nl_core_news_sm / meta.json
adrianeboyd's picture
Update spaCy pipeline
b9d28fe
raw history blame
No virus
19.2 kB
{
"lang":"nl",
"name":"core_news_sm",
"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":0,
"vectors":0,
"keys":0,
"name":null
},
"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":0.939195673,
"sents_p":0.8500345543,
"sents_r":0.8823529412,
"sents_f":0.8658922914,
"dep_uas":0.8535422689,
"dep_las":0.80149091,
"dep_las_per_type":{
"nmod:poss":{
"p":0.9413919414,
"r":0.9379562044,
"f":0.9396709324
},
"nsubj":{
"p":0.8272907053,
"r":0.8251150559,
"f":0.8262014483
},
"aux":{
"p":0.8827361564,
"r":0.8914473684,
"f":0.8870703764
},
"advmod":{
"p":0.738874895,
"r":0.7857142857,
"f":0.7615750757
},
"root":{
"p":0.8507256393,
"r":0.8830703013,
"f":0.8665962689
},
"det":{
"p":0.9329446064,
"r":0.9692773691,
"f":0.9507640068
},
"amod":{
"p":0.8520452567,
"r":0.8772401434,
"f":0.8644591611
},
"obl":{
"p":0.7286295794,
"r":0.7271496276,
"f":0.7278888512
},
"mark":{
"p":0.8917431193,
"r":0.8836363636,
"f":0.8876712329
},
"ccomp":{
"p":0.6494845361,
"r":0.5887850467,
"f":0.6176470588
},
"case":{
"p":0.9296357616,
"r":0.9512918255,
"f":0.940339125
},
"appos":{
"p":0.7166123779,
"r":0.6666666667,
"f":0.6907378336
},
"obj":{
"p":0.7241887906,
"r":0.7496183206,
"f":0.736684171
},
"compound:prt":{
"p":0.7616580311,
"r":0.6901408451,
"f":0.724137931
},
"xcomp":{
"p":0.63099631,
"r":0.6218181818,
"f":0.6263736264
},
"flat":{
"p":0.788590604,
"r":0.7476139979,
"f":0.7675557975
},
"expl:pv":{
"p":0.7446808511,
"r":0.7954545455,
"f":0.7692307692
},
"acl":{
"p":0.4776119403,
"r":0.3265306122,
"f":0.3878787879
},
"advcl":{
"p":0.4401913876,
"r":0.4144144144,
"f":0.4269141531
},
"nummod":{
"p":0.8037974684,
"r":0.8466666667,
"f":0.8246753247
},
"nmod":{
"p":0.7025,
"r":0.7330434783,
"f":0.7174468085
},
"cc":{
"p":0.8579439252,
"r":0.8693181818,
"f":0.863593603
},
"conj":{
"p":0.6082337317,
"r":0.6222826087,
"f":0.6151779718
},
"nsubj:pass":{
"p":0.7604790419,
"r":0.7987421384,
"f":0.7791411043
},
"aux:pass":{
"p":0.8882681564,
"r":0.8833333333,
"f":0.8857938719
},
"iobj":{
"p":0.7058823529,
"r":0.3636363636,
"f":0.48
},
"dep":{
"p":0.0,
"r":0.0,
"f":0.0
},
"cop":{
"p":0.7321428571,
"r":0.7509157509,
"f":0.7414104882
},
"acl:relcl":{
"p":0.6603773585,
"r":0.6603773585,
"f":0.6603773585
},
"parataxis":{
"p":0.3092783505,
"r":0.2173913043,
"f":0.2553191489
},
"fixed":{
"p":0.6479750779,
"r":0.3761301989,
"f":0.47597254
},
"expl":{
"p":0.4210526316,
"r":0.380952381,
"f":0.4
},
"obl:agent":{
"p":0.8518518519,
"r":0.7931034483,
"f":0.8214285714
},
"csubj":{
"p":0.6,
"r":0.45,
"f":0.5142857143
},
"orphan":{
"p":0.0,
"r":0.0,
"f":0.0
}
},
"ents_p":0.7496350365,
"ents_r":0.7102351314,
"ents_f":0.7294034091,
"ents_per_type":{
"DATE":{
"p":0.0,
"r":0.0,
"f":0.0
},
"NORP":{
"p":0.0,
"r":0.0,
"f":0.0
},
"LOC":{
"p":0.0,
"r":0.0,
"f":0.0
},
"WORK_OF_ART":{
"p":0.0,
"r":0.0,
"f":0.0
},
"CARDINAL":{
"p":0.0,
"r":0.0,
"f":0.0
},
"PERSON":{
"p":0.0,
"r":0.0,
"f":0.0
},
"EVENT":{
"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
},
"FAC":{
"p":0.0,
"r":0.0,
"f":0.0
},
"LANGUAGE":{
"p":0.0,
"r":0.0,
"f":0.0
},
"ORG":{
"p":0.0,
"r":0.0,
"f":0.0
},
"QUANTITY":{
"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
},
"PERCENT":{
"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
}
},
"speed":7859.8743254531,
"token_acc":0.999433329,
"token_p":0.9974281853,
"token_r":0.9975586363,
"token_f":0.9974934066,
"pos_acc":0.9572746505,
"morph_acc":0.9504635184,
"morph_micro_p":0.9581605554,
"morph_micro_r":0.9363474935,
"morph_micro_f":0.9471284484,
"morph_per_feat":{
"Person":{
"p":0.9911154985,
"r":0.9598470363,
"f":0.9752306945
},
"Poss":{
"p":0.9921259843,
"r":0.9655172414,
"f":0.9786407767
},
"PronType":{
"p":0.9905008636,
"r":0.9534497091,
"f":0.971622194
},
"Gender":{
"p":0.906358074,
"r":0.8667005851,
"f":0.8860858257
},
"Number":{
"p":0.9747808704,
"r":0.9488100584,
"f":0.9616201456
},
"Tense":{
"p":0.9576129392,
"r":0.9439252336,
"f":0.9507198228
},
"VerbForm":{
"p":0.9392948019,
"r":0.9298308744,
"f":0.9345388788
},
"Degree":{
"p":0.9271809661,
"r":0.9238505747,
"f":0.9255127744
},
"Definite":{
"p":0.9942806863,
"r":0.9947183099,
"f":0.9944994499
},
"Case":{
"p":0.9940357853,
"r":0.9960159363,
"f":0.9950248756
},
"Reflex":{
"p":1.0,
"r":1.0,
"f":1.0
},
"Abbr":{
"p":1.0,
"r":0.5555555556,
"f":0.7142857143
}
},
"lemma_acc":0.9504328674
},
"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"
}
],
"requirements":[
]
}