{ "lang":"ro", "name":"core_news_lg", "version":"3.2.0", "description":"Romanian pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter, ner, attribute_ruler, lemmatizer.", "author":"Explosion", "email":"contact@explosion.ai", "url":"https://explosion.ai", "license":"CC BY-SA 4.0", "spacy_version":">=3.2.0,<3.3.0", "spacy_git_version":"bb26550e2", "vectors":{ "width":300, "vectors":500000, "keys":500000, "name":"ro_vectors" }, "labels":{ "tok2vec":[ ], "tagger":[ "ARROW", "Af", "Afcfp-n", "Afcfson", "Afcfsrn", "Afcmpoy", "Afcms-n", "Afp", "Afp-p-n", "Afp-poy", "Afp-srn", "Afpf--n", "Afpfp-n", "Afpfp-ny", "Afpfpoy", "Afpfpry", "Afpfson", "Afpfsoy", "Afpfsrn", "Afpfsry", "Afpm--n", "Afpmp-n", "Afpmpoy", "Afpmpry", "Afpms-n", "Afpmsoy", "Afpmsry", "Afsfp-n", "Afsfsrn", "BULLET", "COLON", "COMMA", "Ccssp", "Ccsspy", "Crssp", "Csssp", "Cssspy", "DASH", "DBLQ", "Dd3-po---e", "Dd3-po---o", "Dd3fpo", "Dd3fpr", "Dd3fpr---e", "Dd3fpr---o", "Dd3fpr--y", "Dd3fso", "Dd3fso---e", "Dd3fsr", "Dd3fsr---e", "Dd3fsr---o", "Dd3fsr--yo", "Dd3mpo", "Dd3mpr", "Dd3mpr---e", "Dd3mpr---o", "Dd3mso---e", "Dd3msr", "Dd3msr---e", "Dd3msr---o", "Dh1ms", "Dh3fp", "Dh3fso", "Dh3fsr", "Dh3mp", "Dh3ms", "Di3", "Di3-----y", "Di3--r---e", "Di3-po", "Di3-po---e", "Di3-sr", "Di3-sr---e", "Di3-sr--y", "Di3fp", "Di3fpr", "Di3fpr---e", "Di3fso", "Di3fso---e", "Di3fsr", "Di3fsr---e", "Di3mp", "Di3mpr", "Di3mpr---e", "Di3ms", "Di3ms----e", "Di3mso---e", "Di3msr", "Di3msr---e", "Ds1fp-p", "Ds1fp-s", "Ds1fsop", "Ds1fsos", "Ds1fsrp", "Ds1fsrs", "Ds1fsrs-y", "Ds1mp-p", "Ds1mp-s", "Ds1ms-p", "Ds1ms-s", "Ds1msrs-y", "Ds2---s", "Ds2fp-p", "Ds2fp-s", "Ds2fsrp", "Ds2fsrs", "Ds2mp-p", "Ds2mp-s", "Ds2ms-p", "Ds2ms-s", "Ds3---p", "Ds3---s", "Ds3---sy", "Ds3fp-s", "Ds3fsos", "Ds3fsrs", "Ds3mp-s", "Ds3ms-s", "Dw3--r---e", "Dw3-po---e", "Dw3fpr", "Dw3fso---e", "Dw3fsr", "Dw3mpr", "Dw3mso---e", "Dw3msr", "Dz3fsr---e", "Dz3mso---e", "Dz3msr---e", "EQUAL", "EXCL", "EXCLHELLIP", "GE", "GT", "HELLIP", "I", "LCURL", "LPAR", "LSQR", "LT", "M", "Mc-p-d", "Mc-p-l", "Mc-s-b", "Mc-s-d", "Mc-s-l", "Mcfp-l", "Mcfp-ln", "Mcfprln", "Mcfprly", "Mcfsoln", "Mcfsrl", "Mcfsrln", "Mcfsrly", "Mcmp-l", "Mcms-ln", "Mcmsrl", "Mcmsrln", "Mcmsrly", "Mffprln", "Mffsrln", "Mlfpo", "Mlfpr", "Mlmpr", "Mo---l", "Mo---ln", "Mo-s-r", "Mofp-ln", "Mofpoly", "Mofprly", "Mofs-l", "Mofsoln", "Mofsoly", "Mofsrln", "Mofsrly", "Mompoly", "Momprly", "Moms-l", "Moms-ln", "Momsoly", "Momsrly", "Nc", "Nc---n", "Ncf--n", "Ncfp-n", "Ncfpoy", "Ncfpry", "Ncfs-n", "Ncfson", "Ncfsoy", "Ncfsrn", "Ncfsry", "Ncfsryy", "Ncfsvy", "Ncm--n", "Ncmp-n", "Ncmpoy", "Ncmpry", "Ncms-n", "Ncms-ny", "Ncms-y", "Ncmsoy", "Ncmsrn", "Ncmsry", "Ncmsryy", "Ncmsvn", "Ncmsvy", "Np", "Npfson", "Npfsoy", "Npfsrn", "Npfsry", "Npmpoy", "Npmpry", "Npms-n", "Npmsoy", "Npmsry", "PERCENT", "PERIOD", "PLUS", "PLUSMINUS", "Pd3-po", "Pd3fpr", "Pd3fso", "Pd3fsr", "Pd3mpo", "Pd3mpr", "Pd3mpr--y", "Pd3mso", "Pd3msr", "Pi3--r", "Pi3-po", "Pi3-so", "Pi3-sr", "Pi3fpr", "Pi3fso", "Pi3fsr", "Pi3mpr", "Pi3mso", "Pi3msr", "Pi3msr--y", "Pp1-pa--------w", "Pp1-pa--y-----w", "Pp1-pd--------s", "Pp1-pd--------w", "Pp1-pd--y-----w", "Pp1-pr--------s", "Pp1-sa--------s", "Pp1-sa--------w", "Pp1-sa--y-----w", "Pp1-sd--------s", "Pp1-sd--------w", "Pp1-sd--y-----w", "Pp1-sn--------s", "Pp2-----------s", "Pp2-pa--------w", "Pp2-pa--y-----w", "Pp2-pd--------w", "Pp2-pd--y-----w", "Pp2-pr--------s", "Pp2-sa--------s", "Pp2-sa--------w", "Pp2-sa--y-----w", "Pp2-sd--------s", "Pp2-sd--------w", "Pp2-sd--y-----w", "Pp2-sn--------s", "Pp2-so--------s", "Pp2-sr--------s", "Pp3-p---------s", "Pp3-pd--------w", "Pp3-pd--y-----w", "Pp3-po--------s", "Pp3-sd--------w", "Pp3-sd--y-----w", "Pp3-so--------s", "Pp3fpa--------w", "Pp3fpa--y-----w", "Pp3fpr--------s", "Pp3fs---------s", "Pp3fsa--------w", "Pp3fsa--y-----w", "Pp3fso--------s", "Pp3fsr--------s", "Pp3fsr--y-----s", "Pp3mpa--------w", "Pp3mpa--y-----w", "Pp3mpr--------s", "Pp3ms---------s", "Pp3msa--------w", "Pp3msa--y-----w", "Pp3mso--------s", "Pp3msr--------s", "Pp3msr--y-----s", "Ps1fp-s", "Ps1fsrp", "Ps1fsrs", "Ps1mp-p", "Ps1ms-p", "Ps2fp-s", "Ps2fsrp", "Ps2fsrs", "Ps3---p", "Ps3---s", "Ps3fp-s", "Ps3fsrs", "Ps3mp-s", "Ps3ms-s", "Pw3--r", "Pw3-po", "Pw3-so", "Pw3fpr", "Pw3fso", "Pw3mpr", "Pw3mso", "Px3--a--------s", "Px3--a--------w", "Px3--a--y-----w", "Px3--d--------w", "Px3--d--y-----w", "Pz3-sr", "Pz3fsr", "QUEST", "QUOT", "Qf", "Qn", "Qs", "Qs-y", "Qz", "Qz-y", "RCURL", "RPAR", "RSQR", "Rc", "Rgp", "Rgpy", "Rgs", "Rp", "Rw", "Rw-y", "Rz", "SCOLON", "SLASH", "STAR", "Sp", "Spsa", "Spsay", "Spsd", "Spsg", "Td-po", "Tdfpr", "Tdfso", "Tdfsr", "Tdmpr", "Tdmso", "Tdmsr", "Tf-so", "Tffpoy", "Tffpry", "Tffs-y", "Tfmpoy", "Tfms-y", "Tfmsoy", "Tfmsry", "Ti-po", "Tifp-y", "Tifso", "Tifsr", "Timso", "Timsr", "Tsfp", "Tsfs", "Tsmp", "Tsms", "UNDERSC", "Va--1", "Va--1-----y", "Va--1p", "Va--1s", "Va--1s----y", "Va--2p", "Va--2p----y", "Va--2s", "Va--2s----y", "Va--3", "Va--3-----y", "Va--3p", "Va--3p----y", "Va--3s", "Va--3s----y", "Vag", "Vag-------y", "Vaii1", "Vaii2s", "Vaii3p", "Vaii3s", "Vail3p", "Vail3s", "Vaip1p", "Vaip1s", "Vaip2p", "Vaip2s", "Vaip3p", "Vaip3p----y", "Vaip3s", "Vaip3s----y", "Vais3p", "Vais3s", "Vam-2s", "Vanp", "Vap--sm", "Vasp1p", "Vasp1s", "Vasp2p", "Vasp2s", "Vasp3", "Vmg", "Vmg-------y", "Vmii1", "Vmii1-----y", "Vmii2p", "Vmii2s", "Vmii3p", "Vmii3p----y", "Vmii3s", "Vmii3s----y", "Vmil1", "Vmil1p", "Vmil2s", "Vmil3p", "Vmil3p----y", "Vmil3s", "Vmil3s----y", "Vmip1p", "Vmip1p----y", "Vmip1s", "Vmip1s----y", "Vmip2p", "Vmip2s", "Vmip2s----y", "Vmip3", "Vmip3-----y", "Vmip3p", "Vmip3s", "Vmip3s----y", "Vmis1p", "Vmis1s", "Vmis3p", "Vmis3p----y", "Vmis3s", "Vmis3s----y", "Vmm-2p", "Vmm-2s", "Vmnp", "Vmnp------y", "Vmp--pf", "Vmp--pm", "Vmp--sf", "Vmp--sm", "Vmp--sm---y", "Vmsp1p", "Vmsp2p", "Vmsp2s", "Vmsp3", "Vmsp3-----y", "X", "Y", "Ya", "Yn", "Ynfsoy", "Ynfsry", "Ynmsoy", "Ynmsry", "Yp", "Yp,Yn", "Yp-sr", "Yr" ], "parser":[ "ROOT", "acl", "advcl", "advcl:tcl", "advmod", "advmod:tmod", "amod", "appos", "aux", "aux:pass", "case", "cc", "cc:preconj", "ccomp", "ccomp:pmod", "compound", "conj", "cop", "csubj", "csubj:pass", "dep", "det", "expl", "expl:impers", "expl:pass", "expl:poss", "expl:pv", "fixed", "flat", "goeswith", "iobj", "mark", "nmod", "nmod:tmod", "nsubj", "nsubj:pass", "nummod", "obj", "obl", "obl:agent", "obl:pmod", "orphan", "parataxis", "punct", "vocative", "xcomp" ], "senter":[ "I", "S" ], "attribute_ruler":[ ], "lemmatizer":[ ], "ner":[ "DATETIME", "EVENT", "FACILITY", "GPE", "LANGUAGE", "LOC", "MONEY", "NAT_REL_POL", "NUMERIC_VALUE", "ORDINAL", "ORGANIZATION", "PERIOD", "PERSON", "PRODUCT", "QUANTITY", "WORK_OF_ART" ] }, "pipeline":[ "tok2vec", "tagger", "parser", "attribute_ruler", "lemmatizer", "ner" ], "components":[ "tok2vec", "tagger", "parser", "senter", "attribute_ruler", "lemmatizer", "ner" ], "disabled":[ "senter" ], "performance":{ "token_acc":0.9990029326, "token_p":0.9967350492, "token_r":0.9957244934, "token_f":0.9959492157, "tag_acc":0.9664291788, "sents_p":0.954787234, "sents_r":0.954787234, "sents_f":0.954787234, "dep_uas":0.8897462438, "dep_las":0.8389686971, "dep_las_per_type":{ "root":{ "p":0.8786231884, "r":0.9133709981, "f":0.8956602031 }, "mark":{ "p":0.9288389513, "r":0.9358490566, "f":0.9323308271 }, "case":{ "p":0.9638554217, "r":0.959880015, "f":0.9618636107 }, "nmod:tmod":{ "p":0.6842105263, "r":0.1092436975, "f":0.1884057971 }, "amod":{ "p":0.9172297297, "r":0.9250425894, "f":0.9211195929 }, "nsubj":{ "p":0.8803986711, "r":0.8372827804, "f":0.8582995951 }, "nmod":{ "p":0.8218838527, "r":0.8286326312, "f":0.8252444444 }, "aux":{ "p":0.9867924528, "r":0.9561243144, "f":0.9712163417 }, "advcl":{ "p":0.5862068966, "r":0.6390977444, "f":0.6115107914 }, "obj":{ "p":0.8326180258, "r":0.896073903, "f":0.8631813126 }, "det":{ "p":0.9575688073, "r":0.9456398641, "f":0.9515669516 }, "cc":{ "p":0.9340425532, "r":0.9164926931, "f":0.9251844046 }, "conj":{ "p":0.6115288221, "r":0.5654692932, "f":0.5875978326 }, "nummod":{ "p":0.887675507, "r":0.8835403727, "f":0.8856031128 }, "acl":{ "p":0.8063583815, "r":0.7209302326, "f":0.761255116 }, "advmod":{ "p":0.8117048346, "r":0.8416886544, "f":0.8264248705 }, "obl":{ "p":0.6821052632, "r":0.8223350254, "f":0.7456846951 }, "expl:pass":{ "p":0.8085106383, "r":0.7037037037, "f":0.7524752475 }, "nsubj:pass":{ "p":0.8, "r":0.756097561, "f":0.7774294671 }, "fixed":{ "p":0.9, "r":0.8562367865, "f":0.8775731311 }, "appos":{ "p":0.4956896552, "r":0.4389312977, "f":0.4655870445 }, "parataxis":{ "p":0.1627906977, "r":0.2, "f":0.1794871795 }, "aux:pass":{ "p":0.9125, "r":0.9733333333, "f":0.9419354839 }, "nmod:agent":{ "p":0.0, "r":0.0, "f":0.0 }, "ccomp":{ "p":0.8759689922, "r":0.8759689922, "f":0.8759689922 }, "nmod:pmod":{ "p":0.0, "r":0.0, "f":0.0 }, "iobj":{ "p":0.8157894737, "r":0.7654320988, "f":0.7898089172 }, "flat":{ "p":0.7557251908, "r":0.7815789474, "f":0.7684346701 }, "cop":{ "p":0.8524590164, "r":0.8387096774, "f":0.8455284553 }, "csubj":{ "p":0.8235294118, "r":0.6666666667, "f":0.7368421053 }, "obl:agent":{ "p":0.0, "r":0.0, "f":0.0 }, "dep":{ "p":0.0, "r":0.0, "f":0.0 }, "expl:pv":{ "p":0.7564102564, "r":0.8550724638, "f":0.8027210884 }, "expl":{ "p":0.6875, "r":0.8148148148, "f":0.7457627119 }, "obl:pmod":{ "p":0.0, "r":0.0, "f":0.0 }, "expl:poss":{ "p":0.9655172414, "r":0.9032258065, "f":0.9333333333 }, "goeswith":{ "p":0.0, "r":0.0, "f":0.0 }, "xcomp":{ "p":0.5806451613, "r":0.6666666667, "f":0.6206896552 }, "orphan":{ "p":0.0, "r":0.0, "f":0.0 }, "expl:impers":{ "p":1.0, "r":0.3333333333, "f":0.5 }, "csubj:pass":{ "p":0.0, "r":0.0, "f":0.0 }, "compound":{ "p":0.5714285714, "r":0.5714285714, "f":0.5714285714 }, "list":{ "p":0.0, "r":0.0, "f":0.0 }, "ccomp:pmod":{ "p":0.25, "r":0.3333333333, "f":0.2857142857 }, "cc:preconj":{ "p":0.0, "r":0.0, "f":0.0 } }, "pos_acc":0.9405873228, "morph_acc":0.9510657636, "morph_micro_p":0.9896160458, "morph_micro_r":0.9582489383, "morph_micro_f":0.9706797273, "morph_per_feat":{ "Case":{ "p":0.9938697318, "r":0.9896985883, "f":0.9917797744 }, "Gender":{ "p":0.991821842, "r":0.9854981873, "f":0.9886499028 }, "Number":{ "p":0.9894903379, "r":0.922363847, "f":0.9547486643 }, "Person":{ "p":0.9911452184, "r":0.9893930466, "f":0.9902683574 }, "PronType":{ "p":0.9965349965, "r":0.993780235, "f":0.9951557093 }, "Polarity":{ "p":0.9918566775, "r":0.9983606557, "f":0.9950980392 }, "AdpType":{ "p":0.998982706, "r":0.9969543147, "f":0.9979674797 }, "Definite":{ "p":0.9886490807, "r":0.9815873016, "f":0.9851055356 }, "Degree":{ "p":0.9582772544, "r":0.9563465413, "f":0.9573109244 }, "VerbForm":{ "p":0.9774236388, "r":0.9787234043, "f":0.9780730897 }, "Abbr":{ "p":0.9538461538, "r":0.8303571429, "f":0.8878281623 }, "Poss":{ "p":1.0, "r":0.9927710843, "f":0.9963724305 }, "NumForm":{ "p":0.9871794872, "r":0.3181818182, "f":0.48125 }, "NumType":{ "p":0.9872881356, "r":0.3200549451, "f":0.4834024896 }, "Reflex":{ "p":1.0, "r":1.0, "f":1.0 }, "Strength":{ "p":0.9920318725, "r":0.9880952381, "f":0.9900596421 }, "Mood":{ "p":0.972826087, "r":0.9853211009, "f":0.9790337284 }, "Tense":{ "p":0.9725036179, "r":0.976744186, "f":0.9746192893 }, "Variant":{ "p":0.9932885906, "r":0.9548387097, "f":0.9736842105 }, "Position":{ "p":1.0, "r":0.9910714286, "f":0.9955156951 }, "Number[psor]":{ "p":1.0, "r":0.9666666667, "f":0.9830508475 }, "PartType":{ "p":1.0, "r":0.9459459459, "f":0.9722222222 }, "Foreign":{ "p":0.0, "r":0.0, "f":0.0 } }, "lemma_acc":0.8183070924, "ents_p":0.7550713749, "ents_r":0.7721859393, "ents_f":0.7635327635, "ents_per_type":{ "DATETIME":{ "p":0.7818791946, "r":0.8118466899, "f":0.7965811966 }, "ORGANIZATION":{ "p":0.7076923077, "r":0.7324840764, "f":0.7198748044 }, "FACILITY":{ "p":0.5039370079, "r":0.4885496183, "f":0.496124031 }, "PRODUCT":{ "p":0.5590551181, "r":0.5182481752, "f":0.5378787879 }, "NUMERIC_VALUE":{ "p":0.8875502008, "r":0.936440678, "f":0.9113402062 }, "ORDINAL":{ "p":0.8214285714, "r":0.8363636364, "f":0.8288288288 }, "EVENT":{ "p":0.5151515152, "r":0.4594594595, "f":0.4857142857 }, "GPE":{ "p":0.8636363636, "r":0.8735632184, "f":0.8685714286 }, "PERSON":{ "p":0.7046153846, "r":0.7684563758, "f":0.735152488 }, "NAT_REL_POL":{ "p":0.9315068493, "r":0.9066666667, "f":0.9189189189 }, "MONEY":{ "p":0.9622641509, "r":0.8793103448, "f":0.9189189189 }, "LOC":{ "p":0.4864864865, "r":0.4736842105, "f":0.48 }, "WORK_OF_ART":{ "p":0.3571428571, "r":0.2631578947, "f":0.303030303 }, "QUANTITY":{ "p":0.962962963, "r":1.0, "f":0.9811320755 }, "LANGUAGE":{ "p":0.6666666667, "r":1.0, "f":0.8 }, "PERIOD":{ "p":0.8648648649, "r":0.7619047619, "f":0.8101265823 } }, "speed":7699.716829035 }, "sources":[ { "name":"Lemmatization Lists", "url":"https://github.com/michmech/lemmatization-lists/", "license":"ODbL", "author":"Michal M\u011bchura" }, { "name":"UD Romanian RRT v2.8", "url":"https://github.com/UniversalDependencies/UD_Romanian-RRT", "license":"CC BY-SA 4.0", "author":"Barbu Mititelu, Verginica; Irimia, Elena; Perez, Cenel-Augusto; Ion, Radu; Simionescu, Radu; Popel, Martin" }, { "name":"RONEC - the Romanian Named Entity Corpus (ca9ce460)", "url":"https://github.com/dumitrescustefan/ronec", "license":"MIT", "author":"Dumitrescu, Stefan Daniel; Avram, Andrei-Marius; Morogan, Luciana; Toma; Stefan" }, { "name":"Explosion fastText Vectors (cbow, OSCAR Common Crawl + Wikipedia)", "url":"https://spacy.io", "license":"CC0", "author":"Explosion" } ], "requirements":[ ] }