mk_core_news_md / meta.json
osanseviero's picture
Update spaCy pipeline
f5f19d2
raw
history blame
7.54 kB
{
"lang":"mk",
"name":"core_news_md",
"version":"3.1.0",
"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":">=3.1.0,<3.2.0",
"spacy_git_version":"caba63b74",
"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=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":0.9314809819,
"sents_p":0.768115942,
"sents_r":0.6883116883,
"sents_f":0.7260273973,
"speed":2817.6117268563,
"dep_uas":0.68633235,
"dep_las":0.5329400197,
"dep_las_per_type":{
"nsubj":{
"p":0.6216216216,
"r":0.6052631579,
"f":0.6133333333
},
"root":{
"p":0.7536231884,
"r":0.7428571429,
"f":0.7482014388
},
"cc":{
"p":0.9473684211,
"r":0.6428571429,
"f":0.7659574468
},
"relcl":{
"p":0.4230769231,
"r":0.4230769231,
"f":0.4230769231
},
"pozm":{
"p":0.6666666667,
"r":0.3636363636,
"f":0.4705882353
},
"poss":{
"p":0.0,
"r":0.0,
"f":0.0
},
"aux":{
"p":0.5714285714,
"r":0.6060606061,
"f":0.5882352941
},
"prep":{
"p":0.696969697,
"r":0.7666666667,
"f":0.7301587302
},
"iobj":{
"p":0.1666666667,
"r":0.125,
"f":0.1428571429
},
"pozv":{
"p":0.3636363636,
"r":0.2666666667,
"f":0.3076923077
},
"quantmod":{
"p":0.0,
"r":0.0,
"f":0.0
},
"att":{
"p":0.7872340426,
"r":0.7115384615,
"f":0.7474747475
},
"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":0.4202898551,
"r":0.4833333333,
"f":0.4496124031
},
"ppdo":{
"p":0.7142857143,
"r":0.3333333333,
"f":0.4545454545
},
"neg":{
"p":0.4,
"r":0.3636363636,
"f":0.380952381
},
"pobj":{
"p":0.4473684211,
"r":0.53125,
"f":0.4857142857
},
"mwe":{
"p":0.0,
"r":0.0,
"f":0.0
},
"ppio":{
"p":0.0,
"r":0.0,
"f":0.0
},
"advmod":{
"p":0.0,
"r":0.0,
"f":0.0
},
"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
}
},
"ents_p":0.7577586207,
"ents_r":0.7480851064,
"ents_f":0.7528907923,
"ents_per_type":{
"GPE":{
"p":0.8639455782,
"r":0.8985849057,
"f":0.8809248555
},
"LOC":{
"p":0.7777777778,
"r":0.5632183908,
"f":0.6533333333
},
"QUANTITY":{
"p":0.7027027027,
"r":0.6341463415,
"f":0.6666666667
},
"CARDINAL":{
"p":0.6960784314,
"r":0.7553191489,
"f":0.7244897959
},
"NORP":{
"p":0.4666666667,
"r":0.4307692308,
"f":0.448
},
"DATE":{
"p":0.7755102041,
"r":0.8028169014,
"f":0.7889273356
},
"PERCENT":{
"p":0.9411764706,
"r":1.0,
"f":0.9696969697
},
"PERSON":{
"p":0.7785234899,
"r":0.7733333333,
"f":0.7759197324
},
"ORG":{
"p":0.546875,
"r":0.7142857143,
"f":0.6194690265
},
"MONEY":{
"p":0.5,
"r":0.5,
"f":0.5
},
"ORDINAL":{
"p":0.4615384615,
"r":0.5454545455,
"f":0.5
},
"EVENT":{
"p":0.6111111111,
"r":0.6470588235,
"f":0.6285714286
},
"LANGUAGE":{
"p":0.0,
"r":0.0,
"f":0.0
},
"WORK_OF_ART":{
"p":0.5862068966,
"r":0.4146341463,
"f":0.4857142857
},
"TIME":{
"p":1.0,
"r":0.8333333333,
"f":0.9090909091
},
"FAC":{
"p":0.2222222222,
"r":0.1,
"f":0.1379310345
},
"LAW":{
"p":0.5,
"r":0.3333333333,
"f":0.4
},
"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":[
]
}