A hierarchical phrase-based model for statistical machine translation
2005pp. 263–270
Citations Over TimeTop 1% of 2005 papers
Abstract
We present a statistical phrase-based translation model that uses hierarchical phrases---phrases that contain subphrases. The model is formally a synchronous context-free grammar but is learned from a bitext without any syntactic information. Thus it can be seen as a shift to the formal machinery of syntax-based translation systems without any linguistic commitment. In our experiments using BLEU as a metric, the hierarchical phrase-based model achieves a relative improvement of 7.5% over Pharaoh, a state-of-the-art phrase-based system.
Related Papers
- → Machine translation based on logically isomorphic Montague grammars(1982)21 cited
- → Generate and Repair Machine Translation(2002)9 cited
- → Optimization of English Automated Translation Depending on Weak Grammar Rules(2020)1 cited
- Obtaining Word Phrases with Stochastic Inversion Translation Grammars for Phrase-based Statistical Machine Translation.(2006)
- Основные факторы улучшения машинного перевода(2015)