da_core_news_sm / meta.json
osanseviero's picture
Update spaCy pipeline
99ef642
raw
history blame
16.8 kB
{
"lang":"da",
"name":"core_news_sm",
"version":"3.4.0",
"description":"Danish pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, lemmatizer (trainable_lemmatizer), senter, ner, attribute_ruler.",
"author":"Explosion",
"email":"[email protected]",
"url":"https://explosion.ai",
"license":"CC BY-SA 4.0",
"spacy_version":">=3.4.0,<3.5.0",
"spacy_git_version":"dd038b536",
"vectors":{
"width":0,
"vectors":0,
"keys":0,
"name":null
},
"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",
"POS=SPACE",
"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"
],
"attribute_ruler":[
],
"ner":[
"LOC",
"MISC",
"ORG",
"PER"
]
},
"pipeline":[
"tok2vec",
"morphologizer",
"parser",
"lemmatizer",
"attribute_ruler",
"ner"
],
"components":[
"tok2vec",
"morphologizer",
"parser",
"lemmatizer",
"senter",
"attribute_ruler",
"ner"
],
"disabled":[
"senter"
],
"performance":{
"token_acc":0.9994672349,
"token_p":0.9977732598,
"token_r":0.9974835463,
"token_f":0.997628382,
"pos_acc":0.9498765073,
"morph_acc":0.9343341404,
"morph_micro_p":0.9571895091,
"morph_micro_r":0.9468981879,
"morph_micro_f":0.9520160369,
"morph_per_feat":{
"Mood":{
"p":0.9656160458,
"r":0.9637750238,
"f":0.9646946565
},
"Tense":{
"p":0.9488721805,
"r":0.9503012048,
"f":0.949586155
},
"VerbForm":{
"p":0.9404176904,
"r":0.9369645043,
"f":0.9386879215
},
"Voice":{
"p":0.9699924981,
"r":0.966367713,
"f":0.9681767128
},
"Definite":{
"p":0.9533574588,
"r":0.9367838799,
"f":0.9449980072
},
"Gender":{
"p":0.9351914036,
"r":0.9255566633,
"f":0.9303490897
},
"Number":{
"p":0.9526455026,
"r":0.9392279604,
"f":0.9458891516
},
"AdpType":{
"p":0.9982046679,
"r":0.9832007073,
"f":0.9906458797
},
"PartType":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Case":{
"p":0.9710144928,
"r":0.9526066351,
"f":0.961722488
},
"Person":{
"p":0.9735449735,
"r":0.9804618117,
"f":0.9769911504
},
"PronType":{
"p":0.9810231023,
"r":0.9777960526,
"f":0.9794069193
},
"NumType":{
"p":0.9930555556,
"r":0.9470198675,
"f":0.9694915254
},
"Degree":{
"p":0.94375,
"r":0.9096385542,
"f":0.9263803681
},
"Reflex":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Number[psor]":{
"p":0.9885057471,
"r":1.0,
"f":0.9942196532
},
"Poss":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Polite":{
"p":0.6,
"r":0.75,
"f":0.6666666667
},
"Foreign":{
"p":0.5,
"r":0.3,
"f":0.375
},
"Abbr":{
"p":0.0,
"r":0.0,
"f":0.0
},
"Style":{
"p":1.0,
"r":1.0,
"f":1.0
}
},
"sents_p":0.8961748634,
"sents_r":0.8723404255,
"sents_f":0.884097035,
"dep_uas":0.7988826816,
"dep_las":0.752849162,
"dep_las_per_type":{
"advmod":{
"p":0.6567967699,
"r":0.6892655367,
"f":0.6726395589
},
"root":{
"p":0.8094373866,
"r":0.7907801418,
"f":0.8
},
"nsubj":{
"p":0.8292682927,
"r":0.8248945148,
"f":0.8270756214
},
"case":{
"p":0.8843873518,
"r":0.882642998,
"f":0.8835143139
},
"obl":{
"p":0.666136725,
"r":0.650621118,
"f":0.6582875098
},
"cc":{
"p":0.7679083095,
"r":0.7790697674,
"f":0.7734487734
},
"conj":{
"p":0.5661971831,
"r":0.536,
"f":0.5506849315
},
"obj":{
"p":0.7509090909,
"r":0.8019417476,
"f":0.7755868545
},
"aux":{
"p":0.8475073314,
"r":0.8425655977,
"f":0.8450292398
},
"acl:relcl":{
"p":0.5414364641,
"r":0.5297297297,
"f":0.5355191257
},
"advmod:lmod":{
"p":0.676056338,
"r":0.7164179104,
"f":0.6956521739
},
"det":{
"p":0.8937908497,
"r":0.9011532125,
"f":0.8974569319
},
"amod":{
"p":0.7895622896,
"r":0.8003412969,
"f":0.7949152542
},
"nmod:poss":{
"p":0.6060606061,
"r":0.5940594059,
"f":0.6
},
"ccomp":{
"p":0.5588235294,
"r":0.6129032258,
"f":0.5846153846
},
"nummod":{
"p":0.8487394958,
"r":0.8416666667,
"f":0.8451882845
},
"flat":{
"p":0.75625,
"r":0.8013245033,
"f":0.7781350482
},
"compound:prt":{
"p":0.4285714286,
"r":0.2195121951,
"f":0.2903225806
},
"advcl":{
"p":0.5727272727,
"r":0.5431034483,
"f":0.5575221239
},
"mark":{
"p":0.8426501035,
"r":0.8357289528,
"f":0.8391752577
},
"cop":{
"p":0.7526315789,
"r":0.8171428571,
"f":0.7835616438
},
"dep":{
"p":0.1397849462,
"r":0.2452830189,
"f":0.1780821918
},
"nmod":{
"p":0.614,
"r":0.599609375,
"f":0.6067193676
},
"iobj":{
"p":0.75,
"r":0.4090909091,
"f":0.5294117647
},
"xcomp":{
"p":0.5625,
"r":0.3050847458,
"f":0.3956043956
},
"list":{
"p":0.4,
"r":0.2222222222,
"f":0.2857142857
},
"vocative":{
"p":0.0,
"r":0.0,
"f":0.0
},
"fixed":{
"p":0.8888888889,
"r":0.7804878049,
"f":0.8311688312
},
"expl":{
"p":0.8529411765,
"r":0.8529411765,
"f":0.8529411765
},
"appos":{
"p":0.6153846154,
"r":0.4848484848,
"f":0.5423728814
},
"obl:tmod":{
"p":0.625,
"r":0.2777777778,
"f":0.3846153846
},
"discourse":{
"p":0.0,
"r":0.0,
"f":0.0
},
"obl:lmod":{
"p":0.0,
"r":0.0,
"f":0.0
}
},
"lemma_acc":0.9449878935,
"tag_acc":0.9498765073,
"ents_p":0.7570498915,
"ents_r":0.7270833333,
"ents_f":0.7417640808,
"ents_per_type":{
"PER":{
"p":0.8322580645,
"r":0.7771084337,
"f":0.8037383178
},
"ORG":{
"p":0.6630434783,
"r":0.6777777778,
"f":0.6703296703
},
"MISC":{
"p":0.6788990826,
"r":0.6548672566,
"f":0.6666666667
},
"LOC":{
"p":0.8095238095,
"r":0.7657657658,
"f":0.787037037
}
},
"speed":13598.0305859988
},
"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"
}
],
"requirements":[
]
}