Abstract
We present the LIA systems for the machine translation evaluation campaign of the International Workshop on Spoken Language Translation (IWSLT) 2014 for the English-to-Slovene and English-to-Polish translation tasks. The proposed approach takes into account word context; first, it maps sentences into a latent Dirichlet allocation (LDA) topic space, then it chooses from this space words that are thematically and grammatically close to mistranslated words. This original post-processing approach is compared with a factored translation system built with MOSES. While this postprocessing method does not allow us to achieve better results than a state-of-the-art system, this should be an interesting way to explore, for example by adding this topic space information at an early stage in the translation process.- Anthology ID:
- 2014.iwslt-evaluation.10
- Volume:
- Proceedings of the 11th International Workshop on Spoken Language Translation: Evaluation Campaign
- Month:
- December 4-5
- Year:
- 2014
- Address:
- Lake Tahoe, California
- Venue:
- IWSLT
- SIG:
- SIGSLT
- Publisher:
- Note:
- Pages:
- 80–85
- Language:
- URL:
- https://aclanthology.org/2014.iwslt-evaluation.10
- DOI:
- Cite (ACL):
- Mohamed Morchid, Stéphane Huet, and Richard Dufour. 2014. A topic-based approach for post-processing correction of automatic translations. In Proceedings of the 11th International Workshop on Spoken Language Translation: Evaluation Campaign, pages 80–85, Lake Tahoe, California.
- Cite (Informal):
- A topic-based approach for post-processing correction of automatic translations (Morchid et al., IWSLT 2014)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2014.iwslt-evaluation.10.pdf