Generalizing Word Lattice Translation
Abstract
Word lattice decoding has proven useful in spoken language translation; we argue that it provides a compelling model for translation of text genres, as well. We extend lattice decoding to hierarchical phrase-based models, providing a unified treatment with phrase-based decoding by treating lattices as a case of weighted finite-state automata. In the process, we resolve a significant complication that lattice representations introduce in reordering models. Our experiments evaluating the approach demonstrate substantial gains for Chinese-English and Arabic-English translation.
Document Details
- Document Type
- Technical Report
- Publication Date
- Feb 01, 2008
- Accession Number
- ADA481994
Entities
People
- Christopher Dyer
- Philip Resnik
- Smaranda Muresan
Organizations
- University of Maryland