nl_core_news_lg / meta.json
adrianeboyd's picture
Update spaCy pipeline
cd10e5f
{
"lang":"nl",
"name":"core_news_lg",
"version":"3.7.0",
"description":"Dutch pipeline optimized for CPU. Components: tok2vec, morphologizer, tagger, parser, lemmatizer (trainable_lemmatizer), senter, ner.",
"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":300,
"vectors":500000,
"keys":500000,
"name":"nl_vectors"
},
"labels":{
"tok2vec":[
],
"morphologizer":[
"POS=PRON|Person=3|PronType=Dem",
"Number=Sing|POS=AUX|Tense=Pres|VerbForm=Fin",
"POS=ADV",
"POS=VERB|VerbForm=Part",
"POS=PUNCT",
"Number=Sing|POS=AUX|Tense=Past|VerbForm=Fin",
"POS=ADP",
"POS=NUM",
"Number=Plur|POS=NOUN",
"POS=VERB|VerbForm=Inf",
"POS=SCONJ",
"Definite=Def|POS=DET",
"Gender=Com|Number=Sing|POS=NOUN",
"Number=Sing|POS=VERB|Tense=Pres|VerbForm=Fin",
"Degree=Pos|POS=ADJ",
"Gender=Neut|Number=Sing|POS=PROPN",
"Gender=Com|Number=Sing|POS=PROPN",
"POS=AUX|VerbForm=Inf",
"Number=Sing|POS=VERB|Tense=Past|VerbForm=Fin",
"POS=DET",
"Gender=Neut|Number=Sing|POS=NOUN",
"POS=PRON|Person=3|PronType=Prs",
"POS=CCONJ",
"Number=Plur|POS=VERB|Tense=Pres|VerbForm=Fin",
"POS=PRON|Person=3|PronType=Ind",
"Degree=Cmp|POS=ADJ",
"Case=Nom|POS=PRON|Person=1|PronType=Prs",
"Definite=Ind|POS=DET",
"Case=Nom|POS=PRON|Person=3|PronType=Prs",
"POS=PRON|Person=3|Poss=Yes|PronType=Prs",
"Number=Plur|POS=AUX|Tense=Pres|VerbForm=Fin",
"POS=PRON|PronType=Rel",
"Case=Acc|POS=PRON|Person=1|PronType=Prs",
"Number=Plur|POS=VERB|Tense=Past|VerbForm=Fin",
"Gender=Com,Neut|Number=Sing|POS=NOUN",
"Case=Acc|POS=PRON|Person=3|PronType=Prs|Reflex=Yes",
"Case=Acc|POS=PRON|Person=3|PronType=Prs",
"POS=PROPN",
"POS=PRON|PronType=Ind",
"POS=PRON|Person=3|PronType=Int",
"Case=Acc|POS=PRON|PronType=Rcp",
"Number=Plur|POS=AUX|Tense=Past|VerbForm=Fin",
"Number=Sing|POS=NOUN",
"POS=PRON|Person=1|Poss=Yes|PronType=Prs",
"POS=SYM",
"Abbr=Yes|POS=X",
"Gender=Com,Neut|Number=Sing|POS=PROPN",
"Degree=Sup|POS=ADJ",
"POS=ADJ",
"Number=Sing|POS=PROPN",
"POS=PRON|PronType=Dem",
"POS=AUX|VerbForm=Part",
"POS=SPACE",
"POS=PRON|Person=3|PronType=Rel",
"Number=Plur|POS=PROPN",
"POS=PRON|Person=2|Poss=Yes|PronType=Prs",
"Case=Dat|POS=PRON|PronType=Dem",
"Case=Nom|POS=PRON|Person=2|PronType=Prs",
"POS=INTJ",
"Case=Acc|POS=PRON|Person=2|PronType=Prs",
"Case=Gen|POS=PRON|Person=3|Poss=Yes|PronType=Prs",
"POS=PRON|PronType=Int",
"POS=PRON|Person=2|PronType=Prs",
"POS=PRON|Person=3",
"Case=Gen|POS=PRON|Person=2|PronType=Prs",
"POS=X"
],
"tagger":[
"ADJ|nom|basis|met-e|mv-n",
"ADJ|nom|basis|met-e|zonder-n|bijz",
"ADJ|nom|basis|met-e|zonder-n|stan",
"ADJ|nom|basis|zonder|mv-n",
"ADJ|nom|basis|zonder|zonder-n",
"ADJ|nom|comp|met-e|mv-n",
"ADJ|nom|comp|met-e|zonder-n|stan",
"ADJ|nom|sup|met-e|mv-n",
"ADJ|nom|sup|met-e|zonder-n|bijz",
"ADJ|nom|sup|met-e|zonder-n|stan",
"ADJ|nom|sup|zonder|zonder-n",
"ADJ|postnom|basis|met-s",
"ADJ|postnom|basis|zonder",
"ADJ|postnom|comp|met-s",
"ADJ|prenom|basis|met-e|bijz",
"ADJ|prenom|basis|met-e|stan",
"ADJ|prenom|basis|zonder",
"ADJ|prenom|comp|met-e|stan",
"ADJ|prenom|comp|zonder",
"ADJ|prenom|sup|met-e|stan",
"ADJ|prenom|sup|zonder",
"ADJ|vrij|basis|zonder",
"ADJ|vrij|comp|zonder",
"ADJ|vrij|dim|zonder",
"ADJ|vrij|sup|zonder",
"BW",
"LET",
"LID|bep|dat|evmo",
"LID|bep|gen|evmo",
"LID|bep|gen|rest3",
"LID|bep|stan|evon",
"LID|bep|stan|rest",
"LID|onbep|stan|agr",
"N|eigen|ev|basis|gen",
"N|eigen|ev|basis|genus|stan",
"N|eigen|ev|basis|onz|stan",
"N|eigen|ev|basis|zijd|stan",
"N|eigen|ev|dim|onz|stan",
"N|eigen|mv|basis",
"N|soort|ev|basis|dat",
"N|soort|ev|basis|gen",
"N|soort|ev|basis|genus|stan",
"N|soort|ev|basis|onz|stan",
"N|soort|ev|basis|zijd|stan",
"N|soort|ev|dim|onz|stan",
"N|soort|mv|basis",
"N|soort|mv|dim",
"SPEC|afgebr",
"SPEC|afk",
"SPEC|deeleigen",
"SPEC|enof",
"SPEC|meta",
"SPEC|symb",
"SPEC|vreemd",
"TSW",
"TW|hoofd|nom|mv-n|basis",
"TW|hoofd|nom|mv-n|dim",
"TW|hoofd|nom|zonder-n|basis",
"TW|hoofd|nom|zonder-n|dim",
"TW|hoofd|prenom|stan",
"TW|hoofd|vrij",
"TW|rang|nom|mv-n",
"TW|rang|nom|zonder-n",
"TW|rang|prenom|stan",
"VG|neven",
"VG|onder",
"VNW|aanw|adv-pron|obl|vol|3o|getal",
"VNW|aanw|adv-pron|stan|red|3|getal",
"VNW|aanw|det|dat|nom|met-e|zonder-n",
"VNW|aanw|det|dat|prenom|met-e|evmo",
"VNW|aanw|det|gen|prenom|met-e|rest3",
"VNW|aanw|det|stan|nom|met-e|mv-n",
"VNW|aanw|det|stan|nom|met-e|zonder-n",
"VNW|aanw|det|stan|prenom|met-e|rest",
"VNW|aanw|det|stan|prenom|zonder|agr",
"VNW|aanw|det|stan|prenom|zonder|evon",
"VNW|aanw|det|stan|prenom|zonder|rest",
"VNW|aanw|det|stan|vrij|zonder",
"VNW|aanw|pron|gen|vol|3m|ev",
"VNW|aanw|pron|stan|vol|3o|ev",
"VNW|aanw|pron|stan|vol|3|getal",
"VNW|betr|det|stan|nom|met-e|zonder-n",
"VNW|betr|det|stan|nom|zonder|zonder-n",
"VNW|betr|pron|stan|vol|3|ev",
"VNW|betr|pron|stan|vol|persoon|getal",
"VNW|bez|det|gen|vol|3|ev|prenom|met-e|rest3",
"VNW|bez|det|stan|nadr|2v|mv|prenom|zonder|agr",
"VNW|bez|det|stan|red|1|ev|prenom|zonder|agr",
"VNW|bez|det|stan|red|2v|ev|prenom|zonder|agr",
"VNW|bez|det|stan|red|3|ev|prenom|zonder|agr",
"VNW|bez|det|stan|vol|1|ev|prenom|met-e|rest",
"VNW|bez|det|stan|vol|1|ev|prenom|zonder|agr",
"VNW|bez|det|stan|vol|1|mv|prenom|met-e|rest",
"VNW|bez|det|stan|vol|1|mv|prenom|zonder|evon",
"VNW|bez|det|stan|vol|2v|ev|prenom|zonder|agr",
"VNW|bez|det|stan|vol|2|getal|prenom|zonder|agr",
"VNW|bez|det|stan|vol|3m|ev|nom|met-e|zonder-n",
"VNW|bez|det|stan|vol|3m|ev|prenom|met-e|rest",
"VNW|bez|det|stan|vol|3p|mv|prenom|met-e|rest",
"VNW|bez|det|stan|vol|3v|ev|nom|met-e|zonder-n",
"VNW|bez|det|stan|vol|3v|ev|prenom|met-e|rest",
"VNW|bez|det|stan|vol|3|ev|prenom|zonder|agr",
"VNW|bez|det|stan|vol|3|mv|prenom|zonder|agr",
"VNW|excl|pron|stan|vol|3|getal",
"VNW|onbep|adv-pron|gen|red|3|getal",
"VNW|onbep|adv-pron|obl|vol|3o|getal",
"VNW|onbep|det|stan|nom|met-e|mv-n",
"VNW|onbep|det|stan|nom|met-e|zonder-n",
"VNW|onbep|det|stan|nom|zonder|zonder-n",
"VNW|onbep|det|stan|prenom|met-e|agr",
"VNW|onbep|det|stan|prenom|met-e|evz",
"VNW|onbep|det|stan|prenom|met-e|mv",
"VNW|onbep|det|stan|prenom|met-e|rest",
"VNW|onbep|det|stan|prenom|zonder|agr",
"VNW|onbep|det|stan|prenom|zonder|evon",
"VNW|onbep|det|stan|vrij|zonder",
"VNW|onbep|grad|gen|nom|met-e|mv-n|basis",
"VNW|onbep|grad|stan|nom|met-e|mv-n|basis",
"VNW|onbep|grad|stan|nom|met-e|mv-n|sup",
"VNW|onbep|grad|stan|nom|met-e|zonder-n|basis",
"VNW|onbep|grad|stan|nom|met-e|zonder-n|sup",
"VNW|onbep|grad|stan|prenom|met-e|agr|basis",
"VNW|onbep|grad|stan|prenom|met-e|agr|comp",
"VNW|onbep|grad|stan|prenom|met-e|agr|sup",
"VNW|onbep|grad|stan|prenom|met-e|mv|basis",
"VNW|onbep|grad|stan|prenom|zonder|agr|basis",
"VNW|onbep|grad|stan|prenom|zonder|agr|comp",
"VNW|onbep|grad|stan|vrij|zonder|basis",
"VNW|onbep|grad|stan|vrij|zonder|comp",
"VNW|onbep|grad|stan|vrij|zonder|sup",
"VNW|onbep|pron|gen|vol|3p|ev",
"VNW|onbep|pron|stan|vol|3o|ev",
"VNW|onbep|pron|stan|vol|3p|ev",
"VNW|pers|pron|gen|vol|2|getal",
"VNW|pers|pron|nomin|nadr|3m|ev|masc",
"VNW|pers|pron|nomin|nadr|3v|ev|fem",
"VNW|pers|pron|nomin|red|1|mv",
"VNW|pers|pron|nomin|red|2v|ev",
"VNW|pers|pron|nomin|red|2|getal",
"VNW|pers|pron|nomin|red|3p|ev|masc",
"VNW|pers|pron|nomin|red|3|ev|masc",
"VNW|pers|pron|nomin|vol|1|ev",
"VNW|pers|pron|nomin|vol|1|mv",
"VNW|pers|pron|nomin|vol|2b|getal",
"VNW|pers|pron|nomin|vol|2v|ev",
"VNW|pers|pron|nomin|vol|2|getal",
"VNW|pers|pron|nomin|vol|3p|mv",
"VNW|pers|pron|nomin|vol|3v|ev|fem",
"VNW|pers|pron|nomin|vol|3|ev|masc",
"VNW|pers|pron|obl|nadr|3m|ev|masc",
"VNW|pers|pron|obl|red|3|ev|masc",
"VNW|pers|pron|obl|vol|2v|ev",
"VNW|pers|pron|obl|vol|3p|mv",
"VNW|pers|pron|obl|vol|3|ev|masc",
"VNW|pers|pron|obl|vol|3|getal|fem",
"VNW|pers|pron|stan|nadr|2v|mv",
"VNW|pers|pron|stan|red|3|ev|fem",
"VNW|pers|pron|stan|red|3|ev|onz",
"VNW|pers|pron|stan|red|3|mv",
"VNW|pr|pron|obl|nadr|1|ev",
"VNW|pr|pron|obl|nadr|2v|getal",
"VNW|pr|pron|obl|nadr|2|getal",
"VNW|pr|pron|obl|red|1|ev",
"VNW|pr|pron|obl|red|2v|getal",
"VNW|pr|pron|obl|vol|1|ev",
"VNW|pr|pron|obl|vol|1|mv",
"VNW|pr|pron|obl|vol|2|getal",
"VNW|recip|pron|gen|vol|persoon|mv",
"VNW|recip|pron|obl|vol|persoon|mv",
"VNW|refl|pron|obl|nadr|3|getal",
"VNW|refl|pron|obl|red|3|getal",
"VNW|vb|adv-pron|obl|vol|3o|getal",
"VNW|vb|det|stan|nom|met-e|zonder-n",
"VNW|vb|det|stan|prenom|met-e|rest",
"VNW|vb|det|stan|prenom|zonder|evon",
"VNW|vb|pron|gen|vol|3m|ev",
"VNW|vb|pron|gen|vol|3p|mv",
"VNW|vb|pron|gen|vol|3v|ev",
"VNW|vb|pron|stan|vol|3o|ev",
"VNW|vb|pron|stan|vol|3p|getal",
"VZ|fin",
"VZ|init",
"VZ|versm",
"WW|inf|nom|zonder|zonder-n",
"WW|inf|prenom|met-e",
"WW|inf|vrij|zonder",
"WW|od|nom|met-e|mv-n",
"WW|od|nom|met-e|zonder-n",
"WW|od|prenom|met-e",
"WW|od|prenom|zonder",
"WW|od|vrij|zonder",
"WW|pv|conj|ev",
"WW|pv|tgw|ev",
"WW|pv|tgw|met-t",
"WW|pv|tgw|mv",
"WW|pv|verl|ev",
"WW|pv|verl|mv",
"WW|vd|nom|met-e|mv-n",
"WW|vd|nom|met-e|zonder-n",
"WW|vd|prenom|met-e",
"WW|vd|prenom|zonder",
"WW|vd|vrij|zonder",
"_SP"
],
"parser":[
"ROOT",
"acl",
"acl:relcl",
"advcl",
"advmod",
"amod",
"appos",
"aux",
"aux:pass",
"case",
"cc",
"ccomp",
"compound:prt",
"conj",
"cop",
"csubj",
"dep",
"det",
"expl",
"expl:pv",
"fixed",
"flat",
"iobj",
"mark",
"nmod",
"nmod:poss",
"nsubj",
"nsubj:pass",
"nummod",
"obj",
"obl",
"obl:agent",
"orphan",
"parataxis",
"punct",
"xcomp"
],
"attribute_ruler":[
],
"ner":[
"CARDINAL",
"DATE",
"EVENT",
"FAC",
"GPE",
"LANGUAGE",
"LAW",
"LOC",
"MONEY",
"NORP",
"ORDINAL",
"ORG",
"PERCENT",
"PERSON",
"PRODUCT",
"QUANTITY",
"TIME",
"WORK_OF_ART"
]
},
"pipeline":[
"tok2vec",
"morphologizer",
"tagger",
"parser",
"lemmatizer",
"attribute_ruler",
"ner"
],
"components":[
"tok2vec",
"morphologizer",
"tagger",
"parser",
"lemmatizer",
"senter",
"attribute_ruler",
"ner"
],
"disabled":[
"senter"
],
"performance":{
"tag_acc":0.9514067612,
"sents_p":0.858033241,
"sents_r":0.8888091822,
"sents_f":0.8731501057,
"dep_uas":0.8702417761,
"dep_las":0.8253421186,
"dep_las_per_type":{
"nmod:poss":{
"p":0.9448529412,
"r":0.9379562044,
"f":0.9413919414
},
"nsubj":{
"p":0.8506493506,
"r":0.8612754767,
"f":0.8559294348
},
"aux":{
"p":0.8942307692,
"r":0.9177631579,
"f":0.9058441558
},
"advmod":{
"p":0.7902097902,
"r":0.8071428571,
"f":0.7985865724
},
"root":{
"p":0.875952876,
"r":0.9067431851,
"f":0.891082129
},
"det":{
"p":0.9426057813,
"r":0.9736045002,
"f":0.9578544061
},
"amod":{
"p":0.8789473684,
"r":0.8978494624,
"f":0.8882978723
},
"obl":{
"p":0.7619367855,
"r":0.7670954638,
"f":0.7645074224
},
"mark":{
"p":0.9007220217,
"r":0.9072727273,
"f":0.9039855072
},
"ccomp":{
"p":0.7,
"r":0.6542056075,
"f":0.6763285024
},
"case":{
"p":0.9373703857,
"r":0.9572215163,
"f":0.9471919531
},
"appos":{
"p":0.7391304348,
"r":0.7212121212,
"f":0.7300613497
},
"obj":{
"p":0.7731343284,
"r":0.7908396947,
"f":0.7818867925
},
"compound:prt":{
"p":0.7736842105,
"r":0.6901408451,
"f":0.729528536
},
"xcomp":{
"p":0.6559139785,
"r":0.6654545455,
"f":0.6606498195
},
"flat":{
"p":0.7821782178,
"r":0.7539766702,
"f":0.7678185745
},
"expl:pv":{
"p":0.8,
"r":0.7272727273,
"f":0.7619047619
},
"acl":{
"p":0.5373134328,
"r":0.3673469388,
"f":0.4363636364
},
"advcl":{
"p":0.4953271028,
"r":0.4774774775,
"f":0.4862385321
},
"nummod":{
"p":0.798136646,
"r":0.8566666667,
"f":0.8263665595
},
"nmod":{
"p":0.7304785894,
"r":0.7565217391,
"f":0.7432721059
},
"cc":{
"p":0.8598484848,
"r":0.8598484848,
"f":0.8598484848
},
"conj":{
"p":0.6921985816,
"r":0.6630434783,
"f":0.6773074254
},
"nsubj:pass":{
"p":0.8333333333,
"r":0.8490566038,
"f":0.8411214953
},
"aux:pass":{
"p":0.8918918919,
"r":0.9166666667,
"f":0.904109589
},
"iobj":{
"p":0.5416666667,
"r":0.3939393939,
"f":0.4561403509
},
"cop":{
"p":0.7738515901,
"r":0.8021978022,
"f":0.7877697842
},
"acl:relcl":{
"p":0.7142857143,
"r":0.7232704403,
"f":0.71875
},
"parataxis":{
"p":0.3971291866,
"r":0.3007246377,
"f":0.3422680412
},
"expl":{
"p":0.44,
"r":0.5238095238,
"f":0.4782608696
},
"fixed":{
"p":0.676056338,
"r":0.4339963834,
"f":0.5286343612
},
"obl:agent":{
"p":0.962962963,
"r":0.8965517241,
"f":0.9285714286
},
"csubj":{
"p":0.5625,
"r":0.45,
"f":0.5
},
"orphan":{
"p":0.0,
"r":0.0,
"f":0.0
},
"dep":{
"p":0.0,
"r":0.0,
"f":0.0
}
},
"ents_p":0.7850940666,
"ents_r":0.7503457815,
"ents_f":0.7673267327,
"ents_per_type":{
"DATE":{
"p":0.0,
"r":0.0,
"f":0.0
},
"PERSON":{
"p":0.0,
"r":0.0,
"f":0.0
},
"GPE":{
"p":0.0,
"r":0.0,
"f":0.0
},
"QUANTITY":{
"p":0.0,
"r":0.0,
"f":0.0
},
"CARDINAL":{
"p":0.0,
"r":0.0,
"f":0.0
},
"ORG":{
"p":0.0,
"r":0.0,
"f":0.0
},
"EVENT":{
"p":0.0,
"r":0.0,
"f":0.0
},
"NORP":{
"p":0.0,
"r":0.0,
"f":0.0
},
"ORDINAL":{
"p":0.0,
"r":0.0,
"f":0.0
},
"LANGUAGE":{
"p":0.0,
"r":0.0,
"f":0.0
},
"FAC":{
"p":0.0,
"r":0.0,
"f":0.0
},
"WORK_OF_ART":{
"p":0.0,
"r":0.0,
"f":0.0
},
"LOC":{
"p":0.0,
"r":0.0,
"f":0.0
},
"PRODUCT":{
"p":0.0,
"r":0.0,
"f":0.0
},
"MONEY":{
"p":0.0,
"r":0.0,
"f":0.0
},
"TIME":{
"p":0.0,
"r":0.0,
"f":0.0
},
"LAW":{
"p":0.0,
"r":0.0,
"f":0.0
},
"PERCENT":{
"p":0.0,
"r":0.0,
"f":0.0
}
},
"speed":9742.936269209,
"token_acc":0.999433329,
"token_p":0.9974281853,
"token_r":0.9975586363,
"token_f":0.9974934066,
"pos_acc":0.9638822246,
"morph_acc":0.9628967172,
"morph_micro_p":0.9711903659,
"morph_micro_r":0.9546965351,
"morph_micro_f":0.9628728216,
"morph_per_feat":{
"Person":{
"p":0.9912280702,
"r":0.9722753346,
"f":0.9816602317
},
"Poss":{
"p":0.992248062,
"r":0.9808429119,
"f":0.9865125241
},
"PronType":{
"p":0.989787234,
"r":0.9667497922,
"f":0.9781328848
},
"Gender":{
"p":0.9335968379,
"r":0.9012973798,
"f":0.9171628268
},
"Number":{
"p":0.980195003,
"r":0.9630294866,
"f":0.9715364288
},
"Tense":{
"p":0.9724517906,
"r":0.970313359,
"f":0.9713813979
},
"VerbForm":{
"p":0.9609261939,
"r":0.9557394746,
"f":0.9583258163
},
"Degree":{
"p":0.9626099707,
"r":0.9432471264,
"f":0.9528301887
},
"Definite":{
"p":0.9973439575,
"r":0.9916373239,
"f":0.9944824542
},
"Case":{
"p":0.996007984,
"r":0.9940239044,
"f":0.9950149551
},
"Reflex":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Abbr":{
"p":1.0,
"r":0.5555555556,
"f":0.7142857143
}
},
"lemma_acc":0.9556229147
},
"sources":[
{
"name":"UD Dutch LassySmall v2.8",
"url":"https://github.com/UniversalDependencies/UD_Dutch-LassySmall",
"license":"CC BY-SA 4.0",
"author":"Bouma, Gosse; van Noord, Gertjan"
},
{
"name":"Dutch NER Annotations for UD LassySmall",
"url":"https://nlp.town",
"license":"CC BY-SA 4.0",
"author":"NLP Town"
},
{
"name":"UD Dutch Alpino v2.8",
"url":"https://github.com/UniversalDependencies/UD_Dutch-Alpino",
"license":"CC BY-SA 4.0",
"author":"Zeman, Daniel; \u017dabokrtsk\u00fd, Zden\u011bk; Bouma, Gosse; van Noord, Gertjan"
},
{
"name":"Explosion fastText Vectors (cbow, OSCAR Common Crawl + Wikipedia)",
"url":"https://spacy.io",
"license":"CC0",
"author":"Explosion"
}
],
"requirements":[
]
}