- 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.
- Copyright:
- 2006 by ACL. All Rights Reserved
- Links To Paper
- 1st Link
- Bibtex format
- @InProceedings{EDI-INF-RR-0731,
- author = {
Philipp Koehn
and Franz Josef Och
and Daniel Marcu
},
- title = {Statistical phrase-based translation},
- book title = {Proceedings of HLT-NAACL 2003 (Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics)},
- publisher = {ACL},
- year = 2003,
- pages = {48-54},
- url = {http://acl.ldc.upenn.edu/N/N03/N03-1017.pdf},
- }
|