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

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 performance improvement for all four word alignment methods on both Chi-nese-to-English spoken and written language tasks.