Gappy Phrasal Alignment By Agreement

8 years 3 months ago
Gappy Phrasal Alignment By Agreement
We propose a principled and efficient phraseto-phrase alignment model, useful in machine translation as well as other related natural language processing problems. In a hidden semiMarkov model, word-to-phrase and phraseto-word translations are modeled directly by the system. Agreement between two directional models encourages the selection of parsimonious phrasal alignments, avoiding the overfitting commonly encountered in unsupervised training with multi-word units. Expanding the state space to include “gappy phrases” (such as French ne pas) makes the alignment space more symmetric; thus, it allows agreement between discontinuous alignments. The resulting system shows substantial improvements in both alignment quality and translation quality over word-based Hidden Markov Models, while maintaining asymptotically equivalent runtime.
Mohit Bansal, Chris Quirk, Robert C. Moore
Added 23 Aug 2011
Updated 23 Aug 2011
Type Journal
Year 2011
Where ACL
Authors Mohit Bansal, Chris Quirk, Robert C. Moore
Comments (0)