nl_core_news_md / meta.json
EC2 Default User
Update spaCy pipeline
6775ca6
raw history blame
No virus
19.6 kB
{
"lang":"nl",
"name":"core_news_md",
"version":"3.3.0",
"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":">=3.3.0.dev0,<3.4.0",
"spacy_git_version":"849bef2de",
"vectors":{
"width":300,
"vectors":20000,
"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=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"
],
"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":0.9481352236,
"sents_p":0.8468899522,
"sents_r":0.8888091822,
"sents_f":0.8673433672,
"dep_uas":0.8684343946,
"dep_las":0.8217698801,
"dep_las_per_type":{
"nmod:poss":{
"p":0.9487179487,
"r":0.9452554745,
"f":0.9469835466
},
"nsubj":{
"p":0.8507265522,
"r":0.8468113083,
"f":0.8487644152
},
"aux":{
"p":0.8838709677,
"r":0.9013157895,
"f":0.8925081433
},
"advmod":{
"p":0.7780656304,
"r":0.8044642857,
"f":0.7910447761
},
"root":{
"p":0.8591934381,
"r":0.9017216643,
"f":0.8799439972
},
"det":{
"p":0.9389121339,
"r":0.9710082215,
"f":0.9546904914
},
"amod":{
"p":0.8591184097,
"r":0.8906810036,
"f":0.8746150462
},
"obl":{
"p":0.7505016722,
"r":0.759647935,
"f":0.7550471063
},
"mark":{
"p":0.9027027027,
"r":0.9109090909,
"f":0.9067873303
},
"ccomp":{
"p":0.6534653465,
"r":0.6168224299,
"f":0.6346153846
},
"case":{
"p":0.9375258585,
"r":0.9597628124,
"f":0.9485140226
},
"appos":{
"p":0.6952380952,
"r":0.6636363636,
"f":0.6790697674
},
"obj":{
"p":0.7549167927,
"r":0.7618320611,
"f":0.7583586626
},
"compound:prt":{
"p":0.7889447236,
"r":0.7370892019,
"f":0.7621359223
},
"xcomp":{
"p":0.68359375,
"r":0.6363636364,
"f":0.65913371
},
"flat":{
"p":0.8029115342,
"r":0.7603393425,
"f":0.7810457516
},
"expl:pv":{
"p":0.8333333333,
"r":0.7954545455,
"f":0.8139534884
},
"acl":{
"p":0.5443037975,
"r":0.4387755102,
"f":0.4858757062
},
"advcl":{
"p":0.567839196,
"r":0.509009009,
"f":0.5368171021
},
"nummod":{
"p":0.8205128205,
"r":0.8533333333,
"f":0.8366013072
},
"nmod":{
"p":0.7213930348,
"r":0.7565217391,
"f":0.7385398981
},
"cc":{
"p":0.8582375479,
"r":0.8484848485,
"f":0.8533333333
},
"conj":{
"p":0.6833810888,
"r":0.6480978261,
"f":0.6652719665
},
"nsubj:pass":{
"p":0.8197674419,
"r":0.8867924528,
"f":0.8519637462
},
"aux:pass":{
"p":0.9116022099,
"r":0.9166666667,
"f":0.9141274238
},
"cop":{
"p":0.7820069204,
"r":0.8278388278,
"f":0.8042704626
},
"iobj":{
"p":0.7058823529,
"r":0.3636363636,
"f":0.48
},
"acl:relcl":{
"p":0.7168674699,
"r":0.748427673,
"f":0.7323076923
},
"parataxis":{
"p":0.3944954128,
"r":0.3115942029,
"f":0.3481781377
},
"fixed":{
"p":0.6704545455,
"r":0.4267631103,
"f":0.5215469613
},
"obl:agent":{
"p":0.9565217391,
"r":0.7586206897,
"f":0.8461538462
},
"expl":{
"p":0.619047619,
"r":0.619047619,
"f":0.619047619
},
"csubj":{
"p":0.6666666667,
"r":0.4,
"f":0.5
},
"dep":{
"p":0.0,
"r":0.0,
"f":0.0
},
"orphan":{
"p":0.0,
"r":0.0,
"f":0.0
}
},
"ents_p":0.77532097,
"ents_r":0.7517289073,
"ents_f":0.7633426966,
"ents_per_type":{
"PERSON":{
"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
},
"DATE":{
"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
},
"GPE":{
"p":0.0,
"r":0.0,
"f":0.0
},
"ORDINAL":{
"p":0.0,
"r":0.0,
"f":0.0
},
"LOC":{
"p":0.0,
"r":0.0,
"f":0.0
},
"FAC":{
"p":0.0,
"r":0.0,
"f":0.0
},
"LANGUAGE":{
"p":0.0,
"r":0.0,
"f":0.0
},
"TIME":{
"p":0.0,
"r":0.0,
"f":0.0
},
"WORK_OF_ART":{
"p":0.0,
"r":0.0,
"f":0.0
},
"MONEY":{
"p":0.0,
"r":0.0,
"f":0.0
},
"LAW":{
"p":0.0,
"r":0.0,
"f":0.0
},
"PRODUCT":{
"p":0.0,
"r":0.0,
"f":0.0
},
"PERCENT":{
"p":0.0,
"r":0.0,
"f":0.0
}
},
"speed":10425.5234641703,
"token_acc":0.9997165842,
"token_p":0.9974281853,
"token_r":0.9975586363,
"token_f":0.9974934066,
"pos_acc":0.9624427481,
"morph_acc":0.9582497164,
"morph_micro_p":0.9681380529,
"morph_micro_r":0.9476847425,
"morph_micro_f":0.957802218,
"morph_per_feat":{
"Person":{
"p":0.9922103213,
"r":0.9741873805,
"f":0.9831162566
},
"Poss":{
"p":0.9849056604,
"r":1.0,
"f":0.9923954373
},
"PronType":{
"p":0.9906462585,
"r":0.9684123026,
"f":0.9794031106
},
"Gender":{
"p":0.9252584151,
"r":0.8880691936,
"f":0.9062824507
},
"Number":{
"p":0.9812423124,
"r":0.9552462206,
"f":0.9680697763
},
"Tense":{
"p":0.9758698092,
"r":0.9560197911,
"f":0.9658428214
},
"VerbForm":{
"p":0.9528643945,
"r":0.9456639079,
"f":0.9492504967
},
"Degree":{
"p":0.9463768116,
"r":0.9382183908,
"f":0.9422799423
},
"Definite":{
"p":0.9955830389,
"r":0.9920774648,
"f":0.9938271605
},
"Case":{
"p":0.998003992,
"r":0.9960159363,
"f":0.9970089731
},
"Reflex":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Abbr":{
"p":1.0,
"r":0.5555555556,
"f":0.7142857143
}
},
"lemma_acc":0.9396166343
},
"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 LassySmall v2.8",
"url":"https://github.com/UniversalDependencies/UD_Dutch-LassySmall",
"license":"CC BY-SA 4.0",
"author":"Bouma, Gosse; van Noord, Gertjan"
},
{
"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":[
]
}