Show simple record

dc.contributor.authorMohaghegh, Mahsa
dc.date.accessioned2013-06-28T01:41:29Z
dc.date.available2013-06-28T01:41:29Z
dc.date.issued2012
dc.identifier.urihttps://hdl.handle.net/10652/2226
dc.description.abstractIn this paper we show that a hierarchical phrase-based translation system will outperform a classical (non-hierarchical) phrase-based system in the English-to-Persian translation direction, yet for the Persian-to-English direction, the classical phrase-based system is preferable. We seek to explain why this is so, and detail a series of translation experiments with our SMT system using various bilingual corpora each with both toolkits Moses (non-hierarchical) and Joshua (hierarchical).en_NZ
dc.language.isoenen_NZ
dc.subjectstatistical machine translation (SMT)en_NZ
dc.subjectEnglish-Persianen_NZ
dc.subjectParallel Corporaen_NZ
dc.titleAdvancements in English-Persian Hierarchical Statistical Machine Translationen_NZ
dc.typeConference Contribution - Paper in Published Proceedingsen_NZ
dc.rights.holderAuthoren_NZ
dc.subject.marsden089999 Information and Computing Sciences not elsewhere classifieden_NZ
dc.identifier.bibliographicCitationMohaghegh, M. (2012). Advancements in English-Persian Hierarchical Statistical Machine Translation. NZCSRSC New Zealand Computer Science Research Student Conference. Dunedin, New Zealand. 13 April.en_NZ
unitec.institutionUnitec Institute of Technologyen_NZ
unitec.conference.titleNZCSRSC New Zealand Computer Science Research Student Conferenceen_NZ
unitec.peerreviewedyesen_NZ
unitec.identifier.roms53243


Files in this item

Thumbnail

This item appears in

Show simple record