{ "lang":"ro", "name":"core_news_sm", "version":"3.1.0", "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":">=3.1.0,<3.2.0", "spacy_git_version":"caba63b74", "vectors":{ "width":0, "vectors":0, "keys":0, "name":null }, "labels":{ "tok2vec":[ ], "tagger":[ "ARROW", "Af", "Afcfp-n", "Afcfson", "Afcfsrn", "Afcmpoy", "Afcms-n", "Afp", "Afp-p-n", "Afp-poy", "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", "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", "Mc-p-d", "Mc-p-l", "Mcfp-l", "Mcfp-ln", "Mcfprln", "Mcfprly", "Mcfsoln", "Mcfsrln", "Mcmp-l", "Mcms-ln", "Mcmsrl", "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", "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", "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", "Ps2ms-s", "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", "Rgc", "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", "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", "Vmsp1s", "Vmsp2s", "Vmsp3", "Vmsp3-----y", "X", "Y", "Ya", "Yn", "Ynfsoy", "Ynfsry", "Ynmsoy", "Ynmsry", "Yp", "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:agent", "nmod:pmod", "nmod:tmod", "nsubj", "nsubj:pass", "nummod", "obj", "obl", "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, "tag_acc":0.9612171026, "pos_acc":0.9556105925, "morph_acc":0.9623560794, "lemma_acc":0.8186589263, "dep_uas":0.8705660969, "dep_las":0.8189173932, "sents_p":0.950928382, "sents_r":0.9534574468, "sents_f":0.9521912351, "speed":9573.3292142848, "morph_per_feat":{ "Case":{ "p":0.985836417, "r":0.9825766247, "f":0.9842038217 }, "Gender":{ "p":0.9825625474, "r":0.9721215152, "f":0.9773141457 }, "Number":{ "p":0.9856352415, "r":0.9757716212, "f":0.98067863 }, "Person":{ "p":0.9789227166, "r":0.9852681202, "f":0.9820851689 }, "PronType":{ "p":0.9951523546, "r":0.99308915, "f":0.9941196818 }, "Polarity":{ "p":0.9918166939, "r":0.993442623, "f":0.9926289926 }, "AdpType":{ "p":0.9976311337, "r":0.9976311337, "f":0.9976311337 }, "Definite":{ "p":0.9854908915, "r":0.9703174603, "f":0.9778453171 }, "Degree":{ "p":0.9436038514, "r":0.9214237743, "f":0.9323819232 }, "VerbForm":{ "p":0.9632545932, "r":0.9760638298, "f":0.9696169089 }, "Abbr":{ "p":0.9804878049, "r":0.8973214286, "f":0.9370629371 }, "Poss":{ "p":1.0, "r":0.9951807229, "f":0.9975845411 }, "NumForm":{ "p":0.9944134078, "r":0.9807162534, "f":0.987517337 }, "NumType":{ "p":0.995821727, "r":0.9821428571, "f":0.9889349931 }, "Reflex":{ "p":1.0, "r":0.9935897436, "f":0.9967845659 }, "Strength":{ "p":0.9841269841, "r":0.9841269841, "f":0.9841269841 }, "Mood":{ "p":0.9446428571, "r":0.9706422018, "f":0.9574660633 }, "Tense":{ "p":0.9470672389, "r":0.9622093023, "f":0.9545782264 }, "Variant":{ "p":0.9867549669, "r":0.9612903226, "f":0.9738562092 }, "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 } }, "dep_las_per_type":{ "root":{ "p":0.8519855596, "r":0.8888888889, "f":0.8700460829 }, "mark":{ "p":0.9138576779, "r":0.920754717, "f":0.9172932331 }, "case":{ "p":0.9520392749, "r":0.9452568429, "f":0.948635936 }, "nmod:tmod":{ "p":0.5151515152, "r":0.1428571429, "f":0.2236842105 }, "amod":{ "p":0.8744625967, "r":0.8662691652, "f":0.8703465982 }, "nsubj":{ "p":0.8336106489, "r":0.7914691943, "f":0.811993517 }, "nmod":{ "p":0.8005068791, "r":0.7893609425, "f":0.7948948409 }, "aux":{ "p":0.9757462687, "r":0.9561243144, "f":0.9658356417 }, "advcl":{ "p":0.5620915033, "r":0.6466165414, "f":0.6013986014 }, "obj":{ "p":0.7931769723, "r":0.8591224018, "f":0.8248337029 }, "det":{ "p":0.9598623853, "r":0.9479048698, "f":0.9538461538 }, "cc":{ "p":0.9182389937, "r":0.9144050104, "f":0.9163179916 }, "conj":{ "p":0.5696969697, "r":0.5446118192, "f":0.5568720379 }, "nummod":{ "p":0.8888888889, "r":0.8571428571, "f":0.8727272727 }, "acl":{ "p":0.7819767442, "r":0.6950904393, "f":0.7359781122 }, "advmod":{ "p":0.7928388747, "r":0.8179419525, "f":0.8051948052 }, "obl":{ "p":0.6563500534, "r":0.7804568528, "f":0.7130434783 }, "expl:pass":{ "p":0.8372093023, "r":0.6666666667, "f":0.7422680412 }, "nsubj:pass":{ "p":0.8582089552, "r":0.7012195122, "f":0.7718120805 }, "fixed":{ "p":0.8381742739, "r":0.8541226216, "f":0.8460732984 }, "appos":{ "p":0.4291666667, "r":0.393129771, "f":0.4103585657 }, "parataxis":{ "p":0.2045454545, "r":0.2571428571, "f":0.2278481013 }, "aux:pass":{ "p":0.9256756757, "r":0.9133333333, "f":0.9194630872 }, "nmod:agent":{ "p":0.9462365591, "r":0.7927927928, "f":0.862745098 }, "ccomp":{ "p":0.8770491803, "r":0.8294573643, "f":0.8525896414 }, "nmod:pmod":{ "p":0.3555555556, "r":0.2666666667, "f":0.3047619048 }, "iobj":{ "p":0.7619047619, "r":0.7901234568, "f":0.7757575758 }, "flat":{ "p":0.7560321716, "r":0.7421052632, "f":0.7490039841 }, "cop":{ "p":0.7952755906, "r":0.814516129, "f":0.8047808765 }, "csubj":{ "p":0.7619047619, "r":0.7619047619, "f":0.7619047619 }, "dep":{ "p":0.0, "r":0.0, "f":0.0 }, "expl:pv":{ "p":0.7532467532, "r":0.8405797101, "f":0.7945205479 }, "expl":{ "p":0.7037037037, "r":0.7037037037, "f":0.7037037037 }, "vocative":{ "p":0.0, "r":0.0, "f":0.0 }, "expl:poss":{ "p":0.9310344828, "r":0.8709677419, "f":0.9 }, "goeswith":{ "p":0.1, "r":0.3333333333, "f":0.1538461538 }, "xcomp":{ "p":0.325, "r":0.4814814815, "f":0.3880597015 }, "compound":{ "p":0.3333333333, "r":0.5714285714, "f":0.4210526316 }, "ccomp:pmod":{ "p":0.0, "r":0.0, "f":0.0 }, "orphan":{ "p":0.0, "r":0.0, "f":0.0 }, "expl:impers":{ "p":0.5, "r":0.3333333333, "f":0.4 }, "list":{ "p":0.0, "r":0.0, "f":0.0 }, "cc:preconj":{ "p":0.0, "r":0.0, "f":0.0 }, "csubj:pass":{ "p":0.0, "r":0.0, "f":0.0 } }, "ents_p":0.7244897959, "ents_r":0.7091817134, "ents_f":0.7167540283, "ents_per_type":{ "DATETIME":{ "p":0.7889273356, "r":0.7944250871, "f":0.7916666667 }, "ORGANIZATION":{ "p":0.6656050955, "r":0.6656050955, "f":0.6656050955 }, "FACILITY":{ "p":0.4953271028, "r":0.4045801527, "f":0.4453781513 }, "NUMERIC_VALUE":{ "p":0.875, "r":0.9194915254, "f":0.8966942149 }, "ORDINAL":{ "p":0.7962962963, "r":0.7818181818, "f":0.7889908257 }, "EVENT":{ "p":0.6551724138, "r":0.5135135135, "f":0.5757575758 }, "GPE":{ "p":0.8025477707, "r":0.8689655172, "f":0.8344370861 }, "PERSON":{ "p":0.675862069, "r":0.6577181208, "f":0.6666666667 }, "NAT_REL_POL":{ "p":0.8976377953, "r":0.76, "f":0.8231046931 }, "MONEY":{ "p":0.8867924528, "r":0.8103448276, "f":0.8468468468 }, "PRODUCT":{ "p":0.4424778761, "r":0.3649635036, "f":0.4 }, "LOC":{ "p":0.4461538462, "r":0.3815789474, "f":0.4113475177 }, "WORK_OF_ART":{ "p":0.24, "r":0.3157894737, "f":0.2727272727 }, "QUANTITY":{ "p":0.8518518519, "r":0.8846153846, "f":0.8679245283 }, "LANGUAGE":{ "p":0.5714285714, "r":1.0, "f":0.7272727273 }, "PERIOD":{ "p":0.8717948718, "r":0.8095238095, "f":0.8395061728 } } }, "sources":[ { "name":"Lemmatization Lists", "url":"https://github.com/michmech/lemmatization-lists/", "license":"ODbL", "author":"Michal M\u011bchura" }, { "name":"UD Romanian RRT v2.5", "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" } ], "requirements":[ ] }