NLP-Cube

NLP-Cube is an opensource Natural Language Processing Framework with support for languages which are included in the UD Treebanks. NLP-Cube performs the following tasks:
-Sentence segmentation
-Tokenization
-POS Tagging (both language independent (UPOSes) and language dependent (XPOSes and ATTRs))
-Lemmatization
-Dependency parsing


Languages: Latin (la), Kurdish (ku), Korean (ko), Kazakh (kk), Japanese (ja), Italian (it), Irish (ga), Indonesian (id), Sami Languages (smi), Latvian (lv), Portuguese (pt), Romanian; Moldavian; Moldovan (ro), Russian (ru), Serbian (sr), Norwegian Bokmål (nb), Norwegian Nynorsk (nn), Church Slavic; Church Slavonic; Old Bulgarian; Old Church Slavonic; Old Slavonic (cu), Persian (fa), Slovak (sk), Spanish; Castilian (es), Serbian (sr), Russian (ru), Spanish; Castilian (es), Slovak (sk), Turkish (tr), Swedish (sv), Upper Sorbian (hsb), Ukrainian (uk), Vietnamese (vi), Urdu (ur), Hindi (hi), Hungarian (hu), Gothic (got), Hebrew (he), Galician (gl), German (de), Finnish (fi), French (fr), Uighur; Uyghur (ug), Estonian (et), Afrikaans (af), Korean (ko), Kazakh (kk), Hungarian (hu), Hindi (hi), Hebrew (he), Gothic (got), Japanese (ja), Italian (it), Irish (ga), Indonesian (id), Modern Greek (1453-) (el), Ancient Greek (to 1453) (grc), Arabic (ar), Armenian (hy), Basque (eu), Bulgarian (bg), Buriat (bua), Catalan; Valencian (ca), Chinese (zh), Portuguese (pt), Romanian; Moldavian; Moldovan (ro), Kurdish (ku), Latin (la), Latvian (lv), Sami Languages (smi), Norwegian Bokmål (nb), Norwegian Nynorsk (nn), Church Slavic; Church Slavonic; Old Bulgarian; Old Church Slavonic; Old Slavonic (cu), Persian (fa), Vietnamese (vi), Urdu (ur), Uighur; Uyghur (ug), Turkish (tr), Swedish (sv), Upper Sorbian (hsb), Ukrainian (uk), Danish (da), Dutch; Flemish (nl), Croatian (hr), Czech (cs), Finnish (fi), French (fr), English (en), Estonian (et), Galician (gl), German (de)
People who looked at this resource also viewed the following: