Incremental Re-training for Post-editing SMT

Show simple item record

dc.contributor.author	Hardt, Daniel
dc.contributor.author	Elming, Jakob
dc.date.accessioned	2011-01-20
dc.date.accessioned	2011-02-18T12:25:43Z
dc.date.available	2011-02-18T12:25:43Z
dc.date.issued	2011-02-17
dc.identifier.uri	http://hdl.handle.net/10398/8272
dc.description.abstract	A method is presented for incremental retraining of an SMT system, in which a local phrase table is created and incrementally updated as a file is translated and post-edited. It is shown that translation data from within the same file has higher value than other domain-specific data. In two technical domains, within-file data increases BLEU score by several full points. Furthermore, a strong recency effect is documented; nearby data within the file has greater value than more distant data. It is also shown that the value of translation data is strongly correlated with a metric defined over new occurrences of ngrams. Finally, it is argued that the incremental re-training prototype could serve as the basis for a practical system which could be interactively updated in real time in a post-editing setting. Based on the results here, such an interactive system has the potential to dramatically improve translation quality.	en_US
dc.format.extent	10	en_US
dc.language	eng	en_US
dc.title	Incremental Re-training for Post-editing SMT	en_US
dc.type	cp	en_US
dc.accessionstatus	modt11feb17 lbjl	en_US
dc.contributor.corporation	Copenhagen Business School. CBS	en_US
dc.contributor.department	Institut for Internationale Sprogstudier og Vidensteknologi (	en_US
dc.contributor.departmentshort	ISV(	en_US
dc.contributor.departmentuk	Department of International Language Studies and Computational Linguistics(	en_US
dc.contributor.departmentukshort	ISV(	en_US
dc.description.notes	Fremlagt på The Ninth Conference of the Association for Machine Translation in the Americas 2010	en_US
dc.idnumber	x656703570	en_US
dc.publisher.city	Frederiksberg	en_US
dc.publisher.year	2010	en_US