da_core_news_trf / meta.json
adrianeboyd's picture
Update spaCy pipeline
eca5c8a
raw
history blame
17 kB
{
"lang":"da",
"name":"core_news_trf",
"version":"3.5.0",
"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":">=3.5.0,<3.6.0",
"spacy_git_version":"9e0322de1",
"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":0.9989350373,
"token_p":0.9977732598,
"token_r":0.9974835463,
"token_f":0.997628382,
"pos_acc":0.9767058937,
"morph_acc":0.97360647,
"morph_micro_p":0.9872225616,
"morph_micro_r":0.9789006108,
"morph_micro_f":0.9830439741,
"morph_per_feat":{
"Mood":{
"p":0.9904761905,
"r":0.9914204004,
"f":0.9909480705
},
"Tense":{
"p":0.984882842,
"r":0.9811746988,
"f":0.9830252735
},
"VerbForm":{
"p":0.9833948339,
"r":0.9785801714,
"f":0.9809815951
},
"Voice":{
"p":0.9902985075,
"r":0.9917787743,
"f":0.9910380881
},
"Definite":{
"p":0.9903459372,
"r":0.9727380482,
"f":0.9814630257
},
"Gender":{
"p":0.9788235294,
"r":0.9677633765,
"f":0.9732620321
},
"Number":{
"p":0.9883935637,
"r":0.9773082942,
"f":0.9828196721
},
"AdpType":{
"p":0.9982238011,
"r":0.9938107869,
"f":0.9960124058
},
"PartType":{
"p":1.0,
"r":0.9967532468,
"f":0.9983739837
},
"Case":{
"p":0.9951923077,
"r":0.981042654,
"f":0.9880668258
},
"Person":{
"p":0.9892665474,
"r":0.9822380107,
"f":0.9857397504
},
"PronType":{
"p":0.9901315789,
"r":0.9901315789,
"f":0.9901315789
},
"NumType":{
"p":0.9865771812,
"r":0.9735099338,
"f":0.98
},
"Degree":{
"p":0.9745454545,
"r":0.9686746988,
"f":0.9716012085
},
"Reflex":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Number[psor]":{
"p":0.9770114943,
"r":0.988372093,
"f":0.9826589595
},
"Poss":{
"p":1.0,
"r":0.9886363636,
"f":0.9942857143
},
"Foreign":{
"p":0.8571428571,
"r":0.6,
"f":0.7058823529
},
"Abbr":{
"p":1.0,
"r":0.4,
"f":0.5714285714
},
"Style":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Polite":{
"p":0.0,
"r":0.0,
"f":0.0
}
},
"sents_p":0.8584070796,
"sents_r":0.859929078,
"sents_f":0.8591674048,
"dep_uas":0.8648950424,
"dep_las":0.8355942612,
"dep_las_per_type":{
"advmod":{
"p":0.7762430939,
"r":0.7937853107,
"f":0.7849162011
},
"root":{
"p":0.8490230906,
"r":0.8475177305,
"f":0.8482697427
},
"nsubj":{
"p":0.9080338266,
"r":0.9061181435,
"f":0.9070749736
},
"case":{
"p":0.92,
"r":0.9072978304,
"f":0.9136047666
},
"obl":{
"p":0.784591195,
"r":0.7748447205,
"f":0.7796875
},
"cc":{
"p":0.8579710145,
"r":0.8604651163,
"f":0.8592162554
},
"conj":{
"p":0.7146596859,
"r":0.728,
"f":0.7212681638
},
"obj":{
"p":0.8661710037,
"r":0.9048543689,
"f":0.8850902184
},
"aux":{
"p":0.8927536232,
"r":0.8979591837,
"f":0.8953488372
},
"acl:relcl":{
"p":0.7314285714,
"r":0.6918918919,
"f":0.7111111111
},
"advmod:lmod":{
"p":0.7878787879,
"r":0.776119403,
"f":0.7819548872
},
"det":{
"p":0.9248366013,
"r":0.9324546952,
"f":0.9286300246
},
"amod":{
"p":0.8700854701,
"r":0.8686006826,
"f":0.8693424424
},
"nmod:poss":{
"p":0.7326732673,
"r":0.7326732673,
"f":0.7326732673
},
"ccomp":{
"p":0.6875,
"r":0.7096774194,
"f":0.6984126984
},
"nummod":{
"p":0.8211382114,
"r":0.8416666667,
"f":0.8312757202
},
"flat":{
"p":0.8846153846,
"r":0.9139072848,
"f":0.8990228013
},
"compound:prt":{
"p":0.6333333333,
"r":0.4634146341,
"f":0.5352112676
},
"advcl":{
"p":0.7433628319,
"r":0.724137931,
"f":0.7336244541
},
"mark":{
"p":0.9074074074,
"r":0.9055441478,
"f":0.9064748201
},
"cop":{
"p":0.8806818182,
"r":0.8857142857,
"f":0.8831908832
},
"dep":{
"p":0.219047619,
"r":0.4339622642,
"f":0.2911392405
},
"nmod":{
"p":0.7094188377,
"r":0.69140625,
"f":0.7002967359
},
"iobj":{
"p":0.9230769231,
"r":0.5454545455,
"f":0.6857142857
},
"xcomp":{
"p":0.6388888889,
"r":0.3898305085,
"f":0.4842105263
},
"list":{
"p":0.3571428571,
"r":0.2777777778,
"f":0.3125
},
"vocative":{
"p":0.0,
"r":0.0,
"f":0.0
},
"fixed":{
"p":0.9428571429,
"r":0.8048780488,
"f":0.8684210526
},
"expl":{
"p":0.9117647059,
"r":0.9117647059,
"f":0.9117647059
},
"appos":{
"p":0.7096774194,
"r":0.6666666667,
"f":0.6875
},
"obl:tmod":{
"p":0.9,
"r":0.5,
"f":0.6428571429
},
"discourse":{
"p":0.0,
"r":0.0,
"f":0.0
},
"obl:lmod":{
"p":0.0,
"r":0.0,
"f":0.0
}
},
"lemma_acc":0.9471186441,
"tag_acc":0.9767058937,
"ents_p":0.8236514523,
"ents_r":0.8270833333,
"ents_f":0.8253638254,
"ents_per_type":{
"PER":{
"p":0.8988095238,
"r":0.9096385542,
"f":0.9041916168
},
"ORG":{
"p":0.7590361446,
"r":0.7,
"f":0.7283236994
},
"MISC":{
"p":0.7043478261,
"r":0.7168141593,
"f":0.7105263158
},
"LOC":{
"p":0.8793103448,
"r":0.9189189189,
"f":0.8986784141
}
},
"speed":4246.2689210915
},
"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>=1.2.0.dev0,<1.3.0"
]
}