mk_core_news_sm / meta.json
adrianeboyd's picture
Update spaCy pipeline
f802e47
raw history blame
No virus
6.78 kB
{
"lang":"mk",
"name":"core_news_sm",
"version":"3.5.0",
"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":">=3.5.0,<3.6.0",
"spacy_git_version":"9e0322de1",
"vectors":{
"width":0,
"vectors":0,
"keys":0,
"name":null
},
"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":0.7605633803,
"sents_r":0.7012987013,
"sents_f":0.7297297297,
"dep_uas":0.6463654224,
"dep_las":0.4754420432,
"dep_las_per_type":{
"nsubj":{
"p":0.4871794872,
"r":0.5,
"f":0.4935064935
},
"root":{
"p":0.7183098592,
"r":0.7285714286,
"f":0.7234042553
},
"cc":{
"p":0.8823529412,
"r":0.5357142857,
"f":0.6666666667
},
"relcl":{
"p":0.2777777778,
"r":0.1923076923,
"f":0.2272727273
},
"pozm":{
"p":0.6,
"r":0.2727272727,
"f":0.375
},
"poss":{
"p":0.0,
"r":0.0,
"f":0.0
},
"aux":{
"p":0.5897435897,
"r":0.696969697,
"f":0.6388888889
},
"prep":{
"p":0.7258064516,
"r":0.75,
"f":0.737704918
},
"iobj":{
"p":0.0714285714,
"r":0.125,
"f":0.0909090909
},
"pozv":{
"p":0.375,
"r":0.2,
"f":0.2608695652
},
"quantmod":{
"p":0.0,
"r":0.0,
"f":0.0
},
"att":{
"p":0.6428571429,
"r":0.5192307692,
"f":0.5744680851
},
"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":0.4098360656,
"r":0.4166666667,
"f":0.4132231405
},
"ppdo":{
"p":0.75,
"r":0.4,
"f":0.5217391304
},
"neg":{
"p":0.6,
"r":0.5454545455,
"f":0.5714285714
},
"advmod":{
"p":0.0,
"r":0.0,
"f":0.0
},
"pobj":{
"p":0.3939393939,
"r":0.40625,
"f":0.4
},
"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
},
"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":1969.1332574144,
"ents_p":0.7264808362,
"ents_r":0.709787234,
"ents_f":0.7180370211,
"ents_per_type":{
"LOC":{
"p":0.7288135593,
"r":0.4942528736,
"f":0.5890410959
},
"GPE":{
"p":0.8823529412,
"r":0.8844339623,
"f":0.8833922261
},
"QUANTITY":{
"p":0.7631578947,
"r":0.7073170732,
"f":0.7341772152
},
"PERSON":{
"p":0.6585365854,
"r":0.72,
"f":0.6878980892
},
"CARDINAL":{
"p":0.6168224299,
"r":0.7021276596,
"f":0.6567164179
},
"DATE":{
"p":0.7253521127,
"r":0.7253521127,
"f":0.7253521127
},
"NORP":{
"p":0.4509803922,
"r":0.3538461538,
"f":0.3965517241
},
"PRODUCT":{
"p":0.0,
"r":0.0,
"f":0.0
},
"ORDINAL":{
"p":0.5,
"r":0.5454545455,
"f":0.5217391304
},
"PERCENT":{
"p":1.0,
"r":1.0,
"f":1.0
},
"MONEY":{
"p":0.0,
"r":0.0,
"f":0.0
},
"ORG":{
"p":0.5087719298,
"r":0.5918367347,
"f":0.5471698113
},
"WORK_OF_ART":{
"p":0.5277777778,
"r":0.4634146341,
"f":0.4935064935
},
"LANGUAGE":{
"p":0.0,
"r":0.0,
"f":0.0
},
"FAC":{
"p":0.25,
"r":0.15,
"f":0.1875
},
"TIME":{
"p":0.6666666667,
"r":0.6666666667,
"f":0.6666666667
},
"EVENT":{
"p":0.5882352941,
"r":0.5882352941,
"f":0.5882352941
},
"LAW":{
"p":0.0,
"r":0.0,
"f":0.0
}
},
"pos_acc":0.9198813056
},
"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"
}
],
"requirements":[
]
}