Abstract
We report on our participation in the IWSLT 2010 evaluation campaign. Similar to previous years, our submitted systems are based on the Moses statistical machine translation toolkit. This year, we also experimented with hierarchical phrase-based models. In addition, we utilized automatic minimum error-rate training instead of manually-guided tuning. We focused more on the BTEC Turkish-English task and explored various experimentations with unsupervised segmentation to measure their effects on the translation performance. We present the results of several contrastive experiments, including those that failed to improve the translation performance.- Anthology ID:
- 2010.iwslt-evaluation.25
- Volume:
- Proceedings of the 7th International Workshop on Spoken Language Translation: Evaluation Campaign
- Month:
- December 2-3
- Year:
- 2010
- Address:
- Paris, France
- Venue:
- IWSLT
- SIG:
- SIGSLT
- Publisher:
- Note:
- Pages:
- 183–188
- Language:
- URL:
- https://aclanthology.org/2010.iwslt-evaluation.25
- DOI:
- Cite (ACL):
- Coskun Mermer, Hamza Kaya, and Mehmet Uğur Doğan. 2010. The TÜBİTAK-UEKAE statistical machine translation system for IWSLT 2010. In Proceedings of the 7th International Workshop on Spoken Language Translation: Evaluation Campaign, pages 183–188, Paris, France.
- Cite (Informal):
- The TÜBİTAK-UEKAE statistical machine translation system for IWSLT 2010 (Mermer et al., IWSLT 2010)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2010.iwslt-evaluation.25.pdf