Show simple item record

dc.contributor.authorMohaghegh, M
dc.contributor.authorSarrafzadeh, A
dc.contributor.authorMoir, T
dc.date.accessioned2011-09-05T21:46:44Z
dc.date.accessioned2012-04-12T06:44:25Z
dc.date.accessioned2012-04-12T06:47:14Z
dc.date.available2011-09-05T21:46:44Z
dc.date.available2012-04-12T06:44:25Z
dc.date.available2012-04-12T06:47:14Z
dc.date.copyright2011-11
dc.date.issued2011-09-06
dc.identifier.citationThe 5th International Joint Conference on Natural Language Processing, Thailand, 2011-11-08 - 2011-11-13
dc.identifier.urihttp://hdl.handle.net/10292/3771
dc.description.abstractThis paper documents recent work carried out for PeEn-SMT, our Statistical Machine Translation system for translation between the English-Persian language pair. We give details of our previous SMT system, and present our current development of significantly larger corpora. We explain how recent tests using much larger corpora helped to evaluate problems in parallel corpus alignment, corpus content, and how matching the domains of PeEn-SMT’s components affect translation output. We then focus on combining corpora and approaches to improve test data, showing details of experimental setup, together with a number of experiment results and comparisons between them. We show how one combination of corpora gave us a metric score outperforming Google Translate for the English-to-Persian translation. Finally, we outline areas of our intended future work, and how we plan to improve the performance of our system to achieve higher metric scores, and ultimately to provide accurate, reliable language translation.
dc.publisherCiteSeerX
dc.relation.replaceshttp://hdl.handle.net/10292/1983
dc.relation.replaces10292/1983
dc.relation.replaceshttp://hdl.handle.net/10292/3770
dc.relation.replaces10292/3770
dc.relation.urihttp://www.ijcnlp2011.org/proceeding/workshop/WS1_WSSANLP/pdf/WSSANLP02.pdf
dc.rightsCiteSeerx is compliant with the Open Archives Initiative Protocol for Metadata Harvesting, which is a standard proposed by The Open Archive Initiative in order to facilitate content dissemination. For data not mentioned here, please contact us through feedback.
dc.titleImproving Persian-English statistical machine translation: experiments in domain adaption
dc.typeConference Contribution
dc.rights.accessrightsOpenAccess


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record