Abstract
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.- Anthology ID:
- 2012.iwslt-papers.12
- Volume:
- Proceedings of the 9th International Workshop on Spoken Language Translation: Papers
- Month:
- December 6-7
- Year:
- 2012
- Address:
- Hong Kong, Table of contents
- Venue:
- IWSLT
- SIG:
- SIGSLT
- Publisher:
- Note:
- Pages:
- 229–236
- Language:
- URL:
- https://aclanthology.org/2012.iwslt-papers.12
- DOI:
- Cite (ACL):
- Frédéric Blain, Holger Schwenk, and Jean Senellart. 2012. Incremental adaptation using translation information and post-editing analysis. In Proceedings of the 9th International Workshop on Spoken Language Translation: Papers, pages 229–236, Hong Kong, Table of contents.
- Cite (Informal):
- Incremental adaptation using translation information and post-editing analysis (Blain et al., IWSLT 2012)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2012.iwslt-papers.12.pdf