nucci's picture
Update spaCy pipeline
9441f36
{
"lang":"sv",
"name":"pipeline",
"version":"0.0.0",
"description":"This is a transformer-based pipeline for Swedish, which includes tagger, parser, ner and lemmatizer modules. The model was trained on UD Treebanks and the SUC 3.0 dataset at the National Library of Sweden by KBLab. Warning: the lemmatizer is not based on a statistical model and its performance is a bit erratic, so use at your own risk!",
"author":"KBLab",
"email":"elena.fano@kb.se",
"url":"https://kb-labb.github.io/",
"license":"mit",
"spacy_version":">=3.0.6,<3.1.0",
"spacy_git_version":"91a3cab1c",
"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"
],
"parser":[
"ROOT",
"acl",
"acl:cleft",
"acl:relcl",
"advcl",
"advmod",
"amod",
"appos",
"aux",
"aux:pass",
"case",
"cc",
"ccomp",
"compound",
"compound:prt",
"conj",
"cop",
"csubj",
"dep",
"det",
"discourse",
"dislocated",
"expl",
"fixed",
"flat",
"flat:name",
"iobj",
"mark",
"nmod",
"nmod:poss",
"nsubj",
"nsubj:pass",
"nummod",
"obj",
"obl",
"obl:agent",
"parataxis",
"punct",
"xcomp"
],
"transformer_ner":[
],
"ner":[
"EVN",
"LOC",
"LOC/LOC",
"LOC/ORG",
"LOC/PRS",
"MSR",
"OBJ",
"ORG",
"ORG/PRS",
"PRS",
"PRS/WRK",
"TME",
"WRK"
],
"attribute_ruler":[
],
"lemmatizer":[
]
},
"pipeline":[
"transformer",
"tagger",
"parser",
"transformer_ner",
"ner",
"attribute_ruler",
"lemmatizer"
],
"components":[
"transformer",
"tagger",
"parser",
"transformer_ner",
"ner",
"attribute_ruler",
"lemmatizer"
],
"disabled":[
],
"performance":{
"dep_las_per_type":{
"nsubj":{
"p":0.9362389023,
"r":0.9411764706,
"f":0.9387011936
},
"root":{
"p":0.9250960307,
"r":0.9407552083,
"f":0.9328599096
},
"case":{
"p":0.9461899603,
"r":0.953073845,
"f":0.9496194273
},
"det":{
"p":0.9752342704,
"r":0.976541555,
"f":0.9758874749
},
"obl":{
"p":0.8194130926,
"r":0.829240434,
"f":0.8242974737
},
"nsubj:pass":{
"p":0.905511811,
"r":0.905511811,
"f":0.905511811
},
"acl:relcl":{
"p":0.8390501319,
"r":0.8548387097,
"f":0.8468708389
},
"advmod":{
"p":0.8364808844,
"r":0.8578176665,
"f":0.8470149254
},
"amod":{
"p":0.9642160052,
"r":0.9530546624,
"f":0.9586028461
},
"obl:agent":{
"p":0.5454545455,
"r":0.6,
"f":0.5714285714
},
"aux":{
"p":0.9682320442,
"r":0.972260749,
"f":0.9702422145
},
"nmod:poss":{
"p":0.9770642202,
"r":0.97856049,
"f":0.9778117827
},
"obj":{
"p":0.9472182596,
"r":0.9215822346,
"f":0.9342244108
},
"nmod":{
"p":0.7784926471,
"r":0.7763519707,
"f":0.7774208352
},
"mark":{
"p":0.9313408724,
"r":0.9194577352,
"f":0.9253611557
},
"advcl":{
"p":0.7108910891,
"r":0.7108910891,
"f":0.7108910891
},
"cop":{
"p":0.8858921162,
"r":0.9364035088,
"f":0.9104477612
},
"xcomp":{
"p":0.8351955307,
"r":0.7400990099,
"f":0.7847769029
},
"cc":{
"p":0.9250440917,
"r":0.9242290749,
"f":0.9246364037
},
"conj":{
"p":0.7889060092,
"r":0.7810831426,
"f":0.7849750862
},
"appos":{
"p":0.4180327869,
"r":0.4146341463,
"f":0.4163265306
},
"acl":{
"p":0.7630057803,
"r":0.6470588235,
"f":0.700265252
},
"iobj":{
"p":0.813559322,
"r":0.8,
"f":0.8067226891
},
"compound:prt":{
"p":0.8035714286,
"r":0.7287449393,
"f":0.7643312102
},
"fixed":{
"p":0.8652849741,
"r":0.7713625866,
"f":0.8156288156
},
"parataxis":{
"p":0.45,
"r":0.525974026,
"f":0.4850299401
},
"expl":{
"p":0.6815286624,
"r":0.7086092715,
"f":0.6948051948
},
"csubj":{
"p":0.6507936508,
"r":0.640625,
"f":0.6456692913
},
"dep":{
"p":0.0,
"r":0.0,
"f":0.0
},
"ccomp":{
"p":0.7544642857,
"r":0.8203883495,
"f":0.7860465116
},
"nummod":{
"p":0.8425925926,
"r":0.8504672897,
"f":0.8465116279
},
"aux:pass":{
"p":0.9565217391,
"r":0.5789473684,
"f":0.7213114754
},
"dislocated":{
"p":0.4791666667,
"r":0.2804878049,
"f":0.3538461538
},
"acl:cleft":{
"p":0.5172413793,
"r":0.8333333333,
"f":0.6382978723
},
"flat:name":{
"p":0.8333333333,
"r":0.9090909091,
"f":0.8695652174
},
"csubj:pass":{
"p":0.0,
"r":0.0,
"f":0.0
},
"discourse":{
"p":0.7692307692,
"r":0.6818181818,
"f":0.7228915663
},
"orphan":{
"p":0.0,
"r":0.0,
"f":0.0
},
"vocative":{
"p":0.0,
"r":0.0,
"f":0.0
},
"flat":{
"p":0.8681318681,
"r":0.8404255319,
"f":0.8540540541
},
"compound":{
"p":0.5,
"r":0.7272727273,
"f":0.5925925926
},
"reparandum":{
"p":0.0,
"r":0.0,
"f":0.0
}
},
"sents_p":0.9212548015,
"sents_r":0.9368489583,
"tag_acc":0.9818079056,
"dep_uas":0.9198832946,
"dep_las":0.883373418,
"sents_f":0.9289864429,
"transformer_loss":3996.3977112946,
"tagger_loss":304.7223157457,
"parser_loss":17219.7631057223
}
}