mk_core_news_md / meta.json
adrianeboyd's picture
Update spaCy pipeline
470f9da
{
"lang":"mk",
"name":"core_news_md",
"version":"3.7.0",
"description":"Macedonian pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, ner, attribute_ruler, lemmatizer.",
"author":"Explosion",
"email":"[email protected]",
"url":"https://explosion.ai",
"license":"CC BY-SA 4.0",
"spacy_version":">=3.7.0,<3.8.0",
"spacy_git_version":"6b4f77441",
"vectors":{
"width":300,
"vectors":20000,
"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=SPACE",
"POS=X",
"POS=INTJ"
],
"parser":[
"ROOT",
"advmod",
"att",
"aux",
"cc",
"dep",
"det",
"dobj",
"iobj",
"neg",
"nsubj",
"pobj",
"poss",
"pozm",
"pozv",
"prep",
"punct",
"relcl"
],
"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,
"token_p":1.0,
"token_r":1.0,
"token_f":1.0,
"sents_p":0.8,
"sents_r":0.6753246753,
"sents_f":0.7323943662,
"dep_uas":0.6771344455,
"dep_las":0.5201177625,
"dep_las_per_type":{
"nsubj":{
"p":0.6756756757,
"r":0.6578947368,
"f":0.6666666667
},
"root":{
"p":0.7692307692,
"r":0.7142857143,
"f":0.7407407407
},
"cc":{
"p":0.8947368421,
"r":0.6071428571,
"f":0.7234042553
},
"relcl":{
"p":0.4137931034,
"r":0.4615384615,
"f":0.4363636364
},
"pozm":{
"p":0.75,
"r":0.2727272727,
"f":0.4
},
"poss":{
"p":0.0,
"r":0.0,
"f":0.0
},
"aux":{
"p":0.4523809524,
"r":0.5757575758,
"f":0.5066666667
},
"prep":{
"p":0.737704918,
"r":0.75,
"f":0.7438016529
},
"iobj":{
"p":0.0,
"r":0.0,
"f":0.0
},
"pozv":{
"p":0.2,
"r":0.1333333333,
"f":0.16
},
"quantmod":{
"p":0.0,
"r":0.0,
"f":0.0
},
"att":{
"p":0.7555555556,
"r":0.6538461538,
"f":0.7010309278
},
"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":0.4411764706,
"r":0.5,
"f":0.46875
},
"ppdo":{
"p":0.6666666667,
"r":0.2666666667,
"f":0.380952381
},
"neg":{
"p":0.5555555556,
"r":0.4545454545,
"f":0.5
},
"pobj":{
"p":0.4090909091,
"r":0.5625,
"f":0.4736842105
},
"mwe":{
"p":0.0,
"r":0.0,
"f":0.0
},
"ppio":{
"p":0.0,
"r":0.0,
"f":0.0
},
"advmod":{
"p":0.5,
"r":0.5,
"f":0.5
},
"appos":{
"p":0.0,
"r":0.0,
"f":0.0
},
"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
}
},
"speed":1771.1077774905,
"ents_p":0.7472245944,
"ents_r":0.7446808511,
"ents_f":0.7459505541,
"ents_per_type":{
"GPE":{
"p":0.8711943794,
"r":0.8773584906,
"f":0.8742655699
},
"LOC":{
"p":0.6933333333,
"r":0.5977011494,
"f":0.6419753086
},
"QUANTITY":{
"p":0.725,
"r":0.7073170732,
"f":0.7160493827
},
"CARDINAL":{
"p":0.68,
"r":0.7234042553,
"f":0.7010309278
},
"DATE":{
"p":0.7397260274,
"r":0.7605633803,
"f":0.75
},
"PERSON":{
"p":0.7834394904,
"r":0.82,
"f":0.8013029316
},
"ORG":{
"p":0.5737704918,
"r":0.7142857143,
"f":0.6363636364
},
"NORP":{
"p":0.4262295082,
"r":0.4,
"f":0.4126984127
},
"MONEY":{
"p":1.0,
"r":1.0,
"f":1.0
},
"ORDINAL":{
"p":0.5,
"r":0.6363636364,
"f":0.56
},
"PERCENT":{
"p":1.0,
"r":1.0,
"f":1.0
},
"WORK_OF_ART":{
"p":0.6111111111,
"r":0.5365853659,
"f":0.5714285714
},
"LANGUAGE":{
"p":0.0,
"r":0.0,
"f":0.0
},
"TIME":{
"p":1.0,
"r":0.6666666667,
"f":0.8
},
"FAC":{
"p":0.2222222222,
"r":0.1,
"f":0.1379310345
},
"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
}
},
"pos_acc":0.9260857837
},
"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":"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":[
]
}