Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/39953
DC FieldValue
dc.titleImproved statistical machine translation for resource-poor languages using related resource-rich languages
dc.contributor.authorNakov, P.
dc.contributor.authorNg, H.T.
dc.date.accessioned2013-07-04T07:53:21Z
dc.date.available2013-07-04T07:53:21Z
dc.date.issued2009
dc.identifier.citationNakov, P.,Ng, H.T. (2009). Improved statistical machine translation for resource-poor languages using related resource-rich languages. EMNLP 2009 - Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: A Meeting of SIGDAT, a Special Interest Group of ACL, Held in Conjunction with ACL-IJCNLP 2009 : 1358-1367. ScholarBank@NUS Repository.
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/39953
dc.description.abstractWe propose a novel language-independent approach for improving statistical machine translation for resource-poor languages by exploiting their similarity to resource-rich ones. More precisely, we improve the translation from a resource-poor source language X 1 into a resource-rich language Y given a bi-text containing a limited number of parallel sentences for X 1-Y and a larger bi-text for X 2-Y for some resource-rich language X 2 that is closely related to X1. The evaluation for Indonesian→English (using Malay) and Spanish→English (using Portuguese and pretending Spanish is resource-poor) shows an absolute gain of up to 1.35 and 3.37 Bleu points, respectively, which is an improvement over the rivaling approaches, while using much less additional data. © 2009 ACL and AFNLP.
dc.sourceScopus
dc.typeConference Paper
dc.contributor.departmentCOMPUTER SCIENCE
dc.description.sourcetitleEMNLP 2009 - Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: A Meeting of SIGDAT, a Special Interest Group of ACL, Held in Conjunction with ACL-IJCNLP 2009
dc.description.page1358-1367
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)

113
checked on Aug 18, 2022

Google ScholarTM

Check


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