Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/41304
DC FieldValue
dc.titleA hybrid morpheme-word representation for machine translation of morphologically rich languages
dc.contributor.authorLuong, M.-T.
dc.contributor.authorNakov, P.
dc.contributor.authorKan, M.-Y.
dc.date.accessioned2013-07-04T08:24:23Z
dc.date.available2013-07-04T08:24:23Z
dc.date.issued2010
dc.identifier.citationLuong, M.-T.,Nakov, P.,Kan, M.-Y. (2010). A hybrid morpheme-word representation for machine translation of morphologically rich languages. EMNLP 2010 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference : 148-157. ScholarBank@NUS Repository.
dc.identifier.isbn1932432868
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/41304
dc.description.abstractWe propose a language-independent approach for improving statistical machine translation for morphologically rich languages using a hybrid morpheme-word representation where the basic unit of translation is the morpheme, but word boundaries are respected at all stages of the translation process. Our model extends the classic phrase-based model by means of (1) word boundary-aware morpheme-level phrase extraction, (2) minimum error-rate training for a morpheme-level translation model using word-level BLEU, and (3) joint scoring with morpheme- and word-level language models. Further improvements are achieved by combining our model with the classic one. The evaluation on English to Finnish using Europarl (714K sentence pairs; 15.5M English words) shows statistically significant improvements over the classic model based on BLEU and human judgments. © 2010 Association for Computational Linguistics.
dc.sourceScopus
dc.typeConference Paper
dc.contributor.departmentCOMPUTER SCIENCE
dc.description.sourcetitleEMNLP 2010 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
dc.description.page148-157
dc.identifier.isiutNOT_IN_WOS
Appears in Collections:Staff Publications

Show simple item record
Files in This Item:
There are no files associated with this item.

Page view(s)

85
checked on Oct 28, 2019

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.