da_dacy_medium_trf / meta.json
KennethEnevoldsen's picture
Updated readme
e7dba91
raw
history blame
19.9 kB
{
"lang":"da",
"name":"dacy_medium_trf",
"version":"0.2.0",
"description":"\n<a href=\"https://github.com/centre-for-humanities-computing/Dacy\"><img src=\"https://centre-for-humanities-computing.github.io/DaCy/_static/icon.png\" width=\"175\" height=\"175\" align=\"right\" /></a>\n\n# DaCy medium\n\nDaCy is a Danish language processing framework with state-of-the-art pipelines as well as functionality for analysing Danish pipelines.\nDaCy's largest pipeline has achieved State-of-the-Art performance on parts-of-speech tagging and dependency \nparsing for Danish on the Danish Dependency treebank as well as competitive performance on named entity recognition, named entity disambiguation and coreference resolution. \nTo read more check out the [DaCy repository](https://github.com/centre-for-humanities-computing/DaCy) for material on how to use DaCy and reproduce the results. \nDaCy also contains guides on usage of the package as well as behavioural test for biases and robustness of Danish NLP pipelines.\n",
"author":"Kenneth Enevoldsen",
"email":"Kenneth.enevoldsen@cas.au.dk",
"url":"https://chcaa.io/#/",
"license":"Apache-2.0",
"spacy_version":">=3.5.2,<3.6.0",
"spacy_git_version":"Unknown",
"vectors":{
"width":0,
"vectors":0,
"keys":0,
"name":null
},
"labels":{
"transformer":[
],
"tagger":[
"ADJ",
"ADP",
"ADV",
"AUX",
"CCONJ",
"DET",
"INTJ",
"NOUN",
"NUM",
"PART",
"PRON",
"PROPN",
"PUNCT",
"SCONJ",
"SYM",
"VERB",
"X"
],
"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",
"NumType=Ord|POS=ADJ",
"POS=CCONJ",
"Definite=Ind|Gender=Neut|Number=Plur|POS=NOUN",
"POS=VERB|VerbForm=Inf|Voice=Act",
"Case=Acc|Gender=Neut|Number=Sing|POS=PRON|Person=3|PronType=Prs",
"Degree=Sup|POS=ADV",
"Degree=Pos|POS=ADV",
"Gender=Com|Number=Sing|POS=DET|PronType=Ind",
"Number=Plur|POS=DET|PronType=Ind",
"POS=ADP",
"POS=ADV|PartType=Inf",
"Case=Nom|Gender=Com|Number=Sing|POS=PRON|Person=3|PronType=Prs",
"Mood=Ind|POS=AUX|Tense=Past|VerbForm=Fin|Voice=Act",
"Definite=Def|Degree=Pos|Number=Sing|POS=ADJ",
"Number[psor]=Sing|POS=DET|Person=3|Poss=Yes|PronType=Prs",
"Mood=Ind|POS=VERB|Tense=Past|VerbForm=Fin|Voice=Act",
"POS=ADP|PartType=Inf",
"Definite=Ind|Degree=Pos|Gender=Com|Number=Sing|POS=ADJ",
"NumType=Card|POS=NUM",
"Degree=Pos|POS=ADJ",
"Definite=Ind|Number=Sing|POS=AUX|Tense=Past|VerbForm=Part",
"POS=PART|PartType=Inf",
"Case=Acc|POS=PRON|Person=3|PronType=Prs|Reflex=Yes",
"Definite=Def|Gender=Com|Number=Plur|POS=NOUN",
"Definite=Ind|Gender=Neut|Number=Sing|POS=NOUN",
"Number[psor]=Plur|POS=DET|Person=3|Poss=Yes|PronType=Prs",
"POS=VERB|Tense=Pres|VerbForm=Part",
"Case=Nom|Number=Plur|POS=PRON|Person=3|PronType=Prs",
"Case=Gen|Definite=Def|Gender=Com|Number=Sing|POS=NOUN",
"Definite=Def|Degree=Sup|Number=Plur|POS=ADJ",
"Case=Acc|Number=Plur|POS=PRON|Person=3|PronType=Prs",
"POS=AUX|VerbForm=Inf|Voice=Act",
"Definite=Ind|Degree=Pos|Gender=Neut|Number=Sing|POS=ADJ",
"Definite=Ind|Degree=Cmp|Number=Sing|POS=ADJ",
"Degree=Cmp|POS=ADJ",
"POS=PRON|PartType=Inf",
"Definite=Ind|Degree=Pos|Number=Sing|POS=ADJ",
"Case=Nom|Gender=Com|POS=PRON|PronType=Ind",
"Number=Plur|POS=PRON|PronType=Ind",
"POS=INTJ",
"Gender=Com|Number=Sing|POS=DET|PronType=Dem",
"Case=Gen|Number=Plur|POS=DET|PronType=Ind",
"Mood=Ind|POS=VERB|Tense=Pres|VerbForm=Fin|Voice=Pass",
"Definite=Def|Gender=Neut|Number=Plur|POS=NOUN",
"Degree=Cmp|POS=ADV",
"Number=Plur|Number[psor]=Plur|POS=PRON|Person=1|Poss=Yes|PronType=Prs|Style=Form",
"Case=Acc|Gender=Com|Number=Sing|POS=PRON|Person=3|PronType=Prs",
"Number=Plur|Number[psor]=Sing|POS=DET|Person=3|Poss=Yes|PronType=Prs|Reflex=Yes",
"Case=Gen|POS=PROPN",
"Gender=Neut|Number=Sing|POS=PRON|PronType=Ind",
"Number=Plur|POS=VERB|Tense=Past|VerbForm=Part",
"Gender=Neut|Number=Sing|Number[psor]=Sing|POS=DET|Person=3|Poss=Yes|PronType=Prs|Reflex=Yes",
"Case=Acc|Gender=Com|Number=Sing|POS=PRON|Person=1|PronType=Prs",
"Definite=Def|Degree=Sup|POS=ADJ",
"Gender=Neut|Number=Sing|POS=DET|PronType=Ind",
"Case=Gen|Definite=Ind|Gender=Neut|Number=Sing|POS=NOUN",
"Gender=Neut|Number=Sing|POS=DET|PronType=Dem",
"Definite=Def|Number=Sing|POS=VERB|Tense=Past|VerbForm=Part",
"POS=PRON|PronType=Dem",
"Degree=Pos|Gender=Com|Number=Sing|POS=ADJ",
"Number=Plur|POS=NUM",
"POS=VERB|VerbForm=Inf|Voice=Pass",
"Definite=Def|Degree=Sup|Number=Sing|POS=ADJ",
"Number=Sing|POS=PRON|PronType=Int,Rel",
"Case=Nom|Gender=Com|Number=Sing|POS=PRON|Person=1|PronType=Prs",
"Gender=Neut|Number=Sing|Number[psor]=Sing|POS=DET|Person=1|Poss=Yes|PronType=Prs",
"Gender=Com|Number=Sing|Number[psor]=Sing|POS=DET|Person=1|Poss=Yes|PronType=Prs",
"POS=PRON",
"Definite=Ind|Number=Sing|POS=NOUN",
"Definite=Ind|Number=Sing|POS=NUM",
"Case=Gen|Definite=Ind|Gender=Com|Number=Sing|POS=NOUN",
"Foreign=Yes|POS=ADV",
"POS=NOUN",
"Case=Gen|Definite=Def|Gender=Neut|Number=Sing|POS=NOUN",
"Gender=Com|Number=Plur|POS=NOUN",
"Gender=Neut|Number=Sing|POS=PRON|PronType=Int,Rel",
"Case=Nom|Gender=Com|Number=Plur|POS=PRON|Person=1|PronType=Prs",
"Number[psor]=Plur|POS=DET|Person=1|Poss=Yes|PronType=Prs",
"Gender=Com|Number=Sing|POS=PRON|PronType=Ind",
"Case=Gen|Definite=Ind|Gender=Com|Number=Plur|POS=NOUN",
"Degree=Pos|Gender=Neut|Number=Sing|POS=ADJ",
"Degree=Sup|POS=ADJ",
"Degree=Pos|Number=Sing|POS=ADJ",
"Mood=Imp|POS=VERB",
"Case=Nom|Gender=Com|POS=PRON|Person=2|Polite=Form|PronType=Prs",
"Case=Acc|Gender=Com|POS=PRON|Person=2|Polite=Form|PronType=Prs",
"POS=X",
"Case=Gen|Definite=Def|Gender=Com|Number=Plur|POS=NOUN",
"Number=Plur|POS=PRON|PronType=Dem",
"Case=Acc|Gender=Com|Number=Plur|POS=PRON|Person=1|PronType=Prs",
"Number=Plur|POS=PRON|PronType=Int,Rel",
"Gender=Com|Number=Sing|Number[psor]=Sing|POS=DET|Person=3|Poss=Yes|PronType=Prs|Reflex=Yes",
"Degree=Cmp|Number=Plur|POS=ADJ",
"Number=Plur|Number[psor]=Sing|POS=DET|Person=1|Poss=Yes|PronType=Prs",
"Gender=Com|Number=Sing|Number[psor]=Plur|POS=DET|Person=1|Poss=Yes|PronType=Prs|Style=Form",
"Case=Nom|Gender=Com|Number=Sing|POS=PRON|Person=2|PronType=Prs",
"Case=Acc|Gender=Com|Number=Sing|POS=PRON|Person=2|PronType=Prs",
"Gender=Com|POS=PRON|PronType=Int,Rel",
"Case=Gen|Degree=Pos|Number=Plur|POS=ADJ",
"Gender=Neut|Number=Sing|Number[psor]=Sing|POS=PRON|Person=3|Poss=Yes|PronType=Prs|Reflex=Yes",
"POS=VERB|VerbForm=Ger",
"Gender=Com|Number=Sing|POS=PRON|PronType=Dem",
"Case=Gen|POS=PRON|PronType=Int,Rel",
"Mood=Ind|POS=VERB|Tense=Past|VerbForm=Fin|Voice=Pass",
"Abbr=Yes|POS=X",
"Case=Gen|Definite=Ind|Gender=Neut|Number=Plur|POS=NOUN",
"Gender=Com|Number=Sing|Number[psor]=Sing|POS=DET|Person=2|Poss=Yes|PronType=Prs",
"Definite=Ind|Number=Plur|POS=NOUN",
"Foreign=Yes|POS=X",
"Number=Plur|POS=PRON|PronType=Rcp",
"Case=Nom|Gender=Com|Number=Plur|POS=PRON|Person=2|PronType=Prs",
"Case=Gen|Degree=Cmp|POS=ADJ",
"Case=Gen|Definite=Def|Gender=Neut|Number=Plur|POS=NOUN",
"Case=Acc|Gender=Com|Number=Plur|POS=PRON|Person=2|PronType=Prs",
"Gender=Neut|Number=Sing|POS=PRON|PronType=Dem",
"Number=Plur|Number[psor]=Plur|POS=DET|Person=1|Poss=Yes|PronType=Prs|Style=Form",
"Gender=Neut|Number=Sing|Number[psor]=Plur|POS=DET|Person=1|Poss=Yes|PronType=Prs|Style=Form",
"Number=Plur|Number[psor]=Sing|POS=PRON|Person=3|Poss=Yes|PronType=Prs|Reflex=Yes",
"Number[psor]=Sing|POS=PRON|Person=3|Poss=Yes|PronType=Prs",
"Case=Gen|Number=Plur|POS=PRON|PronType=Rcp",
"POS=DET|Person=2|Polite=Form|Poss=Yes|PronType=Prs",
"POS=SYM",
"POS=DET|PronType=Dem",
"Gender=Com|Number=Sing|POS=NUM",
"Number[psor]=Plur|POS=DET|Person=2|Poss=Yes|PronType=Prs",
"Case=Gen|Number=Plur|POS=VERB|Tense=Past|VerbForm=Part",
"Definite=Def|Degree=Abs|POS=ADJ",
"POS=VERB|Tense=Pres",
"Definite=Ind|Gender=Neut|Number=Sing|POS=NUM",
"Degree=Abs|POS=ADV",
"Case=Gen|Definite=Def|Degree=Pos|Number=Sing|POS=ADJ",
"Gender=Com|Number=Sing|POS=PRON|PronType=Int,Rel",
"POS=VERB|Tense=Past|VerbForm=Part",
"Definite=Ind|Degree=Sup|Number=Sing|POS=ADJ",
"Gender=Neut|Number=Sing|Number[psor]=Sing|POS=DET|Person=2|Poss=Yes|PronType=Prs",
"Gender=Com|Number=Sing|Number[psor]=Sing|POS=PRON|Person=1|Poss=Yes|PronType=Prs",
"Number=Plur|Number[psor]=Sing|POS=DET|Person=2|Poss=Yes|PronType=Prs",
"Number[psor]=Plur|POS=PRON|Person=3|Poss=Yes|PronType=Prs",
"Definite=Ind|POS=NOUN",
"Case=Gen|Gender=Com|Number=Sing|POS=DET|PronType=Ind",
"Definite=Ind|Gender=Com|Number=Sing|POS=NUM",
"Definite=Def|Number=Plur|POS=NOUN",
"Case=Gen|POS=NOUN",
"POS=AUX|Tense=Pres|VerbForm=Part"
],
"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"
],
"ner":[
"LOC",
"MISC",
"ORG",
"PER"
],
"coref":[
],
"span_resolver":[
],
"entity_linker":[
]
},
"pipeline":[
"transformer",
"tagger",
"morphologizer",
"trainable_lemmatizer",
"parser",
"ner",
"coref",
"span_resolver",
"span_cleaner",
"entity_linker"
],
"components":[
"transformer",
"tagger",
"morphologizer",
"trainable_lemmatizer",
"parser",
"ner",
"coref",
"span_resolver",
"span_cleaner",
"entity_linker"
],
"disabled":[
],
"requirements":[
"spacy-experimental>=0.6.2,<0.7.0",
"spacy-transformers>=1.2.3,<1.3.0"
],
"performance":{
"token_acc":0.9992023928,
"token_p":0.9970089731,
"token_r":0.9977052779,
"token_f":0.9973570039,
"sents_p":0.9842105263,
"sents_r":0.992920354,
"sents_f":0.9885462555,
"tag_acc":0.9847290149,
"pos_acc":0.985677928,
"morph_acc":0.9814371257,
"morph_micro_p":0.9910058542,
"morph_micro_r":0.9876942662,
"morph_micro_f":0.989347289,
"morph_per_feat":{
"NumType":{
"p":0.987654321,
"r":0.9302325581,
"f":0.9580838323
},
"Degree":{
"p":0.9894736842,
"r":0.9715762274,
"f":0.9804432855
},
"Number":{
"p":0.9884148064,
"r":0.9859075536,
"f":0.987159588
},
"Definite":{
"p":0.9858490566,
"r":0.9837398374,
"f":0.9847933176
},
"Gender":{
"p":0.9869901547,
"r":0.9838766211,
"f":0.9854309286
},
"Mood":{
"p":0.9971126083,
"r":0.9942418426,
"f":0.9956751562
},
"Tense":{
"p":0.9906469213,
"r":0.9906469213,
"f":0.9906469213
},
"VerbForm":{
"p":0.9924670433,
"r":0.9918444166,
"f":0.9921556323
},
"Voice":{
"p":0.997012696,
"r":0.9955257271,
"f":0.9962686567
},
"AdpType":{
"p":0.9990689013,
"r":0.9972118959,
"f":0.9981395349
},
"PronType":{
"p":0.9954914337,
"r":0.9963898917,
"f":0.9959404601
},
"Case":{
"p":0.9968652038,
"r":0.9860465116,
"f":0.9914263445
},
"Person":{
"p":0.9930555556,
"r":0.9913344887,
"f":0.9921942758
},
"Number[psor]":{
"p":0.987804878,
"r":1.0,
"f":0.9938650307
},
"Poss":{
"p":0.987804878,
"r":1.0,
"f":0.9938650307
},
"PartType":{
"p":1.0,
"r":0.9962406015,
"f":0.9981167608
},
"Polite":{
"p":0.6666666667,
"r":0.6666666667,
"f":0.6666666667
},
"Reflex":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Foreign":{
"p":0.5,
"r":0.2,
"f":0.2857142857
},
"Style":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Abbr":{
"p":0.6666666667,
"r":1.0,
"f":0.8
}
},
"dep_uas":0.9083920564,
"dep_las":0.883349834,
"dep_las_per_type":{
"nummod":{
"p":0.7948717949,
"r":0.8230088496,
"f":0.8086956522
},
"amod":{
"p":0.897810219,
"r":0.9027522936,
"f":0.9002744739
},
"nmod":{
"p":0.7712418301,
"r":0.7729257642,
"f":0.772082879
},
"nsubj":{
"p":0.9510638298,
"r":0.946031746,
"f":0.9485411141
},
"flat":{
"p":0.9285714286,
"r":0.9680851064,
"f":0.9479166667
},
"cc":{
"p":0.8681672026,
"r":0.8940397351,
"f":0.88091354
},
"conj":{
"p":0.8862275449,
"r":0.8554913295,
"f":0.8705882353
},
"root":{
"p":0.926056338,
"r":0.9309734513,
"f":0.9285083848
},
"advmod":{
"p":0.8871715611,
"r":0.8605697151,
"f":0.8736681887
},
"mark":{
"p":0.9148471616,
"r":0.9331848552,
"f":0.9239250276
},
"aux":{
"p":0.9875389408,
"r":0.9753846154,
"f":0.9814241486
},
"ccomp":{
"p":0.7764705882,
"r":0.835443038,
"f":0.8048780488
},
"case":{
"p":0.9348986126,
"r":0.9192025184,
"f":0.926984127
},
"det":{
"p":0.9409448819,
"r":0.9637096774,
"f":0.9521912351
},
"obl":{
"p":0.8476821192,
"r":0.8114104596,
"f":0.8291497976
},
"nmod:poss":{
"p":0.8181818182,
"r":0.8256880734,
"f":0.8219178082
},
"obj":{
"p":0.8943533698,
"r":0.9352380952,
"f":0.9143389199
},
"cop":{
"p":0.8944099379,
"r":0.8834355828,
"f":0.8888888889
},
"acl:relcl":{
"p":0.8343195266,
"r":0.7704918033,
"f":0.8011363636
},
"advcl":{
"p":0.6742857143,
"r":0.7564102564,
"f":0.7129909366
},
"dep":{
"p":0.1136363636,
"r":0.3333333333,
"f":0.1694915254
},
"compound:prt":{
"p":0.6666666667,
"r":0.5882352941,
"f":0.625
},
"fixed":{
"p":0.9473684211,
"r":0.8709677419,
"f":0.9075630252
},
"iobj":{
"p":0.7692307692,
"r":0.6666666667,
"f":0.7142857143
},
"appos":{
"p":0.8181818182,
"r":0.7105263158,
"f":0.7605633803
},
"obl:tmod":{
"p":0.5,
"r":0.3125,
"f":0.3846153846
},
"advmod:lmod":{
"p":0.7678571429,
"r":0.8958333333,
"f":0.8269230769
},
"xcomp":{
"p":0.8913043478,
"r":0.640625,
"f":0.7454545455
},
"expl":{
"p":0.9230769231,
"r":0.9230769231,
"f":0.9230769231
},
"list":{
"p":0.5714285714,
"r":0.2352941176,
"f":0.3333333333
},
"obl:lmod":{
"p":0.25,
"r":0.3333333333,
"f":0.2857142857
},
"parataxis":{
"p":0.0,
"r":0.0,
"f":0.0
},
"orphan":{
"p":0.0,
"r":0.0,
"f":0.0
},
"vocative":{
"p":0.0,
"r":0.0,
"f":0.0
},
"discourse":{
"p":0.0,
"r":0.0,
"f":0.0
},
"dislocated":{
"p":0.0,
"r":0.0,
"f":0.0
},
"compound":{
"p":0.0,
"r":0.0,
"f":0.0
}
},
"ents_p":0.8708487085,
"ents_r":0.8458781362,
"ents_f":0.8581818182,
"ents_per_type":{
"MISC":{
"p":0.8301886792,
"r":0.7272727273,
"f":0.7753303965
},
"ORG":{
"p":0.8611111111,
"r":0.7701863354,
"f":0.8131147541
},
"LOC":{
"p":0.854368932,
"r":0.9166666667,
"f":0.8844221106
},
"PER":{
"p":0.9100529101,
"r":0.9555555556,
"f":0.9322493225
}
},
"lemma_acc":0.9419805438,
"coref_lea_f1":0.4118366346,
"coref_lea_precision":0.4889169083,
"coref_lea_recall":0.3557507008,
"nel_score":0.801242236,
"nel_score_desc":"micro F",
"nel_micro_p":0.9923076923,
"nel_micro_r":0.671875,
"nel_micro_f":0.801242236,
"nel_macro_p":0.993902439,
"nel_macro_r":0.6598989464,
"nel_macro_f":0.7815238616,
"nel_f_per_type":{
"MISC":{
"p":1.0,
"r":0.4117647059,
"f":0.5833333333
},
"PER":{
"p":1.0,
"r":0.7540983607,
"f":0.8598130841
},
"LOC":{
"p":1.0,
"r":0.8285714286,
"f":0.90625
},
"ORG":{
"p":0.9756097561,
"r":0.6451612903,
"f":0.7766990291
}
}
},
"sources":[
{
"name":"UD Danish DDT v2.11",
"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://huggingface.co/datasets/dane",
"license":"CC BY-SA 4.0",
"author":"Rasmus Hvingelby, Amalie B. Pauli, Maria Barrett, Christina Rosted, Lasse M. Lidegaard, Anders S\u00f8gaard"
},
{
"name":"DaCoref",
"url":"https://huggingface.co/datasets/alexandrainst/dacoref",
"license":"CC BY-SA 4.0",
"author":"Buch-Kromann, Matthias"
},
{
"name":"DaNED",
"url":"https://danlp-alexandra.readthedocs.io/en/stable/docs/datasets.html#daned",
"license":"CC BY-SA 4.0",
"author":"Barrett, M. J., Lam, H., Wu, M., Lacroix, O., Plank, B., & S\u00f8gaard, A."
},
{
"name":"vesteinn/DanskBERT",
"author":"V\u00e9steinn Sn\u00e6bjarnarson",
"url":"https://huggingface.co/vesteinn/DanskBERT",
"license":"MIT"
}
],
"notes":"\n\n### Training\nThis model was trained using [spaCy](https://spacy.io) and logged to [Weights & Biases](https://wandb.ai/kenevoldsen/dacy-v0.2.0). You can find all the training logs [here](https://wandb.ai/kenevoldsen/dacy-v0.2.0)."
}