Show simple item record

dc.contributor.authorGupta, Rohit
dc.contributor.authorOrăsan, Constantin
dc.contributor.authorLiu, Qun
dc.contributor.authorMitkov, Ruslan
dc.contributor.editorSojka, Petr
dc.contributor.editorHorak, Ales
dc.contributor.editorKopecek, Ivan
dc.date.accessioned2017-02-13T15:11:53Z
dc.date.available2017-02-13T15:11:53Z
dc.date.issued2016-09
dc.identifier.citationIn: Petr Sojka, Aleš Horák, Ivan Kopeček, Karel Pala (eds), Text, Speech, and Dialogue: olume 9924 of the series Lecture Notes in Computer Science pp 259-269
dc.identifier.isbn9783319455099
dc.identifier.isbn9783319455105 on-line
dc.identifier.urihttp://hdl.handle.net/2436/620374
dc.description.abstractTranslation memory tools lack semantic knowledge like paraphrasing when they perform matching and retrieval. As a result, paraphrased segments are often not retrieved. One of the primary reasons for this is the lack of a simple and efficient algorithm to incorporate paraphrasing in the TM matching process. Gupta and Orăsan [1] proposed an algorithm which incorporates paraphrasing based on greedy approximation and dynamic programming. However, because of greedy approximation, their approach does not make full use of the paraphrases available. In this paper we propose an efficient method for incorporating paraphrasing in matching and retrieval based on dynamic programming only. We tested our approach on English-German, English-Spanish and English-French language pairs and retrieved better results for all three language pairs compared to the earlier approach
dc.description.sponsorshipFP7/2007-2013/ under REA grant agreement no. 317471, Funded by: FP7 People Programme
dc.language.isoen
dc.publisherSpringer
dc.relation.urlhttp://link.springer.com/chapter/10.1007%2F978-3-319-45510-5_30
dc.subjecttranslation memories
dc.subjectmachine translation
dc.subjectsemantically enhanced translation memories
dc.subjectparaphrasing
dc.titleA Dynamic Programming Approach to Improving Translation Memory Matching and Retrieval Using Paraphrases
dc.typeChapter in book
pubs.place-of-publicationCham, Switzerland
dc.source.beginpage259
dc.source.endpage269
html.description.abstractTranslation memory tools lack semantic knowledge like paraphrasing when they perform matching and retrieval. As a result, paraphrased segments are often not retrieved. One of the primary reasons for this is the lack of a simple and efficient algorithm to incorporate paraphrasing in the TM matching process. Gupta and Orăsan [1] proposed an algorithm which incorporates paraphrasing based on greedy approximation and dynamic programming. However, because of greedy approximation, their approach does not make full use of the paraphrases available. In this paper we propose an efficient method for incorporating paraphrasing in matching and retrieval based on dynamic programming only. We tested our approach on English-German, English-Spanish and English-French language pairs and retrieved better results for all three language pairs compared to the earlier approach


This item appears in the following Collection(s)

Show simple item record