Incremental adaptation using translation informations and post-editing analysis
Average rating
Cast your vote
You can rate an item by clicking the amount of stars they wish to award to this item.
When enough users have cast their vote on this item, the average rating will also be shown.
Star rating
Your vote was cast
Thank you for your feedback
Thank you for your feedback
Issue Date
2012-12-06
Metadata
Show full item recordAbstract
It is well known that statistical machine translation systems perform best when they are adapted to the task. In this paper we propose new methods to quickly perform incremental adaptation without the need to obtain word-by-word alignments from GIZA or similar tools. The main idea is to use an automatic translation as pivot to infer alignments between the source sentence and the reference translation, or user correction. We compared our approach to the standard method to perform incremental re-training. We achieve similar results in the BLEU score using less computational resources. Fast retraining is particularly interesting when we want to almost instantly integrate user feed-back, for instance in a post-editing context or machine translation assisted CAT tool. We also explore several methods to combine the translation models.Citation
Blain, F., Schwenk, H. and Senellart, J. (2012) Incremental adaptation using translation informations and post-editing analysis. In Sumita, E. et al. (eds.) Proceedings of the International Workshop on Spoken Language Translation, 6th-7th December, 2012, Hong Kong.Publisher
IWSLTAdditional Links
http://hltc.cs.ust.hk/iwslt/proceedings/Proceedings_Iwslt2012.pdfType
Conference contributionLanguage
enDescription
This is an accepted manuscript of an article published by IWSLT in Proceedings of the International Workshop on Spoken Language Translation 2012, available online: http://hltc.cs.ust.hk/iwslt/proceedings/Proceedings_Iwslt2012.pdf The accepted version of the publication may differ from the final published version.
Except where otherwise noted, this item's license is described as https://creativecommons.org/licenses/by-nc-nd/4.0/