da_core_news_trf / meta.json
adrianeboyd's picture
Update spaCy pipeline
6f612fd
raw history blame
No virus
17.1 kB
{
"lang":"da",
"name":"core_news_trf",
"version":"3.7.2",
"description":"Danish transformer pipeline (Transformer(name='vesteinn/DanskBERT', piece_encoder='xlm-roberta-sentencepiece', stride=120, type='xlm-roberta', width=768, window=152, vocab_size=50005)). 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":">=3.7.0,<3.8.0",
"spacy_git_version":"6b4f77441",
"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":0.9870683392,
"morph_acc":0.9845498135,
"morph_micro_p":0.9929531052,
"morph_micro_r":0.9886426733,
"morph_micro_f":0.9907932011,
"morph_per_feat":{
"Mood":{
"p":0.9952290076,
"r":0.9942802669,
"f":0.9947544111
},
"Tense":{
"p":0.9924242424,
"r":0.9864457831,
"f":0.9894259819
},
"VerbForm":{
"p":0.9919901417,
"r":0.9853121175,
"f":0.9886398526
},
"Voice":{
"p":0.9947643979,
"r":0.9940209268,
"f":0.9943925234
},
"Definite":{
"p":0.9948227798,
"r":0.9869616752,
"f":0.9908766363
},
"Gender":{
"p":0.9886439546,
"r":0.9837155201,
"f":0.9861735799
},
"Number":{
"p":0.9918763103,
"r":0.987219614,
"f":0.9895424837
},
"AdpType":{
"p":0.9991134752,
"r":0.9964633068,
"f":0.9977866313
},
"PartType":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Case":{
"p":0.9968152866,
"r":0.9889415482,
"f":0.9928628073
},
"Person":{
"p":0.9982238011,
"r":0.9982238011,
"f":0.9982238011
},
"PronType":{
"p":0.9975308642,
"r":0.9967105263,
"f":0.9971205265
},
"NumType":{
"p":0.9867549669,
"r":0.9867549669,
"f":0.9867549669
},
"Degree":{
"p":0.9795918367,
"r":0.9831325301,
"f":0.9813589898
},
"Reflex":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Number[psor]":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Poss":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Foreign":{
"p":1.0,
"r":0.7,
"f":0.8235294118
},
"Abbr":{
"p":1.0,
"r":0.4,
"f":0.5714285714
},
"Style":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Polite":{
"p":1.0,
"r":1.0,
"f":1.0
}
},
"sents_p":0.9261862917,
"sents_r":0.9343971631,
"sents_f":0.9302736099,
"dep_uas":0.897934115,
"dep_las":0.8740509156,
"dep_las_per_type":{
"advmod":{
"p":0.8345323741,
"r":0.8192090395,
"f":0.8267997149
},
"root":{
"p":0.9014084507,
"r":0.9078014184,
"f":0.9045936396
},
"nsubj":{
"p":0.9345991561,
"r":0.9345991561,
"f":0.9345991561
},
"case":{
"p":0.9358717435,
"r":0.9211045365,
"f":0.9284294235
},
"obl":{
"p":0.8388625592,
"r":0.8245341615,
"f":0.8316366484
},
"cc":{
"p":0.898255814,
"r":0.898255814,
"f":0.898255814
},
"conj":{
"p":0.816,
"r":0.816,
"f":0.816
},
"obj":{
"p":0.9128787879,
"r":0.9359223301,
"f":0.9242569511
},
"aux":{
"p":0.9176470588,
"r":0.9096209913,
"f":0.9136163982
},
"acl:relcl":{
"p":0.7932960894,
"r":0.7675675676,
"f":0.7802197802
},
"advmod:lmod":{
"p":0.8805970149,
"r":0.8805970149,
"f":0.8805970149
},
"det":{
"p":0.9456342669,
"r":0.9456342669,
"f":0.9456342669
},
"amod":{
"p":0.8939393939,
"r":0.9061433447,
"f":0.9
},
"nmod:poss":{
"p":0.8,
"r":0.7920792079,
"f":0.7960199005
},
"ccomp":{
"p":0.7105263158,
"r":0.8709677419,
"f":0.7826086957
},
"nummod":{
"p":0.8174603175,
"r":0.8583333333,
"f":0.837398374
},
"flat":{
"p":0.8805031447,
"r":0.9271523179,
"f":0.9032258065
},
"compound:prt":{
"p":0.6666666667,
"r":0.6341463415,
"f":0.65
},
"advcl":{
"p":0.7699115044,
"r":0.75,
"f":0.7598253275
},
"mark":{
"p":0.9371069182,
"r":0.9178644764,
"f":0.9273858921
},
"cop":{
"p":0.9152542373,
"r":0.9257142857,
"f":0.9204545455
},
"dep":{
"p":0.2095238095,
"r":0.4150943396,
"f":0.2784810127
},
"nmod":{
"p":0.784989858,
"r":0.755859375,
"f":0.7701492537
},
"iobj":{
"p":0.9375,
"r":0.6818181818,
"f":0.7894736842
},
"xcomp":{
"p":0.7346938776,
"r":0.6101694915,
"f":0.6666666667
},
"obl:lmod":{
"p":0.0,
"r":0.0,
"f":0.0
},
"list":{
"p":0.4,
"r":0.3333333333,
"f":0.3636363636
},
"vocative":{
"p":0.0,
"r":0.0,
"f":0.0
},
"fixed":{
"p":0.9473684211,
"r":0.8780487805,
"f":0.9113924051
},
"expl":{
"p":0.96875,
"r":0.9117647059,
"f":0.9393939394
},
"appos":{
"p":0.7297297297,
"r":0.8181818182,
"f":0.7714285714
},
"obl:tmod":{
"p":1.0,
"r":0.6111111111,
"f":0.7586206897
},
"discourse":{
"p":0.0,
"r":0.0,
"f":0.0
}
},
"lemma_acc":0.9579661017,
"tag_acc":0.9870683392,
"ents_p":0.8866396761,
"ents_r":0.9125,
"ents_f":0.8993839836,
"ents_per_type":{
"MISC":{
"p":0.7846153846,
"r":0.9026548673,
"f":0.8395061728
},
"PER":{
"p":0.950310559,
"r":0.921686747,
"f":0.9357798165
},
"ORG":{
"p":0.8764044944,
"r":0.8666666667,
"f":0.8715083799
},
"LOC":{
"p":0.9210526316,
"r":0.9459459459,
"f":0.9333333333
}
},
"speed":523.1005752745
},
"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":"vesteinn/DanskBERT",
"author":"Sn\u00e6bjarnarson, V\u00e9steinn and Simonsen, Annika and Glava\u0161, Goran and Vuli\u0107, Ivan",
"url":"https://huggingface.co/vesteinn/DanskBERT",
"license":"CC BY 4.0"
}
],
"requirements":[
"spacy-curated-transformers>=0.2.0,<0.3.0"
]
}