| Publication Type | Conference Paper |
| Year of Publication | 2003 |
| Authors | Koehn, P.; Och, F.J.; Marcu, D. |
| Conference Name | Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics (HLT-NAACL 2003) |
| Pagination | 127--133 |
| Conference Start Date | May 27 - June 1 |
| Conference Location | Edmonton, Canada |
| Abstract | We propose a new phrase-based translation model and decoding algorithm that enables us to evaluate and compare several, previously proposed phrase-based translation models. Within our framework, we carry out a large number of experiments to understand better and explain why phrase-based models outperform word-based models. Our empirical results, which hold for all examined language pairs, suggest that the highest levels of performance can be obtained through relatively simple means: heuristic learning of phrase translations from word-based alignments and lexical weighting of phrase translations. Surprisingly, learning phrases longer than three words and learning phrases from high-accuracywordlevel alignment models does not have a strong impact on performance. Learning only syntactically motivated phrases degrades the performance of our systems. |
| URL | Click Here |
Statistical Phrase-Based Translation.
- Login to post comments