Improving translation memory matching and retrieval using paraphrases
Authors
Gupta, RohitOrasan, Constantin
Zampieri, Marcos
Vela, Mihaela
van Genabith, Josef
Mitkov, Ruslan
Issue Date
2016-11-02
Metadata
Show full item recordAbstract
Most of the current Translation Memory (TM) systems work on string level (character or word level) and lack semantic knowledge while matching. They use simple edit-distance calculated on surface-form or some variation on it (stem, lemma), which does not take into consideration any semantic aspects in matching. This paper presents a novel and efficient approach to incorporating semantic information in the form of paraphrasing in the edit-distance metric. The approach computes edit-distance while efficiently considering paraphrases using dynamic programming and greedy approximation. In addition to using automatic evaluation metrics like BLEU and METEOR, we have carried out an extensive human evaluation in which we measured post-editing time, keystrokes, HTER, HMETEOR, and carried out three rounds of subjective evaluations. Our results show that paraphrasing substantially improves TM matching and retrieval, resulting in translation performance increases when translators use paraphrase-enhanced TMs.Citation
Gupta, R., Orăsan, C., Zampieri, M. et al. (2016) Improving translation memory matching and retrieval using paraphrases. Machine Translation 30 (1), pp 19–40.Publisher
Springer NatureJournal
Machine TranslationAdditional Links
http://link.springer.com/10.1007/s10590-016-9180-0Type
Journal articleLanguage
enDescription
This is an accepted manuscript of an article published by Springer Nature in Machine Translation on 02/11/2016, available online: https://doi.org/10.1007/s10590-016-9180-0 The accepted version of the publication may differ from the final published version.ISSN
0922-6567ae974a485f413a2113503eed53cd6c53
10.1007/s10590-016-9180-0
Scopus Count
The following licence applies to the copyright and re-use of this item:
- Creative Commons
Except where otherwise noted, this item's license is described as Archived with thanks to Machine Translation