Sciweavers

NAACL
2003

Statistical Phrase-Based Translation

13 years 5 months ago
Statistical Phrase-Based Translation
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-accuracy wordlevel alignment models does not have a strong impact on performance. Learning only syntactically motivated phrases degrades the performance of our systems.
Philipp Koehn, Franz Josef Och, Daniel Marcu
Added 31 Oct 2010
Updated 31 Oct 2010
Type Conference
Year 2003
Where NAACL
Authors Philipp Koehn, Franz Josef Och, Daniel Marcu
Comments (0)