The LIG English to French machine translation system for IWSLT 2012
Laurent Besacier, Benjamin Lecouteux, Marwen Azouzi, Ngoc Quang Luong
Abstract
This paper presents the LIG participation to the E-F MT task of IWSLT 2012. The primary system proposed made a large improvement (more than 3 point of BLEU on tst2010 set) compared to our last year participation. Part of this improvment was due to the use of an extraction from the Gigaword corpus. We also propose a preliminary adaptation of the driven decoding concept for machine translation. This method allows an efficient combination of machine translation systems, by rescoring the log-linear model at the N-best list level according to auxiliary systems: the basis technique is essentially guiding the search using one or previous system outputs. The results show that the approach allows a significant improvement in BLEU score using Google translate to guide our own SMT system. We also try to use a confidence measure as an additional log-linear feature but we could not get any improvment with this technique.- Anthology ID:
- 2012.iwslt-evaluation.13
- Volume:
- Proceedings of the 9th International Workshop on Spoken Language Translation: Evaluation Campaign
- Month:
- December 6-7
- Year:
- 2012
- Address:
- Hong Kong, Table of contents
- Venue:
- IWSLT
- SIG:
- SIGSLT
- Publisher:
- Note:
- Pages:
- 102–108
- Language:
- URL:
- https://aclanthology.org/2012.iwslt-evaluation.13
- DOI:
- Cite (ACL):
- Laurent Besacier, Benjamin Lecouteux, Marwen Azouzi, and Ngoc Quang Luong. 2012. The LIG English to French machine translation system for IWSLT 2012. In Proceedings of the 9th International Workshop on Spoken Language Translation: Evaluation Campaign, pages 102–108, Hong Kong, Table of contents.
- Cite (Informal):
- The LIG English to French machine translation system for IWSLT 2012 (Besacier et al., IWSLT 2012)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2012.iwslt-evaluation.13.pdf