Paper: A Comparative Study of Hypothesis Alignment and its Improvement for Machine Translation System Combination

ACL ID P09-1106
Title A Comparative Study of Hypothesis Alignment and its Improvement for Machine Translation System Combination
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2009
Authors

Recently confusion network decoding shows the best performance in combining outputs from multiple machine translation (MT) sys- tems. However, overcoming different word orders presented in multiple MT systems dur- ing hypothesis alignment still remains the biggest challenge to confusion network-based MT system combination. In this paper, we compare four commonly used word align- ment methods, namely GIZA++, TER, CLA and IHMM, for hypothesis alignment. Then we propose a method to build the confusion network from intersection word alignment, which utilizes both direct and inverse word alignment between the backbone and hypo- thesis to improve the reliability of hypothesis alignment. Experimental results demonstrate that the intersection word alignment yields consistent perform...