mk_core_news_lg / meta.json
osanseviero's picture
osanseviero HF staff
Update spaCy pipeline
cc93730
raw history blame
No virus
7.46 kB
{
"lang":"mk",
"name":"core_news_lg",
"version":"3.1.0",
"description":"Macedonian pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, ner, attribute_ruler, lemmatizer.",
"author":"Explosion",
"email":"contact@explosion.ai",
"url":"https://explosion.ai",
"license":"CC BY-SA 4.0",
"spacy_version":">=3.1.0,<3.2.0",
"spacy_git_version":"caba63b74",
"vectors":{
"width":300,
"vectors":274587,
"keys":274587,
"name":"mk_vectors"
},
"labels":{
"morphologizer":[
"POS=PROPN",
"POS=AUX",
"POS=ADJ",
"POS=NOUN",
"POS=ADP",
"POS=PUNCT",
"POS=CONJ",
"POS=NUM",
"POS=VERB",
"POS=PRON",
"POS=ADV",
"POS=SCONJ",
"POS=PART",
"POS=SYM",
"POS=X",
"_",
"POS=INTJ"
],
"parser":[
"ROOT",
"advmod",
"att",
"aux",
"cc",
"dep",
"det",
"dobj",
"iobj",
"neg",
"nsubj",
"pobj",
"poss",
"pozm",
"pozv",
"prep",
"punct",
"relcl"
],
"senter":[
"I",
"S"
],
"attribute_ruler":[
],
"lemmatizer":[
],
"ner":[
"CARDINAL",
"DATE",
"EVENT",
"FAC",
"GPE",
"LANGUAGE",
"LAW",
"LOC",
"MONEY",
"NORP",
"ORDINAL",
"ORG",
"PERCENT",
"PERSON",
"PRODUCT",
"QUANTITY",
"TIME",
"WORK_OF_ART"
]
},
"pipeline":[
"morphologizer",
"parser",
"attribute_ruler",
"lemmatizer",
"ner"
],
"components":[
"morphologizer",
"parser",
"senter",
"attribute_ruler",
"lemmatizer",
"ner"
],
"disabled":[
"senter"
],
"performance":{
"token_acc":1.0,
"pos_acc":0.9328297815,
"sents_p":0.7042253521,
"sents_r":0.6493506494,
"sents_f":0.6756756757,
"speed":2724.4873933937,
"dep_uas":0.6561886051,
"dep_las":0.510805501,
"dep_las_per_type":{
"nsubj":{
"p":0.5348837209,
"r":0.6052631579,
"f":0.5679012346
},
"root":{
"p":0.6478873239,
"r":0.6571428571,
"f":0.6524822695
},
"cc":{
"p":0.85,
"r":0.6071428571,
"f":0.7083333333
},
"relcl":{
"p":0.4,
"r":0.3846153846,
"f":0.3921568627
},
"pozm":{
"p":0.8,
"r":0.3636363636,
"f":0.5
},
"poss":{
"p":0.0,
"r":0.0,
"f":0.0
},
"aux":{
"p":0.5789473684,
"r":0.6666666667,
"f":0.6197183099
},
"prep":{
"p":0.7076923077,
"r":0.7666666667,
"f":0.736
},
"iobj":{
"p":0.1428571429,
"r":0.125,
"f":0.1333333333
},
"pozv":{
"p":0.4285714286,
"r":0.2,
"f":0.2727272727
},
"quantmod":{
"p":0.0,
"r":0.0,
"f":0.0
},
"att":{
"p":0.6727272727,
"r":0.7115384615,
"f":0.691588785
},
"det":{
"p":0.0,
"r":0.0,
"f":0.0
},
"num":{
"p":0.0,
"r":0.0,
"f":0.0
},
"dep":{
"p":0.0,
"r":0.0,
"f":0.0
},
"dobj":{
"p":0.4528301887,
"r":0.4,
"f":0.4247787611
},
"ppdo":{
"p":0.7142857143,
"r":0.3333333333,
"f":0.4545454545
},
"neg":{
"p":0.625,
"r":0.4545454545,
"f":0.5263157895
},
"pobj":{
"p":0.3902439024,
"r":0.5,
"f":0.4383561644
},
"mwe":{
"p":0.0,
"r":0.0,
"f":0.0
},
"ppio":{
"p":0.0,
"r":0.0,
"f":0.0
},
"appos":{
"p":0.0,
"r":0.0,
"f":0.0
},
"advmod":{
"p":0.5,
"r":0.5,
"f":0.5
},
"advcl":{
"p":0.0,
"r":0.0,
"f":0.0
},
"number":{
"p":0.0,
"r":0.0,
"f":0.0
},
"amod":{
"p":0.0,
"r":0.0,
"f":0.0
},
"_":{
"p":0.0,
"r":0.0,
"f":0.0
},
"acl":{
"p":0.0,
"r":0.0,
"f":0.0
},
"pozn":{
"p":0.0,
"r":0.0,
"f":0.0
},
"pozk":{
"p":0.0,
"r":0.0,
"f":0.0
}
},
"ents_p":0.7549611734,
"ents_r":0.7446808511,
"ents_f":0.7497857755,
"ents_per_type":{
"GPE":{
"p":0.8713318284,
"r":0.9103773585,
"f":0.8904267589
},
"LOC":{
"p":0.7419354839,
"r":0.5287356322,
"f":0.6174496644
},
"QUANTITY":{
"p":0.6,
"r":0.512195122,
"f":0.5526315789
},
"CARDINAL":{
"p":0.6847826087,
"r":0.670212766,
"f":0.6774193548
},
"NORP":{
"p":0.4827586207,
"r":0.4307692308,
"f":0.4552845528
},
"ORG":{
"p":0.53125,
"r":0.693877551,
"f":0.6017699115
},
"DATE":{
"p":0.7718120805,
"r":0.8098591549,
"f":0.7903780069
},
"TIME":{
"p":0.8333333333,
"r":0.8333333333,
"f":0.8333333333
},
"MONEY":{
"p":1.0,
"r":0.5,
"f":0.6666666667
},
"ORDINAL":{
"p":0.4285714286,
"r":0.5454545455,
"f":0.48
},
"PERCENT":{
"p":1.0,
"r":0.9375,
"f":0.9677419355
},
"PERSON":{
"p":0.8,
"r":0.8266666667,
"f":0.8131147541
},
"FAC":{
"p":0.0833333333,
"r":0.05,
"f":0.0625
},
"LANGUAGE":{
"p":0.0,
"r":0.0,
"f":0.0
},
"WORK_OF_ART":{
"p":0.6774193548,
"r":0.512195122,
"f":0.5833333333
},
"EVENT":{
"p":0.5294117647,
"r":0.5294117647,
"f":0.5294117647
},
"LAW":{
"p":0.0,
"r":0.0,
"f":0.0
},
"PRODUCT":{
"p":0.0,
"r":0.0,
"f":0.0
}
}
},
"sources":[
{
"name":"Macedonian Corpus",
"url":"https://blog.netcetera.com/macedonian-spacy-f3c85484777f",
"license":"CC BY-SA 4.0",
"author":"Damjan Zlatinov, Melanija Gerasimovska, Borijan Georgievski, Marija Todosovska"
},
{
"name":"Macedonian Corpus",
"url":"https://blog.netcetera.com/macedonian-spacy-f3c85484777f",
"license":"CC BY-SA 4.0",
"author":"Damjan Zlatinov, Melanija Gerasimovska, Borijan Georgievski, Marija Todosovska"
},
{
"name":"Macedonian Corpus",
"url":"https://blog.netcetera.com/macedonian-spacy-f3c85484777f",
"license":"CC BY-SA 4.0",
"author":"Damjan Zlatinov, Melanija Gerasimovska, Borijan Georgievski, Marija Todosovska"
},
{
"name":"spaCy lookups data",
"author":"Explosion",
"url":"https://github.com/explosion/spacy-lookups-data",
"license":"MIT"
},
{
"name":"Explosion fastText Vectors (cbow, OSCAR Common Crawl + Wikipedia)",
"url":"https://spacy.io",
"license":"CC0",
"author":"Explosion"
}
],
"requirements":[
]
}