{ "lang":"mk", "name":"core_news_sm", "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":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=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":0.9209603453, "sents_p":0.768115942, "sents_r":0.6883116883, "sents_f":0.7260273973, "speed":2753.0743975125, "dep_uas":0.6457311089, "dep_las":0.4749754661, "dep_las_per_type":{ "nsubj":{ "p":0.525, "r":0.5526315789, "f":0.5384615385 }, "root":{ "p":0.6956521739, "r":0.6857142857, "f":0.690647482 }, "cc":{ "p":0.7368421053, "r":0.5, "f":0.5957446809 }, "relcl":{ "p":0.380952381, "r":0.3076923077, "f":0.3404255319 }, "pozm":{ "p":0.6, "r":0.2727272727, "f":0.375 }, "poss":{ "p":0.0, "r":0.0, "f":0.0 }, "aux":{ "p":0.5454545455, "r":0.7272727273, "f":0.6233766234 }, "prep":{ "p":0.703125, "r":0.75, "f":0.7258064516 }, "iobj":{ "p":0.0, "r":0.0, "f":0.0 }, "pozv":{ "p":0.125, "r":0.0666666667, "f":0.0869565217 }, "quantmod":{ "p":0.0, "r":0.0, "f":0.0 }, "att":{ "p":0.6222222222, "r":0.5384615385, "f":0.5773195876 }, "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":0.3521126761, "r":0.4166666667, "f":0.3816793893 }, "ppdo":{ "p":0.6666666667, "r":0.4, "f":0.5 }, "neg":{ "p":0.5555555556, "r":0.4545454545, "f":0.5 }, "pobj":{ "p":0.3823529412, "r":0.40625, "f":0.3939393939 }, "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":0.3333333333, "r":0.5, "f":0.4 }, "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":0.7100802855, "ents_r":0.6774468085, "ents_f":0.6933797909, "ents_per_type":{ "NORP":{ "p":0.4893617021, "r":0.3538461538, "f":0.4107142857 }, "GPE":{ "p":0.8321995465, "r":0.8655660377, "f":0.8485549133 }, "LOC":{ "p":0.649122807, "r":0.4252873563, "f":0.5138888889 }, "CARDINAL":{ "p":0.6847826087, "r":0.670212766, "f":0.6774193548 }, "QUANTITY":{ "p":0.6285714286, "r":0.5365853659, "f":0.5789473684 }, "FAC":{ "p":0.2, "r":0.1, "f":0.1333333333 }, "ORG":{ "p":0.4558823529, "r":0.6326530612, "f":0.5299145299 }, "PERSON":{ "p":0.68, "r":0.68, "f":0.68 }, "ORDINAL":{ "p":0.4545454545, "r":0.4545454545, "f":0.4545454545 }, "DATE":{ "p":0.7183098592, "r":0.7183098592, "f":0.7183098592 }, "MONEY":{ "p":0.5, "r":1.0, "f":0.6666666667 }, "PERCENT":{ "p":1.0, "r":1.0, "f":1.0 }, "WORK_OF_ART":{ "p":0.5238095238, "r":0.2682926829, "f":0.3548387097 }, "LANGUAGE":{ "p":0.0, "r":0.0, "f":0.0 }, "TIME":{ "p":1.0, "r":0.8333333333, "f":0.9090909091 }, "EVENT":{ "p":0.4210526316, "r":0.4705882353, "f":0.4444444444 }, "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" } ], "requirements":[ ] }