ro_core_news_lg-2.3.1

Details: https://spacy.io/models/ro#ro_core_news_lg

File checksum: bc124513b78c87a5c771cb71089f7e4ea29fdddb85121047076384ff3be70f1d

Romanian multi-task CNN trained on UD Romanian RRT and the Romanian Named Entity Corpus. Assigns word vectors, POS tags, dependency parse and named entities. Word vectors trained using FastText CBOW on Wikipedia and OSCAR (Common Crawl).

Feature	Description
Name	ro_core_news_lg
Version	2.3.1
spaCy	>=2.3.0,<2.4.0
Model size	545 MB
Pipeline	tagger, parser, ner
Vectors	500000 keys, 500000 unique vectors (300 dimensions)
Sources	UD Romanian RRT v2.5 (Barbu Mititelu, Verginica; Irimia, Elena; Perez, Cenel-Augusto; Ion, Radu; Simionescu, Radu; Popel, Martin) RONEC - the Romanian Named Entity Corpus (ca9ce460) (Dumitrescu, Stefan Daniel; Avram, Andrei-Marius; Morogan, Luciana; Toma; Stefan) OSCAR (Common Crawl) Wikipedia (20200201)
License	CC BY-SA 4.0
Author	Explosion

Label Scheme

Component	Labels
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, _SP
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
ner	DATETIME, EVENT, FACILITY, GPE, LANGUAGE, LOC, MONEY, NAT_REL_POL, NUMERIC_VALUE, ORDINAL, ORGANIZATION, PERIOD, PERSON, PRODUCT, QUANTITY, WORK_OF_ART

Accuracy

Type	Score
LAS	81.98
UAS	88.90
TOKEN_ACC	99.61
TAGS_ACC	96.82
ENTS_F	76.36
ENTS_P	74.80
ENTS_R	77.99

Installation

pip install spacy
python -m spacy download ro_core_news_lg