da_core_news_sm / meta.json
osanseviero's picture
osanseviero HF staff
Update spaCy pipeline
ddcdcad
{
"lang":"da",
"name":"core_news_sm",
"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":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",
"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":0.9507990315,
"morph_acc":0.9371428571,
"morph_micro_p":0.9563225412,
"morph_micro_r":0.9482610671,
"morph_micro_f":0.9522747434,
"morph_per_feat":{
"Mood":{
"p":0.9639468691,
"r":0.9685414681,
"f":0.9662387066
},
"Tense":{
"p":0.9529147982,
"r":0.9600903614,
"f":0.9564891223
},
"VerbForm":{
"p":0.9471419791,
"r":0.9430844553,
"f":0.9451088623
},
"Voice":{
"p":0.968492123,
"r":0.9648729447,
"f":0.9666791464
},
"Definite":{
"p":0.9468212715,
"r":0.9355985776,
"f":0.9411764706
},
"Gender":{
"p":0.9299128102,
"r":0.9215686275,
"f":0.9257219162
},
"Number":{
"p":0.9519535375,
"r":0.9405320814,
"f":0.9462083443
},
"AdpType":{
"p":1.0,
"r":0.9840848806,
"f":0.9919786096
},
"PartType":{
"p":1.0,
"r":0.9967532468,
"f":0.9983739837
},
"Case":{
"p":0.9727126806,
"r":0.9573459716,
"f":0.9649681529
},
"Person":{
"p":0.9770723104,
"r":0.9840142096,
"f":0.9805309735
},
"PronType":{
"p":0.9826875515,
"r":0.9802631579,
"f":0.9814738576
},
"NumType":{
"p":0.9793103448,
"r":0.940397351,
"f":0.9594594595
},
"Degree":{
"p":0.9402985075,
"r":0.9108433735,
"f":0.9253365973
},
"Reflex":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Polite":{
"p":0.75,
"r":0.75,
"f":0.75
},
"Number[psor]":{
"p":0.9885057471,
"r":1.0,
"f":0.9942196532
},
"Poss":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Foreign":{
"p":0.8333333333,
"r":0.5,
"f":0.625
},
"Abbr":{
"p":1.0,
"r":0.2,
"f":0.3333333333
},
"Style":{
"p":1.0,
"r":1.0,
"f":1.0
}
},
"sents_p":0.9045045045,
"sents_r":0.890070922,
"sents_f":0.8972296693,
"dep_uas":0.8070861741,
"dep_las":0.7640549905,
"dep_las_per_type":{
"advmod":{
"p":0.6948682386,
"r":0.7076271186,
"f":0.7011896431
},
"root":{
"p":0.8078994614,
"r":0.7978723404,
"f":0.8028545941
},
"nsubj":{
"p":0.8367129136,
"r":0.8270042194,
"f":0.8318302387
},
"case":{
"p":0.8841584158,
"r":0.8806706114,
"f":0.8824110672
},
"obl":{
"p":0.6810207337,
"r":0.6630434783,
"f":0.6719118804
},
"cc":{
"p":0.7620396601,
"r":0.7819767442,
"f":0.7718794835
},
"conj":{
"p":0.6066481994,
"r":0.584,
"f":0.5951086957
},
"obj":{
"p":0.7678244973,
"r":0.8155339806,
"f":0.790960452
},
"aux":{
"p":0.875,
"r":0.8571428571,
"f":0.8659793814
},
"acl:relcl":{
"p":0.5852272727,
"r":0.5567567568,
"f":0.5706371191
},
"advmod:lmod":{
"p":0.7042253521,
"r":0.7462686567,
"f":0.7246376812
},
"det":{
"p":0.903814262,
"r":0.8978583196,
"f":0.9008264463
},
"amod":{
"p":0.7807757167,
"r":0.7901023891,
"f":0.7854113656
},
"nmod:poss":{
"p":0.7083333333,
"r":0.6732673267,
"f":0.6903553299
},
"ccomp":{
"p":0.6212121212,
"r":0.6612903226,
"f":0.640625
},
"nummod":{
"p":0.7868852459,
"r":0.8,
"f":0.7933884298
},
"flat":{
"p":0.7804878049,
"r":0.8476821192,
"f":0.8126984127
},
"compound:prt":{
"p":0.652173913,
"r":0.3658536585,
"f":0.46875
},
"advcl":{
"p":0.6339285714,
"r":0.6120689655,
"f":0.6228070175
},
"mark":{
"p":0.8773784355,
"r":0.8521560575,
"f":0.8645833333
},
"cop":{
"p":0.7700534759,
"r":0.8228571429,
"f":0.7955801105
},
"dep":{
"p":0.1647058824,
"r":0.2641509434,
"f":0.2028985507
},
"nmod":{
"p":0.6058252427,
"r":0.609375,
"f":0.6075949367
},
"iobj":{
"p":0.8181818182,
"r":0.4090909091,
"f":0.5454545455
},
"xcomp":{
"p":0.431372549,
"r":0.3728813559,
"f":0.4
},
"list":{
"p":0.3,
"r":0.1666666667,
"f":0.2142857143
},
"vocative":{
"p":0.0,
"r":0.0,
"f":0.0
},
"fixed":{
"p":0.85,
"r":0.8292682927,
"f":0.8395061728
},
"obl:lmod":{
"p":0.0,
"r":0.0,
"f":0.0
},
"expl":{
"p":0.7941176471,
"r":0.7941176471,
"f":0.7941176471
},
"appos":{
"p":0.4333333333,
"r":0.3939393939,
"f":0.4126984127
},
"obl:tmod":{
"p":0.8571428571,
"r":0.3333333333,
"f":0.48
},
"discourse":{
"p":0.0,
"r":0.0,
"f":0.0
}
},
"tag_acc":0.9507990315,
"lemma_acc":0.8491041162,
"ents_p":0.7682119205,
"ents_r":0.725,
"ents_f":0.7459807074,
"ents_per_type":{
"PER":{
"p":0.8089171975,
"r":0.765060241,
"f":0.786377709
},
"ORG":{
"p":0.7215189873,
"r":0.6333333333,
"f":0.674556213
},
"MISC":{
"p":0.6782608696,
"r":0.6902654867,
"f":0.6842105263
},
"LOC":{
"p":0.8431372549,
"r":0.7747747748,
"f":0.8075117371
}
},
"speed":10057.2129225514
},
"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"
}
],
"requirements":[
]
}