da_core_news_md / meta.json
Adriane Boyd
Update spaCy pipeline
2230db5
raw
history blame
17 kB
{
"lang":"da",
"name":"core_news_md",
"version":"3.4.0",
"description":"Danish pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, lemmatizer (trainable_lemmatizer), senter, ner, attribute_ruler.",
"author":"Explosion",
"email":"contact@explosion.ai",
"url":"https://explosion.ai",
"license":"CC BY-SA 4.0",
"spacy_version":">=3.4.0,<3.5.0",
"spacy_git_version":"dd038b536",
"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",
"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":0.9618401937,
"morph_acc":0.948377724,
"morph_micro_p":0.9675176369,
"morph_micro_r":0.9622431982,
"morph_micro_f":0.9648732095,
"morph_per_feat":{
"Mood":{
"p":0.9799235182,
"r":0.9771210677,
"f":0.9785202864
},
"Tense":{
"p":0.9743396226,
"r":0.9721385542,
"f":0.973237844
},
"VerbForm":{
"p":0.9643953346,
"r":0.9614443084,
"f":0.9629175605
},
"Voice":{
"p":0.976083707,
"r":0.976083707,
"f":0.976083707
},
"Definite":{
"p":0.9622716442,
"r":0.9573291189,
"f":0.9597940186
},
"Gender":{
"p":0.9466310874,
"r":0.9431704885,
"f":0.9448976194
},
"Number":{
"p":0.9613361389,
"r":0.9533124674,
"f":0.9573074908
},
"AdpType":{
"p":0.9982206406,
"r":0.9920424403,
"f":0.9951219512
},
"PartType":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Case":{
"p":0.9741935484,
"r":0.9541864139,
"f":0.9640861931
},
"Person":{
"p":0.9788732394,
"r":0.9875666075,
"f":0.9832007073
},
"PronType":{
"p":0.9860197368,
"r":0.9860197368,
"f":0.9860197368
},
"NumType":{
"p":0.9931034483,
"r":0.9536423841,
"f":0.972972973
},
"Degree":{
"p":0.9545454545,
"r":0.9361445783,
"f":0.9452554745
},
"Reflex":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Number[psor]":{
"p":0.9772727273,
"r":1.0,
"f":0.9885057471
},
"Poss":{
"p":0.9887640449,
"r":1.0,
"f":0.9943502825
},
"Foreign":{
"p":0.5,
"r":0.4,
"f":0.4444444444
},
"Abbr":{
"p":0.0,
"r":0.0,
"f":0.0
},
"Style":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Polite":{
"p":0.75,
"r":0.75,
"f":0.75
}
},
"sents_p":0.9202898551,
"sents_r":0.9007092199,
"sents_f":0.9103942652,
"dep_uas":0.8215642458,
"dep_las":0.7802234637,
"dep_las_per_type":{
"advmod":{
"p":0.7128851541,
"r":0.7189265537,
"f":0.7158931083
},
"root":{
"p":0.8483754513,
"r":0.8333333333,
"f":0.8407871199
},
"nsubj":{
"p":0.8333333333,
"r":0.8333333333,
"f":0.8333333333
},
"case":{
"p":0.8933859822,
"r":0.892504931,
"f":0.8929452393
},
"obl":{
"p":0.6905901116,
"r":0.6723602484,
"f":0.6813532651
},
"cc":{
"p":0.7803468208,
"r":0.7848837209,
"f":0.7826086957
},
"conj":{
"p":0.6422764228,
"r":0.632,
"f":0.6370967742
},
"obj":{
"p":0.7892791128,
"r":0.8291262136,
"f":0.8087121212
},
"aux":{
"p":0.8858858859,
"r":0.860058309,
"f":0.8727810651
},
"acl:relcl":{
"p":0.5837837838,
"r":0.5837837838,
"f":0.5837837838
},
"advmod:lmod":{
"p":0.7164179104,
"r":0.7164179104,
"f":0.7164179104
},
"det":{
"p":0.9126853377,
"r":0.9126853377,
"f":0.9126853377
},
"amod":{
"p":0.8155668359,
"r":0.8225255973,
"f":0.8190314359
},
"nmod:poss":{
"p":0.6730769231,
"r":0.6930693069,
"f":0.6829268293
},
"ccomp":{
"p":0.5967741935,
"r":0.5967741935,
"f":0.5967741935
},
"nummod":{
"p":0.8416666667,
"r":0.8416666667,
"f":0.8416666667
},
"flat":{
"p":0.765060241,
"r":0.8410596026,
"f":0.8012618297
},
"compound:prt":{
"p":0.625,
"r":0.3658536585,
"f":0.4615384615
},
"advcl":{
"p":0.6126126126,
"r":0.5862068966,
"f":0.5991189427
},
"mark":{
"p":0.8553719008,
"r":0.8501026694,
"f":0.8527291452
},
"cop":{
"p":0.825136612,
"r":0.8628571429,
"f":0.843575419
},
"dep":{
"p":0.1875,
"r":0.2830188679,
"f":0.2255639098
},
"nmod":{
"p":0.6581532417,
"r":0.654296875,
"f":0.6562193928
},
"iobj":{
"p":0.7692307692,
"r":0.4545454545,
"f":0.5714285714
},
"xcomp":{
"p":0.4705882353,
"r":0.406779661,
"f":0.4363636364
},
"list":{
"p":0.4615384615,
"r":0.3333333333,
"f":0.3870967742
},
"vocative":{
"p":0.0,
"r":0.0,
"f":0.0
},
"fixed":{
"p":0.9166666667,
"r":0.8048780488,
"f":0.8571428571
},
"expl":{
"p":0.8,
"r":0.8235294118,
"f":0.8115942029
},
"appos":{
"p":0.4166666667,
"r":0.4545454545,
"f":0.4347826087
},
"obl:tmod":{
"p":0.75,
"r":0.3333333333,
"f":0.4615384615
},
"discourse":{
"p":0.0,
"r":0.0,
"f":0.0
},
"obl:lmod":{
"p":0.0,
"r":0.0,
"f":0.0
}
},
"lemma_acc":0.9497336562,
"tag_acc":0.9618401937,
"ents_p":0.8063829787,
"ents_r":0.7895833333,
"ents_f":0.7978947368,
"ents_per_type":{
"PER":{
"p":0.8924050633,
"r":0.8493975904,
"f":0.8703703704
},
"ORG":{
"p":0.7073170732,
"r":0.6444444444,
"f":0.6744186047
},
"MISC":{
"p":0.7142857143,
"r":0.7079646018,
"f":0.7111111111
},
"LOC":{
"p":0.8474576271,
"r":0.9009009009,
"f":0.8733624454
}
},
"speed":12214.1305450038
},
"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":"Explosion fastText Vectors (cbow, OSCAR Common Crawl + Wikipedia)",
"url":"https://spacy.io",
"license":"CC0",
"author":"Explosion"
}
],
"requirements":[
]
}