This paper presents a new hypothesis alignment method for combining outputs of multiple machine translation (MT) systems. An indirect hidden Markov model (IHMM) is proposed to address the synonym matching and word ordering issues in hypothesis alignment. Unlike traditional HMMs whose parameters are trained via maximum likelihood estimation (MLE), the parameters of the IHMM are estimated indirectly from a variety of sources including word semantic similarity, word surface similarity, and a distance-based distortion penalty. The IHMM-based method significantly outperforms the state-of-the-art TER-based alignment model in our experiments on NIST benchmark datasets. Our combined SMT system using the

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

We present a word substitution approach to combine the output of different machine translation systems. Using part of speech information, candidate words are determined among possible translation options, which in turn are estimated through a precomputed word alignment. Automatic substitution is guided by several decision factors, including part of speech, local context, and language model probabilities. The combination of these factors is defined after careful manual analysis of their respective impact. The approach is tested for the language pair German-English, however the general technique itself is language independent. 1

Recently confusion network decoding shows the best performance in combining outputs from multiple machine translation (MT) systems. However, overcoming different word orders presented in multiple MT systems during hypothesis alignment still remains the biggest challenge to confusion network-based MT system combination. In this paper, we compare four commonly used word alignment 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 hypothesis 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 Chinese-to-English spoken and written language tasks. 1

TER-Plus (TERp) is an extended TER evaluation metric incorporating morphology, synonymy and paraphrases. There are three new edit operations

RWTH participated in the System Combination task of the Sixth Workshop on Statistical Machine Translation (WMT 2011). For three language pairs, we combined 6 to 14 systems into a single consensus translation. A three-level metacombination scheme combining six different system combination setups with three different engines was applied on the French–English language pair. Depending on the language pair, improvements versus the best single system are in the range of +1.9 % and +2.5 % abs. on BLEU, and between −1.8 % and −2.4% abs. on TER. Novel techniques compared with RWTH’s submission to WMT 2010 include two additional system combination engines, an additional word alignment technique, meta combination, and additional optimization techniques. 1