da_dacy_large_trf / meta.json
KennethEnevoldsen's picture
Updated model to v 0.2.0
fe85a1c
raw
history blame
19.8 kB
{
"lang":"da",
"name":"dacy_large_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 large\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":1.0,
"sents_r":1.0,
"sents_f":1.0,
"tag_acc":0.9913668347,
"pos_acc":0.9908174469,
"morph_acc":0.9880227568,
"morph_micro_p":0.9945294243,
"morph_micro_r":0.9932106296,
"morph_micro_f":0.9938695894,
"morph_per_feat":{
"NumType":{
"p":0.9826589595,
"r":0.988372093,
"f":0.9855072464
},
"Degree":{
"p":0.9973753281,
"r":0.9819121447,
"f":0.9895833333
},
"Number":{
"p":0.991821771,
"r":0.9912626832,
"f":0.9915421483
},
"Definite":{
"p":0.9910141207,
"r":0.9910141207,
"f":0.9910141207
},
"Gender":{
"p":0.9905329593,
"r":0.9901857694,
"f":0.9903593339
},
"Mood":{
"p":0.9990393852,
"r":0.9980806142,
"f":0.9985597696
},
"Tense":{
"p":0.9953343701,
"r":0.9976617303,
"f":0.9964966913
},
"VerbForm":{
"p":0.9956140351,
"r":0.9968632371,
"f":0.9962382445
},
"Voice":{
"p":0.9970149254,
"r":0.9962714392,
"f":0.9966430436
},
"AdpType":{
"p":1.0,
"r":1.0,
"f":1.0
},
"PronType":{
"p":0.9990966576,
"r":0.9981949458,
"f":0.9986455982
},
"Case":{
"p":1.0,
"r":0.992248062,
"f":0.9961089494
},
"Person":{
"p":0.9982638889,
"r":0.9965337955,
"f":0.9973980919
},
"Number[psor]":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Poss":{
"p":1.0,
"r":1.0,
"f":1.0
},
"PartType":{
"p":0.9962406015,
"r":0.9962406015,
"f":0.9962406015
},
"Reflex":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Foreign":{
"p":0.0,
"r":0.0,
"f":0.0
},
"Style":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Polite":{
"p":1.0,
"r":0.6666666667,
"f":0.8
},
"Abbr":{
"p":1.0,
"r":0.5,
"f":0.6666666667
}
},
"dep_uas":0.9280885781,
"dep_las":0.9079997669,
"dep_las_per_type":{
"nummod":{
"p":0.8738738739,
"r":0.8584070796,
"f":0.8660714286
},
"amod":{
"p":0.9130434783,
"r":0.9247706422,
"f":0.9188696445
},
"nmod":{
"p":0.8213507625,
"r":0.8231441048,
"f":0.8222464558
},
"nsubj":{
"p":0.9587737844,
"r":0.9597883598,
"f":0.9592808038
},
"flat":{
"p":0.9672131148,
"r":0.9414893617,
"f":0.9541778976
},
"cc":{
"p":0.9019607843,
"r":0.9139072848,
"f":0.9078947368
},
"conj":{
"p":0.8904899135,
"r":0.8930635838,
"f":0.8917748918
},
"root":{
"p":0.9468085106,
"r":0.9451327434,
"f":0.9459698849
},
"advmod":{
"p":0.9056316591,
"r":0.892053973,
"f":0.8987915408
},
"mark":{
"p":0.9572072072,
"r":0.9465478842,
"f":0.9518477044
},
"aux":{
"p":0.9782608696,
"r":0.9692307692,
"f":0.9737248841
},
"ccomp":{
"p":0.7931034483,
"r":0.8734177215,
"f":0.8313253012
},
"case":{
"p":0.9511677282,
"r":0.9401888772,
"f":0.945646438
},
"det":{
"p":0.96,
"r":0.9677419355,
"f":0.9638554217
},
"obl":{
"p":0.8901453958,
"r":0.8732171157,
"f":0.8816
},
"nmod:poss":{
"p":0.8245614035,
"r":0.8623853211,
"f":0.8430493274
},
"obj":{
"p":0.9362101313,
"r":0.9504761905,
"f":0.943289225
},
"cop":{
"p":0.9036144578,
"r":0.9202453988,
"f":0.9118541033
},
"acl:relcl":{
"p":0.8554913295,
"r":0.8087431694,
"f":0.8314606742
},
"advcl":{
"p":0.754601227,
"r":0.7884615385,
"f":0.7711598746
},
"compound:prt":{
"p":0.7,
"r":0.6176470588,
"f":0.65625
},
"dep":{
"p":0.1368421053,
"r":0.4333333333,
"f":0.208
},
"fixed":{
"p":0.9655172414,
"r":0.9032258065,
"f":0.9333333333
},
"iobj":{
"p":0.9230769231,
"r":0.8,
"f":0.8571428571
},
"appos":{
"p":0.8,
"r":0.7368421053,
"f":0.7671232877
},
"obl:tmod":{
"p":0.75,
"r":0.375,
"f":0.5
},
"xcomp":{
"p":0.92,
"r":0.71875,
"f":0.8070175439
},
"advmod:lmod":{
"p":0.8775510204,
"r":0.8958333333,
"f":0.8865979381
},
"expl":{
"p":0.972972973,
"r":0.9230769231,
"f":0.9473684211
},
"list":{
"p":0.3636363636,
"r":0.2352941176,
"f":0.2857142857
},
"obl:lmod":{
"p":0.5,
"r":0.3333333333,
"f":0.4
},
"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":0.8858195212,
"ents_r":0.8620071685,
"ents_f":0.8737511353,
"ents_per_type":{
"LOC":{
"p":0.8613861386,
"r":0.90625,
"f":0.883248731
},
"PER":{
"p":0.9550561798,
"r":0.9444444444,
"f":0.9497206704
},
"ORG":{
"p":0.8819444444,
"r":0.7888198758,
"f":0.8327868852
},
"MISC":{
"p":0.8083333333,
"r":0.8016528926,
"f":0.8049792531
}
},
"lemma_acc":0.9589423796,
"coref_lea_f1":0.4672143289,
"coref_lea_precision":0.4590991705,
"coref_lea_recall":0.4756215411,
"nel_score":0.3428571429,
"nel_score_desc":"micro F",
"nel_micro_p":0.84,
"nel_micro_r":0.2153846154,
"nel_micro_f":0.3428571429,
"nel_macro_p":0.8670634921,
"nel_macro_r":0.2470462544,
"nel_macro_f":0.3727980563,
"nel_f_per_type":{
"MISC":{
"p":1.0,
"r":0.2777777778,
"f":0.4347826087
},
"PER":{
"p":0.8571428571,
"r":0.1,
"f":0.1791044776
},
"LOC":{
"p":1.0,
"r":0.4411764706,
"f":0.612244898
},
"ORG":{
"p":0.6111111111,
"r":0.1692307692,
"f":0.265060241
}
}
},
"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":"chcaa/dfm-encoder-large-v1",
"author":"The Danish Foundation Models team",
"url":"https://huggingface.co/chcaa/dfm-encoder-large-v1",
"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)."
}