Paper: Gappy Phrasal Alignment By Agreement

ACL ID P11-1131
Title Gappy Phrasal Alignment By Agreement
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2011

We propose a principled and efficient phrase- to-phrase alignment model, useful in machine translation as well as other related natural lan- guage processing problems. In a hidden semi- Markov model, word-to-phrase and phrase- to-word translations are modeled directly by the system. Agreement between two direc- tional models encourages the selection of par- simonious phrasal alignments, avoiding the overfitting commonly encountered in unsu- pervised training with multi-word units. Ex- panding the state space to include “gappy phrases” (such as French ne star pas) makes the alignment space more symmetric; thus, it al- lows agreement between discontinuous align- ments. The resulting system shows substantial improvements in both alignment quality and translation quality over word-based Hi...