nl_core_news_lg / meta.json
Adriane Boyd
Update spaCy pipeline
a56a017
raw history blame
No virus
19.4 kB
{
"lang":"nl",
"name":"core_news_lg",
"version":"3.4.0",
"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":">=3.4.0,<3.5.0",
"spacy_git_version":"dd038b536",
"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":0.9538495093,
"sents_p":0.8619972261,
"sents_r":0.8916786227,
"sents_f":0.8765867419,
"dep_uas":0.8682669641,
"dep_las":0.8246685762,
"dep_las_per_type":{
"nmod:poss":{
"p":0.9522058824,
"r":0.9452554745,
"f":0.9487179487
},
"nsubj":{
"p":0.8483072917,
"r":0.8566732413,
"f":0.8524697416
},
"aux":{
"p":0.9150326797,
"r":0.9210526316,
"f":0.9180327869
},
"advmod":{
"p":0.7968337731,
"r":0.8089285714,
"f":0.8028356225
},
"root":{
"p":0.8689320388,
"r":0.8988522238,
"f":0.8836389281
},
"det":{
"p":0.9430724152,
"r":0.9749026395,
"f":0.9587234043
},
"amod":{
"p":0.8828193833,
"r":0.8978494624,
"f":0.8902709907
},
"obl":{
"p":0.7610619469,
"r":0.7569397427,
"f":0.7589952478
},
"mark":{
"p":0.8918918919,
"r":0.9,
"f":0.8959276018
},
"ccomp":{
"p":0.6979166667,
"r":0.6261682243,
"f":0.6600985222
},
"case":{
"p":0.9368811881,
"r":0.9618805591,
"f":0.9492163009
},
"appos":{
"p":0.707165109,
"r":0.6878787879,
"f":0.6973886329
},
"obj":{
"p":0.7573529412,
"r":0.786259542,
"f":0.7715355805
},
"compound:prt":{
"p":0.7692307692,
"r":0.7042253521,
"f":0.7352941176
},
"xcomp":{
"p":0.6642599278,
"r":0.6690909091,
"f":0.6666666667
},
"flat":{
"p":0.8215527231,
"r":0.7518557794,
"f":0.7851605759
},
"expl:pv":{
"p":0.7619047619,
"r":0.7272727273,
"f":0.7441860465
},
"acl":{
"p":0.4404761905,
"r":0.3775510204,
"f":0.4065934066
},
"advcl":{
"p":0.5577889447,
"r":0.5,
"f":0.5273159145
},
"nummod":{
"p":0.8291139241,
"r":0.8733333333,
"f":0.8506493506
},
"nmod":{
"p":0.7201986755,
"r":0.7565217391,
"f":0.737913486
},
"cc":{
"p":0.8536585366,
"r":0.8617424242,
"f":0.8576814326
},
"conj":{
"p":0.6527777778,
"r":0.6385869565,
"f":0.6456043956
},
"nsubj:pass":{
"p":0.8128654971,
"r":0.8742138365,
"f":0.8424242424
},
"aux:pass":{
"p":0.9095744681,
"r":0.95,
"f":0.9293478261
},
"cop":{
"p":0.7900355872,
"r":0.8131868132,
"f":0.8014440433
},
"parataxis":{
"p":0.3349282297,
"r":0.2536231884,
"f":0.2886597938
},
"acl:relcl":{
"p":0.701863354,
"r":0.7106918239,
"f":0.70625
},
"expl":{
"p":0.4166666667,
"r":0.4761904762,
"f":0.4444444444
},
"iobj":{
"p":0.6470588235,
"r":0.3333333333,
"f":0.44
},
"fixed":{
"p":0.7255434783,
"r":0.4828209765,
"f":0.5798045603
},
"obl:agent":{
"p":0.8387096774,
"r":0.8965517241,
"f":0.8666666667
},
"csubj":{
"p":0.45,
"r":0.45,
"f":0.45
},
"dep":{
"p":0.0,
"r":0.0,
"f":0.0
},
"orphan":{
"p":0.0,
"r":0.0,
"f":0.0
}
},
"ents_p":0.7845934379,
"ents_r":0.7607192254,
"ents_f":0.7724719101,
"ents_per_type":{
"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
},
"WORK_OF_ART":{
"p":0.0,
"r":0.0,
"f":0.0
},
"PRODUCT":{
"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
},
"DATE":{
"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
},
"TIME":{
"p":0.0,
"r":0.0,
"f":0.0
},
"PERCENT":{
"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
},
"MONEY":{
"p":0.0,
"r":0.0,
"f":0.0
},
"LAW":{
"p":0.0,
"r":0.0,
"f":0.0
}
},
"speed":10089.2857654723,
"token_acc":0.9997165842,
"token_p":0.9974281853,
"token_r":0.9975586363,
"token_f":0.9974934066,
"pos_acc":0.9666739368,
"morph_acc":0.9639000982,
"morph_micro_p":0.9741415265,
"morph_micro_r":0.9571096845,
"morph_micro_f":0.965550503,
"morph_per_feat":{
"Person":{
"p":0.994157741,
"r":0.9760994264,
"f":0.9850458273
},
"Poss":{
"p":0.9886363636,
"r":1.0,
"f":0.9942857143
},
"PronType":{
"p":0.9914965986,
"r":0.9692435578,
"f":0.9802437999
},
"Gender":{
"p":0.9321944809,
"r":0.9023149326,
"f":0.9170113754
},
"Number":{
"p":0.9844227245,
"r":0.9648256249,
"f":0.9745256633
},
"Tense":{
"p":0.9838530067,
"r":0.9714128642,
"f":0.977593361
},
"VerbForm":{
"p":0.9687726943,
"r":0.9600575747,
"f":0.9643954455
},
"Degree":{
"p":0.9598246896,
"r":0.9439655172,
"f":0.9518290474
},
"Definite":{
"p":0.9964757709,
"r":0.9955985915,
"f":0.9960369881
},
"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":0.9568877162
},
"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":[
]
}