da_core_news_trf / meta.json
EC2 Default User
Update spaCy pipeline
cc45a23
raw
history blame
No virus
17 kB
{
"lang":"da",
"name":"core_news_trf",
"version":"3.3.0",
"description":"Danish transformer pipeline (Maltehb/danish-bert-botxo). Components: transformer, morphologizer, parser, lemmatizer (trainable_lemmatizer), ner, attribute_ruler.",
"author":"Explosion",
"email":"contact@explosion.ai",
"url":"https://explosion.ai",
"license":"CC BY-SA 4.0",
"spacy_version":">=3.3.0.dev0,<3.4.0",
"spacy_git_version":"849bef2de",
"vectors":{
"width":0,
"vectors":0,
"keys":0,
"name":null
},
"labels":{
"transformer":[
],
"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"
],
"attribute_ruler":[
],
"ner":[
"LOC",
"MISC",
"ORG",
"PER"
]
},
"pipeline":[
"transformer",
"morphologizer",
"parser",
"lemmatizer",
"attribute_ruler",
"ner"
],
"components":[
"transformer",
"morphologizer",
"parser",
"lemmatizer",
"attribute_ruler",
"ner"
],
"disabled":[
],
"performance":{
"token_acc":0.9994672349,
"token_p":0.9977732598,
"token_r":0.9974835463,
"token_f":0.997628382,
"pos_acc":0.9763184658,
"morph_acc":0.97360647,
"morph_micro_p":0.9874911014,
"morph_micro_r":0.98026349,
"morph_micro_f":0.9838640221,
"morph_per_feat":{
"Mood":{
"p":0.9942638623,
"r":0.9914204004,
"f":0.9928400955
},
"Tense":{
"p":0.9826415094,
"r":0.9804216867,
"f":0.981530343
},
"VerbForm":{
"p":0.9840196681,
"r":0.9798041616,
"f":0.9819073904
},
"Voice":{
"p":0.9940074906,
"r":0.9917787743,
"f":0.9928918818
},
"Definite":{
"p":0.9900039984,
"r":0.9782694587,
"f":0.9841017488
},
"Gender":{
"p":0.979516454,
"r":0.9694250582,
"f":0.97444463
},
"Number":{
"p":0.9889473684,
"r":0.9801773605,
"f":0.9845428347
},
"AdpType":{
"p":0.996460177,
"r":0.9955791335,
"f":0.9960194604
},
"PartType":{
"p":1.0,
"r":0.9967532468,
"f":0.9983739837
},
"Case":{
"p":0.992,
"r":0.9794628752,
"f":0.9856915739
},
"Person":{
"p":0.9857397504,
"r":0.9822380107,
"f":0.9839857651
},
"PronType":{
"p":0.9925619835,
"r":0.9876644737,
"f":0.9901071723
},
"NumType":{
"p":0.9865771812,
"r":0.9735099338,
"f":0.98
},
"Degree":{
"p":0.9732685298,
"r":0.965060241,
"f":0.9691470054
},
"Reflex":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Polite":{
"p":0.0,
"r":0.0,
"f":0.0
},
"Number[psor]":{
"p":0.9770114943,
"r":0.988372093,
"f":0.9826589595
},
"Poss":{
"p":1.0,
"r":0.9886363636,
"f":0.9942857143
},
"Foreign":{
"p":1.0,
"r":0.6,
"f":0.75
},
"Abbr":{
"p":0.75,
"r":0.6,
"f":0.6666666667
},
"Style":{
"p":1.0,
"r":1.0,
"f":1.0
}
},
"sents_p":0.8661971831,
"sents_r":0.8723404255,
"sents_f":0.8692579505,
"dep_uas":0.8620092701,
"dep_las":0.8339289703,
"dep_las_per_type":{
"advmod":{
"p":0.7837078652,
"r":0.7881355932,
"f":0.785915493
},
"root":{
"p":0.8533568905,
"r":0.8563829787,
"f":0.8548672566
},
"nsubj":{
"p":0.8970588235,
"r":0.9008438819,
"f":0.8989473684
},
"case":{
"p":0.9159248269,
"r":0.9132149901,
"f":0.9145679012
},
"obl":{
"p":0.7840375587,
"r":0.7779503106,
"f":0.7809820733
},
"cc":{
"p":0.8529411765,
"r":0.8430232558,
"f":0.8479532164
},
"conj":{
"p":0.7260273973,
"r":0.7066666667,
"f":0.7162162162
},
"obj":{
"p":0.8733944954,
"r":0.9242718447,
"f":0.8981132075
},
"aux":{
"p":0.8837209302,
"r":0.8862973761,
"f":0.885007278
},
"acl:relcl":{
"p":0.7428571429,
"r":0.7027027027,
"f":0.7222222222
},
"advmod:lmod":{
"p":0.7878787879,
"r":0.776119403,
"f":0.7819548872
},
"det":{
"p":0.9169381107,
"r":0.9275123558,
"f":0.9221949222
},
"amod":{
"p":0.8605442177,
"r":0.8634812287,
"f":0.8620102215
},
"nmod:poss":{
"p":0.7741935484,
"r":0.7128712871,
"f":0.7422680412
},
"ccomp":{
"p":0.6721311475,
"r":0.6612903226,
"f":0.6666666667
},
"nummod":{
"p":0.8130081301,
"r":0.8333333333,
"f":0.8230452675
},
"flat":{
"p":0.825,
"r":0.8741721854,
"f":0.8488745981
},
"compound:prt":{
"p":0.65625,
"r":0.512195122,
"f":0.5753424658
},
"advcl":{
"p":0.6890756303,
"r":0.7068965517,
"f":0.6978723404
},
"mark":{
"p":0.9089026915,
"r":0.9014373717,
"f":0.9051546392
},
"cop":{
"p":0.8532608696,
"r":0.8971428571,
"f":0.8746518106
},
"dep":{
"p":0.2197802198,
"r":0.3773584906,
"f":0.2777777778
},
"nmod":{
"p":0.7321063395,
"r":0.69921875,
"f":0.7152847153
},
"iobj":{
"p":0.9375,
"r":0.6818181818,
"f":0.7894736842
},
"obl:lmod":{
"p":0.0,
"r":0.0,
"f":0.0
},
"xcomp":{
"p":0.5102040816,
"r":0.4237288136,
"f":0.462962963
},
"list":{
"p":0.5,
"r":0.2222222222,
"f":0.3076923077
},
"vocative":{
"p":0.0,
"r":0.0,
"f":0.0
},
"fixed":{
"p":0.9166666667,
"r":0.8048780488,
"f":0.8571428571
},
"expl":{
"p":0.9117647059,
"r":0.9117647059,
"f":0.9117647059
},
"appos":{
"p":0.6,
"r":0.6363636364,
"f":0.6176470588
},
"obl:tmod":{
"p":0.8,
"r":0.4444444444,
"f":0.5714285714
},
"discourse":{
"p":0.0,
"r":0.0,
"f":0.0
}
},
"lemma_acc":0.9458595642,
"tag_acc":0.9763184658,
"ents_p":0.8106995885,
"ents_r":0.8208333333,
"ents_f":0.8157349896,
"ents_per_type":{
"PER":{
"p":0.8841463415,
"r":0.8734939759,
"f":0.8787878788
},
"ORG":{
"p":0.7093023256,
"r":0.6777777778,
"f":0.6931818182
},
"MISC":{
"p":0.7272727273,
"r":0.7787610619,
"f":0.7521367521
},
"LOC":{
"p":0.8695652174,
"r":0.9009009009,
"f":0.8849557522
}
},
"speed":451.6438624119
},
"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":"Maltehb/danish-bert-botxo",
"author":"BotXO.ai",
"url":"https://huggingface.co/Maltehb/danish-bert-botxo",
"license":"CC BY 4.0"
}
],
"requirements":[
"spacy-transformers>=1.1.2,<1.2.0"
]
}