":0.9973333333,
"r":0.9920424403,
"f":0.9946808511
},
"PartType":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Case":{
"p":0.9696485623,
"r":0.9589257504,
"f":0.9642573471
},
"Person":{
"p":0.9704347826,
"r":0.9911190053,
"f":0.9806678383
},
"PronType":{
"p":0.9811165846,
"r":0.9827302632,
"f":0.9819227609
},
"NumType":{
"p":0.9794520548,
"r":0.9470198675,
"f":0.962962963
},
"Degree":{
"p":0.9520295203,
"r":0.9325301205,
"f":0.942178941
},
"Reflex":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Number[psor]":{
"p":0.9662921348,
"r":1.0,
"f":0.9828571429
},
"Poss":{
"p":0.9777777778,
"r":1.0,
"f":0.9887640449
},
"Foreign":{
"p":0.6666666667,
"r":0.4,
"f":0.5
},
"Abbr":{
"p":0.0,
"r":0.0,
"f":0.0
},
"Style":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Polite":{
"p":1.0,
"r":0.75,
"f":0.8571428571
}
},
"sents_p":0.908438061,
"sents_r":0.8971631206,
"sents_f":0.902765388,
"dep_uas":0.8220632614,
"dep_las":0.7813355686,
"dep_las_per_type":{
"advmod":{
"p":0.7073509015,
"r":0.7203389831,
"f":0.7137858642
},
"root":{
"p":0.8411552347,
"r":0.8262411348,
"f":0.8336314848
},
"nsubj":{
"p":0.8428417653,
"r":0.8259493671,
"f":0.8343100693
},
"case":{
"p":0.881372549,
"r":0.8865877712,
"f":0.883972468
},
"obl":{
"p":0.7053291536,
"r":0.698757764,
"f":0.7020280811
},
"cc":{
"p":0.7851002865,
"r":0.7965116279,
"f":0.7907647908
},
"conj":{
"p":0.6491712707,
"r":0.6266666667,
"f":0.6377204885
},
"obj":{
"p":0.8033088235,
"r":0.8485436893,
"f":0.8253068933
},
"aux":{
"p":0.875739645,
"r":0.8629737609,
"f":0.8693098385
},
"acl:relcl":{
"p":0.5879120879,
"r":0.5783783784,
"f":0.583106267
},
"advmod:lmod":{
"p":0.7586206897,
"r":0.6567164179,
"f":0.704
},
"det":{
"p":0.9194078947,
"r":0.92092257,
"f":0.9201646091
},
"amod":{
"p":0.8193979933,
"r":0.8361774744,
"f":0.8277027027
},
"nmod:poss":{
"p":0.7340425532,
"r":0.6831683168,
"f":0.7076923077
},
"ccomp":{
"p":0.5652173913,
"r":0.6290322581,
"f":0.5954198473
},
"nummod":{
"p":0.8306451613,
"r":0.8583333333,
"f":0.8442622951
},
"flat":{
"p":0.7636363636,
"r":0.8344370861,
"f":0.7974683544
},
"compound:prt":{
"p":0.5,
"r":0.3170731707,
"f":0.3880597015
},
"advcl":{
"p":0.6339285714,
"r":0.6120689655,
"f":0.6228070175
},
"mark":{
"p":0.8905579399,
"r":0.8521560575,
"f":0.870933893
},
"cop":{
"p":0.7837837838,
"r":0.8285714286,
"f":0.8055555556
},
"dep":{
"p":0.1555555556,
"r":0.2641509434,
"f":0.1958041958
},
"nmod":{
"p":0.6352941176,
"r":0.6328125,
"f":0.6340508806
},
"iobj":{
"p":0.8125,
"r":0.5909090909,
"f":0.6842105263
},
"xcomp":{
"p":0.5675675676,
"r":0.3559322034,
"f":0.4375
},
"list":{
"p":0.4,
"r":0.2222222222,
"f":0.2857142857
},
"vocative":{
"p":0.0,
"r":0.0,
"f":0.0
},
"fixed":{
"p":0.8918918919,
"r":0.8048780488,
"f":0.8461538462
},
"expl":{
"p":0.8484848485,
"r":0.8235294118,
"f":0.8358208955
},
"appos":{
"p":0.4146341463,
"r":0.5151515152,
"f":0.4594594595
},
"obl:tmod":{
"p":0.6,
"r":0.3333333333,
"f":0.4285714286
},
"discourse":{
"p":0.0,
"r":0.0,
"f":0.0
},
"obl:lmod":{
"p":0.0,
"r":0.0,
"f":0.0
}
},
"tag_acc":0.962905569,
"lemma_acc":0.8491041162,
"ents_p":0.8075313808,
"ents_r":0.8041666667,
"ents_f":0.8058455115,
"ents_per_type":{
"PER":{
"p":0.9215686275,
"r":0.8493975904,
"f":0.8840125392
},
"ORG":{
"p":0.7032967033,
"r":0.7111111111,
"f":0.7071823204
},
"MISC":{
"p":0.7179487179,
"r":0.7433628319,
"f":0.7304347826
},
"LOC":{
"p":0.8290598291,
"r":0.8738738739,
"f":0.850877193
}
},
"speed":10055.5372609128
},
"sources":[
{
"name":"UD Danish DDT v2.8",
"url":"https://github.com/UniversalDependencies/UD_Danish-DDT",
"license":"CC BY-SA 4.0",
"author":"Johannsen, Anders; Mart\u00ednez Alonso, H\u00e9ctor; Plank, Barbara"
},
{
"name":"DaNE",
"url":"https://github.com/alexandrainst/danlp/blob/master/docs/datasets.md#danish-dependency-treebank-dane",
"license":"CC BY-SA 4.0",
"author":"Rasmus Hvingelby, Amalie B. Pauli, Maria Barrett, Christina Rosted, Lasse M. Lidegaard, Anders S\u00f8gaard"
},
{
"name":"Lemmatization Lists",
"url":"https://github.com/michmech/lemmatization-lists/",
"license":"ODbL",
"author":"Michal M\u011bchura"
},
{
"name":"Explosion fastText Vectors (cbow, OSCAR Common Crawl + Wikipedia)",
"url":"https://spacy.io",
"license":"CC0",
"author":"Explosion"
}
],
"requirements":[
]
}