da_dacy_small_trf / meta.json
KennethEnevoldsen's picture
Updated to version v0.2.0
0eadea0
raw
history blame
19.8 kB
{
"lang":"da",
"name":"dacy_small_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 small\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":0.9295532646,
"sents_r":0.9575221239,
"sents_f":0.9433304272,
"tag_acc":0.9846798742,
"pos_acc":0.9842315369,
"morph_acc":0.9772942762,
"morph_micro_p":0.9894326733,
"morph_micro_r":0.9833448258,
"morph_micro_f":0.9863793562,
"morph_per_feat":{
"NumType":{
"p":0.9941176471,
"r":0.9825581395,
"f":0.9883040936
},
"Degree":{
"p":0.9791666667,
"r":0.9715762274,
"f":0.9753566796
},
"Number":{
"p":0.9824362606,
"r":0.9774520857,
"f":0.9799378355
},
"Definite":{
"p":0.9870410367,
"r":0.9777492512,
"f":0.9823731728
},
"Gender":{
"p":0.9781150724,
"r":0.9712583246,
"f":0.9746746395
},
"Mood":{
"p":0.9990366089,
"r":0.9952015355,
"f":0.9971153846
},
"Tense":{
"p":0.9960784314,
"r":0.9898674981,
"f":0.9929632525
},
"VerbForm":{
"p":0.9968454259,
"r":0.991217064,
"f":0.9940232778
},
"Voice":{
"p":0.999251497,
"r":0.9955257271,
"f":0.9973851326
},
"AdpType":{
"p":1.0,
"r":0.9953531599,
"f":0.9976711691
},
"PronType":{
"p":0.9936708861,
"r":0.9918772563,
"f":0.9927732611
},
"Case":{
"p":0.9984350548,
"r":0.9891472868,
"f":0.9937694704
},
"Person":{
"p":0.9965095986,
"r":0.9896013865,
"f":0.9930434783
},
"Number[psor]":{
"p":0.9875,
"r":0.975308642,
"f":0.9813664596
},
"Poss":{
"p":1.0,
"r":0.987654321,
"f":0.9937888199
},
"PartType":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Reflex":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Foreign":{
"p":0.5,
"r":0.4,
"f":0.4444444444
},
"Abbr":{
"p":0.3333333333,
"r":0.5,
"f":0.4
},
"Style":{
"p":1.0,
"r":0.5,
"f":0.6666666667
},
"Polite":{
"p":1.0,
"r":0.6666666667,
"f":0.8
}
},
"dep_uas":0.8978522787,
"dep_las":0.8701623698,
"dep_las_per_type":{
"nummod":{
"p":0.8070175439,
"r":0.814159292,
"f":0.8105726872
},
"amod":{
"p":0.8970588235,
"r":0.895412844,
"f":0.8962350781
},
"nmod":{
"p":0.7772727273,
"r":0.7467248908,
"f":0.7616926503
},
"nsubj":{
"p":0.9386243386,
"r":0.9386243386,
"f":0.9386243386
},
"flat":{
"p":0.9319371728,
"r":0.9468085106,
"f":0.9393139842
},
"cc":{
"p":0.8813559322,
"r":0.8609271523,
"f":0.8710217755
},
"conj":{
"p":0.8392857143,
"r":0.8150289017,
"f":0.8269794721
},
"root":{
"p":0.8807495741,
"r":0.9150442478,
"f":0.8975694444
},
"advmod":{
"p":0.8590704648,
"r":0.8590704648,
"f":0.8590704648
},
"mark":{
"p":0.9280898876,
"r":0.9198218263,
"f":0.9239373602
},
"aux":{
"p":0.9813084112,
"r":0.9692307692,
"f":0.9752321981
},
"ccomp":{
"p":0.7411764706,
"r":0.7974683544,
"f":0.7682926829
},
"case":{
"p":0.9367631297,
"r":0.9171038825,
"f":0.9268292683
},
"det":{
"p":0.9388560158,
"r":0.9596774194,
"f":0.9491525424
},
"obl":{
"p":0.8076923077,
"r":0.7987321712,
"f":0.803187251
},
"appos":{
"p":0.7352941176,
"r":0.6578947368,
"f":0.6944444444
},
"nmod:poss":{
"p":0.8113207547,
"r":0.7889908257,
"f":0.8
},
"obj":{
"p":0.8905380334,
"r":0.9142857143,
"f":0.9022556391
},
"advcl":{
"p":0.7763157895,
"r":0.7564102564,
"f":0.7662337662
},
"cop":{
"p":0.875,
"r":0.8588957055,
"f":0.866873065
},
"acl:relcl":{
"p":0.7666666667,
"r":0.7540983607,
"f":0.7603305785
},
"compound:prt":{
"p":0.5,
"r":0.6176470588,
"f":0.5526315789
},
"dep":{
"p":0.0892857143,
"r":0.3333333333,
"f":0.1408450704
},
"fixed":{
"p":0.9310344828,
"r":0.8709677419,
"f":0.9
},
"iobj":{
"p":0.7857142857,
"r":0.7333333333,
"f":0.7586206897
},
"obl:tmod":{
"p":0.4285714286,
"r":0.1875,
"f":0.2608695652
},
"xcomp":{
"p":0.7894736842,
"r":0.703125,
"f":0.7438016529
},
"advmod:lmod":{
"p":0.9111111111,
"r":0.8541666667,
"f":0.8817204301
},
"expl":{
"p":0.9,
"r":0.9230769231,
"f":0.9113924051
},
"list":{
"p":0.3333333333,
"r":0.1764705882,
"f":0.2307692308
},
"obl:lmod":{
"p":1.0,
"r":0.3333333333,
"f":0.5
},
"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":0.8306010929,
"ents_r":0.8172043011,
"ents_f":0.8238482385,
"ents_per_type":{
"LOC":{
"p":0.8,
"r":0.875,
"f":0.8358208955
},
"ORG":{
"p":0.8,
"r":0.7204968944,
"f":0.7581699346
},
"PER":{
"p":0.9060773481,
"r":0.9111111111,
"f":0.9085872576
},
"MISC":{
"p":0.7796610169,
"r":0.7603305785,
"f":0.769874477
}
},
"lemma_acc":0.9466699925,
"coref_lea_f1":0.4218334451,
"coref_lea_precision":0.4478869466,
"coref_lea_recall":0.398644375,
"nel_score":0.352,
"nel_score_desc":"micro F",
"nel_micro_p":0.8461538462,
"nel_micro_r":0.2222222222,
"nel_micro_f":0.352,
"nel_macro_p":0.8767857143,
"nel_macro_r":0.2475984839,
"nel_macro_f":0.3752026075,
"nel_f_per_type":{
"MISC":{
"p":1.0,
"r":0.2631578947,
"f":0.4166666667
},
"PER":{
"p":0.8571428571,
"r":0.1016949153,
"f":0.1818181818
},
"LOC":{
"p":1.0,
"r":0.4285714286,
"f":0.6
},
"ORG":{
"p":0.65,
"r":0.196969697,
"f":0.3023255814
}
}
},
"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":"jonfd/electra-small-nordic",
"author":"J\u00f3n Fri\u00f0rik Da\u00f0ason",
"url":"https://huggingface.co/jonfd/electra-small-nordic",
"license":"CC BY 4.0"
}
],
"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)."
}