Joint Optimization for Machine Translation System Combination

Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, pages 1202–1211, Singapore, 6-7 August 2009. c⃝2009 ACL and AFNLP Joint Optimization for Machine Translation System Combination Xiaodong He Microsoft Research One Microsoft Way, Redmond, WA xiaohe@microsoft.com Kristina Toutanova Microsoft Research One Microsoft Way, Redmond, WA kristout@microsoft.com Abstract System combination has emerged as a powerful method for machine translation (MT). This paper pursues a joint optimization strategy for combining outputs from multiple MT systems, where word alignment, ordering, and lexical selection decisions are made jointly according to a set of feature functions combined in a single log-linear model. The decoding algorithm is described in detail and a set of new features that support this joint decoding approach is proposed. The approach is evaluated in comparison to state-of-the-art confusion-network-based system combination methods using equivalent features and shown to outperform them significantly. 1 Introduction System combination for machine translation (MT) has emerged as a powerful method of combining the strengths of multiple MT systems and achieving results which surpass those of each individual system (e.g. Bangalore, et. al., 2001, Matusov, et. al., 2006, Rosti, et. al., 2007a). Most state-of-the-art system combination methods are based on constructing a confusion network (CN) from several input translation hypotheses, and choosing the best output from the CN based on several scoring functions (e.g. Rosti et. al., 2007a, He et. al., 2008, Matusov et al. 2008). Confusion networks allow word-level system combination, which was shown to outperform sentence re-ranking methods and phrase-level combination (Rosti, et. al. 2007a). We will review confusion-network-based system combination with the help of the examples in Figures 1 and 2. Figure 1 shows translation hypotheses from three Chinese-to- English MT systems. The general idea is to combine hypotheses in a representation such as the ones in Figure 2, where for each word position there is a set of possible words, shown in columns.1The final output is determined by choosing one word from each column, which can be a real word or the empty word ε. For example, the CN in Figure 2a) can generate eight distinct sequences of words, including e.g. “she bought the Jeep” and “she bought the SUV Jeep”. The choice is performed to maximize a scoring function using a set of features and a log-linear model (Matusov, et. al 2006, Rosti, et al. 2007a). We can view a confusion network as an ordered sequence of columns (correspondence sets). Each word from each input hypothesis belongs to exactly one correspondence set. Each correspondence set contains at most one word from each input hypothesis and contributes exactly one of its words (including the possible ε) to the final output. Final words are output in the order of correspondence sets. In order to construct such a representation, we need to solve the following two sub-problems: arrange words from all input hypotheses into correspondence sets (alignment problem) and order correspondence sets (ordering problem). After constructing the confusion network we need to solve a third sub-problem: decide which words to output from each …

Content truncated to 500 words