| VRSTA GRADIVA | analitična raven (sestavni del), tekstovno gradivo, tiskano, 1.01 - izvirni znanstveni članek |
| DRŽAVA IZIDA | Slovenija |
| LETO IZIDA | 2013 |
| JEZIK BESEDILA/IZVIRNIKA | angleški |
| PISAVA | latinica |
| AVTOR | Apidianaki, Marianna - avtor |
| ODGOVORNOST | Ljubešić, Nikola - avtor // Fišer, Darja - avtor |
| NASLOV | Vector disambiguation for translation extraction from comparable corpora |
| V PUBLIKACIJI | Informatica. - ISSN 0350-5596. - ǂno. ǂ2, ǂVol. ǂ37 (jun. 2013), str. 193-201. |
| KRATKA VSEBINA | We present a new data-driven approach for enhancing the extraction of translation equivalents from comparable corporawhich exploits bilingual lexico-semantic knowledge harvested from a parallel corpus. First, the bilingual lexicon obtained from word-aligning the parallel corpus replaces an external seed dictionary, making the approach knowledge-light and portable. Next, instead of using simple one-to-one mappings between the source and the target language, translationequivalents are clustered into sets of synonyms by a cross-lingual Word Sense Induction method. The obtained sense clusters enable us to expand thetranslation of vector features with several translation variants using a cross-lingual Word Sense Disambiguation method. Consequently, the vector features are disambiguated and translated with the translation variants included in the semantically most appropriate cluster, thus producing less noisy and richer vectors that allow for a more successful cross-lingual vector comparison than in previous methods. // V prispevku predstavljamo pristop za izboljšanje luščenja prevodnih ustreznic iz primerljivih korpusov z dodatnim virom leksiko-semantičnega znanja, izluščenega iz vzporednega korpusa. |
| OPOMBE | Bibliografija: str. 200-201 // Abstract ; Povzetek |
| PREDMETNE OZNAKE | // korpusno jezikoslovje // primerljivi korpusi // razdvoumljanje večpomenskih besed // razvrščanje pomenov v skupine // comparable corpora // word-sense disambiguation // language corpora // sense clustering |
| UDK | 81'322:004.9 |
| DRUGE KLASIFIKACIJE | 6-200 FRASCATI |