{ "lang":"mk", "name":"core_news_md", "version":"3.4.0", "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":">=3.4.0,<3.5.0", "spacy_git_version":"dd038b536", "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":0.6666666667, "sents_r":0.6493506494, "sents_f":0.6578947368, "dep_uas":0.6836434868, "dep_las":0.5190989226, "dep_las_per_type":{ "nsubj":{ "p":0.6857142857, "r":0.6315789474, "f":0.6575342466 }, "root":{ "p":0.76, "r":0.8142857143, "f":0.7862068966 }, "cc":{ "p":0.8888888889, "r":0.5714285714, "f":0.6956521739 }, "relcl":{ "p":0.4210526316, "r":0.3076923077, "f":0.3555555556 }, "pozm":{ "p":0.8333333333, "r":0.4545454545, "f":0.5882352941 }, "poss":{ "p":0.0, "r":0.0, "f":0.0 }, "aux":{ "p":0.5882352941, "r":0.6060606061, "f":0.5970149254 }, "prep":{ "p":0.6825396825, "r":0.7166666667, "f":0.6991869919 }, "iobj":{ "p":0.0, "r":0.0, "f":0.0 }, "pozv":{ "p":0.1818181818, "r":0.1333333333, "f":0.1538461538 }, "quantmod":{ "p":0.0, "r":0.0, "f":0.0 }, "att":{ "p":0.7254901961, "r":0.7115384615, "f":0.7184466019 }, "det":{ "p":0.0, "r":0.0, "f":0.0 }, "num":{ "p":0.0, "r":0.0, "f":0.0 }, "dep":{ "p":0.0138888889, "r":0.3333333333, "f":0.0266666667 }, "dobj":{ "p":0.4126984127, "r":0.4333333333, "f":0.4227642276 }, "ppdo":{ "p":0.7142857143, "r":0.3333333333, "f":0.4545454545 }, "neg":{ "p":0.5555555556, "r":0.4545454545, "f":0.5 }, "pobj":{ "p":0.5, "r":0.5, "f":0.5 }, "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":0.0, "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":2245.2550240296, "ents_p":0.7373737374, "ents_r":0.7455319149, "ents_f":0.7414303851, "ents_per_type":{ "LOC":{ "p":0.6666666667, "r":0.5747126437, "f":0.6172839506 }, "GPE":{ "p":0.8646788991, "r":0.8891509434, "f":0.876744186 }, "QUANTITY":{ "p":0.6511627907, "r":0.6829268293, "f":0.6666666667 }, "CARDINAL":{ "p":0.7052631579, "r":0.7127659574, "f":0.708994709 }, "DATE":{ "p":0.7465753425, "r":0.7676056338, "f":0.7569444444 }, "PRODUCT":{ "p":0.0, "r":0.0, "f":0.0 }, "NORP":{ "p":0.4202898551, "r":0.4461538462, "f":0.4328358209 }, "MONEY":{ "p":0.5, "r":0.5, "f":0.5 }, "ORDINAL":{ "p":0.5, "r":0.7272727273, "f":0.5925925926 }, "PERCENT":{ "p":1.0, "r":1.0, "f":1.0 }, "PERSON":{ "p":0.7843137255, "r":0.8, "f":0.7920792079 }, "FAC":{ "p":0.3, "r":0.15, "f":0.2 }, "ORG":{ "p":0.5454545455, "r":0.7346938776, "f":0.6260869565 }, "EVENT":{ "p":0.4705882353, "r":0.4705882353, "f":0.4705882353 }, "WORK_OF_ART":{ "p":0.5757575758, "r":0.4634146341, "f":0.5135135135 }, "LANGUAGE":{ "p":0.0, "r":0.0, "f":0.0 }, "TIME":{ "p":0.8333333333, "r":0.8333333333, "f":0.8333333333 }, "LAW":{ "p":0.0, "r":0.0, "f":0.0 } }, "pos_acc":0.9314809819 }, "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":[ ] }