{ "lang":"mk", "name":"core_news_md", "version":"3.3.0", "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":">=3.3.0.dev0,<3.4.0", "spacy_git_version":"849bef2de", "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" ], "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":0.7536231884, "sents_r":0.6753246753, "sents_f":0.7123287671, "dep_uas":0.6916256158, "dep_las":0.5300492611, "dep_las_per_type":{ "nsubj":{ "p":0.6046511628, "r":0.6842105263, "f":0.6419753086 }, "root":{ "p":0.7971014493, "r":0.7857142857, "f":0.7913669065 }, "cc":{ "p":0.875, "r":0.5, "f":0.6363636364 }, "relcl":{ "p":0.4444444444, "r":0.4615384615, "f":0.4528301887 }, "pozm":{ "p":1.0, "r":0.3636363636, "f":0.5333333333 }, "poss":{ "p":0.0, "r":0.0, "f":0.0 }, "aux":{ "p":0.6, "r":0.6363636364, "f":0.6176470588 }, "prep":{ "p":0.7142857143, "r":0.75, "f":0.7317073171 }, "iobj":{ "p":0.0, "r":0.0, "f":0.0 }, "pozv":{ "p":0.1428571429, "r":0.0666666667, "f":0.0909090909 }, "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":0.0153846154, "r":0.3333333333, "f":0.0294117647 }, "dobj":{ "p":0.4576271186, "r":0.45, "f":0.4537815126 }, "ppdo":{ "p":0.5714285714, "r":0.2666666667, "f":0.3636363636 }, "neg":{ "p":0.5555555556, "r":0.4545454545, "f":0.5 }, "pobj":{ "p":0.4210526316, "r":0.5, "f":0.4571428571 }, "mwe":{ "p":0.0, "r":0.0, "f":0.0 }, "ppio":{ "p":0.0, "r":0.0, "f":0.0 }, "advmod":{ "p":0.3333333333, "r":0.5, "f":0.4 }, "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":2181.9209832256, "ents_p":0.7543402778, "ents_r":0.7395744681, "ents_f":0.7468844005, "ents_per_type":{ "GPE":{ "p":0.8643678161, "r":0.8867924528, "f":0.8754365541 }, "LOC":{ "p":0.7246376812, "r":0.5747126437, "f":0.641025641 }, "QUANTITY":{ "p":0.7435897436, "r":0.7073170732, "f":0.725 }, "DATE":{ "p":0.7142857143, "r":0.7042253521, "f":0.7092198582 }, "CARDINAL":{ "p":0.6930693069, "r":0.7446808511, "f":0.7179487179 }, "NORP":{ "p":0.5192307692, "r":0.4153846154, "f":0.4615384615 }, "PERSON":{ "p":0.7756410256, "r":0.8066666667, "f":0.7908496732 }, "ORG":{ "p":0.5666666667, "r":0.693877551, "f":0.623853211 }, "MONEY":{ "p":1.0, "r":0.5, "f":0.6666666667 }, "ORDINAL":{ "p":0.5384615385, "r":0.6363636364, "f":0.5833333333 }, "PERCENT":{ "p":0.9411764706, "r":1.0, "f":0.9696969697 }, "WORK_OF_ART":{ "p":0.7, "r":0.512195122, "f":0.5915492958 }, "LANGUAGE":{ "p":0.0, "r":0.0, "f":0.0 }, "FAC":{ "p":0.0833333333, "r":0.05, "f":0.0625 }, "TIME":{ "p":1.0, "r":0.8333333333, "f":0.9090909091 }, "EVENT":{ "p":0.6111111111, "r":0.6470588235, "f":0.6285714286 }, "LAW":{ "p":0.0, "r":0.0, "f":0.0 }, "PRODUCT":{ "p":0.0, "r":0.0, "f":0.0 } }, "pos_acc":0.9309414621 }, "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":[ ] }