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

This paper describes the CMU entry for the system combination shared task at WMT’09. Our combination method is hypothesis selection, which uses information from n-best lists from several MT systems. The sentence level features are independent from the MT systems involved. To compensate for various n-best list sizes in the workshop shared task including firstbest-only entries, we normalize one of our high-impact features for varying sub-list size. We combined restricted data track

This paper describes the incremental hypothesis alignment algorithm used in the BBN submissions to the WMT09 system combination task. The alignment algorithm used a sentence specific alignment order, flexible matching, and new shift heuristics. These refinements yield more compact confusion networks compared to using the pair-wise or incremental TER alignment algorithms. This should reduce the number of spurious insertions in the system combination output and the system combination weight tuning converges faster. System combination experiments on the WMT09 test sets from five source languages to English are presented. The best BLEU scores were achieved by combing the English outputs of three systems from all five source languages. 1

We describe a synthetic method for combining machine translations produced by different systems given the same input. One-best outputs are explicitly aligned to remove duplicate words. Hypotheses follow system outputs in sentence order, switching between systems mid-sentence to produce a combined output. Experiments with the WMT 2009 tuning data showed improvement of 2 BLEU and 1 METEOR point over the best Hungarian-English system. Constrained to data provided by the contest, our system was submitted to the WMT 2009 shared system combination task. 1

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

Current system combination methods usually use confusion networks to find consensus translations among different systems. Requiring one-to-one mappings between the words in candidate translations, confusion networks have difficulty in handling more general situations in which several words are connected to another several words. Instead, we propose a lattice-based system combination model that allows for such phrase alignments and uses lattices to encode all candidate translations. Experiments show that our approach achieves significant improvements over the state-ofthe-art baseline system on Chinese-to-English translation test sets. 1

The Carnegie Mellon multi-engine machine translation software merges output from several machine translation systems into a single improved translation. This improvement is significant: in the recent NIST MT09 evaluation, the combined Arabic-English output scored 5.22 BLEU points higher than the best individual system. Concurrent with this paper, we release the source code behind this result consisting of a recombining beam search decoder, the combination search space and features, and several accessories. Here we describe how the released software works and its use. 1.

System combination is a technique which has been shown to yield significant gains in speech recognition and machine translation. Most combination schemes perform an alignment between different system outputs in order to produce lattices (or confusion networks), from which a composite hypothesis is chosen, possibly with the help of a large language model. The benefit of this approach is two-fold: (i) whenever many systems agree with each other on a set of words, the combination output contains these words with high confidence; and (ii) whenever the systems disagree, the language model resolves the ambiguity based on the (probably correct) agreedupon context. The case of machine translation system combination is more challenging because of the different word orders of the translations: the alignment has to incorporate computationally expensive movements of word blocks. In this paper, we show how one can combine translation outputs efficiently, extending the incremental alignment procedure of [1]. A comparison between different system combination design choices is performed on an Arabic speech translation task.

This paper presents a new hypothesis alignment method for combining outputs of multiple machine translation (MT) systems. Traditional hypothesis alignment algorithms such as TER, HMM and IHMM do not directly utilise the context information of the source side but rather address the alignment issues via the output data itself. In this paper, a source-side context-informed (SSCI) hypothesis alignment method is proposed to carry out the word alignment and word reordering issues. First of all, the source–target word alignment links are produced as the hidden variables by exporting source phrase spans during the translation decoding process. Secondly, a mapping strategy and normalisation model are employed to acquire the 1-to-1 alignment links and build the confusion network (CN). The source-side context-based method outperforms the state-of-the-art TERbased alignment model in our experiments on the WMT09 English-to-French and NIST Chinese-to-English data sets respectively. Experimental results demonstrate that our proposed approach scores consistently among the best results across different data and language pair conditions. 1

Inspired by the incremental TER alignment, we re-designed the Indirect HMM (IHMM) alignment, which is one of the best hypothesis alignment methods for conventional MT system combination, in an incremental manner. One crucial problem of incremental alignment is to align a hypothesis to a confusion network (CN). Our incremental IHMM alignment is implemented in three different ways: 1) treat CN spans as HMM states and define state transition as distortion over covered n-grams between two spans; 2) treat CN spans as HMM states and define state transition as distortion over words in component translations in the CN; and 3) use a consensus decoding algorithm over one hypothesis and multiple IHMMs, each of which corresponds to a component translation in the CN. All these three approaches of incremental alignment based on IHMM are shown to be superior to both incremental TER alignment and conventional IHMM alignment in the setting of the Chinese-to-English track of the 2008 NIST Open MT evaluation. 1