We present improvements to a greedy decoding algorithm for statistical machine translation that reduce its time complexity from at least cubic (O(n^6) when applied navely) to practically linear time without sacrificing translation quality. We achieve this by integrating hypothesis evaluation into hypothesis creation, tiling improvements over the translation hypothesis at the end of each search iteration, and by imposing restrictions on the amount of word reordering during decoding.

In this paper we describe MARIE, an Ngram-based statistical machine translation decoder. It is implemented using a beam search strategy, with distortion (or reordering) capabilities. The underlying translation model is based on an Ngram approach, extended to introduce reordering at the phrase level. The search graph structure is designed to perform very accurate comparisons, what allows for a high level of pruning, improving the decoder efficiency. We report several techniques for efficiently prune out the search space. The combinatory explosion of the search space derived from the search graph structure is reduced by limiting the number of reorderings a given translation is allowed to perform, and also the maximum distance a word (or a phrase) is allowed to be reordered. We finally report translation accuracy results on three different translation tasks.

This paper describes an alternative translation model based on a text chunk under the framework of statistical machine translation. The translation model suggested here first performs chunking. Then, each word in a chunk is translated. Finally, translated chunks are reordered. Under this scenario of translation modeling, we have experimented on a broadcoverage Japanese-English traveling corpus and achieved improved performance. 1

Typically, the lexicon models used in statistical machine translation systems do not include any kind of linguistic or contextual information, which often leads to problems in performing a correct word-sense disambiguation. One way to deal with this problem within the statistical framework is using maximum entropy methods. In this paper, we present how to use this information within a statistical machine translation system. We show that it is possible to significantly decrease training and test corpus perplexity of the translation models. In addition, we perform a rescoring of N-Best lists using our maximum entropy model and thereby yield an improvement in translation quality. Experimental results are presented with the so called "Vermobil Task".

This paper presents a decoder for statistical machine translation that can take advantage of the example-based machine translation framework. The decoder presented here is based on the greedy approach to the decoding problem, but the search is initiated from a similar translation extracted from a bilingual corpus. The experiments on multilingual translations showed that the proposed method was far superior to a word-by-word generation beam search algorithm. 1

This paper presents a statistical machine translation trained on normalized corpora. The automatic paraphrasing is carried out by inducing paraphrasing expressions from a bilingual corpus. Then, the normalization is treated as a specific paraphrase of a given input determined by the frequency in a corpus. The experimental results on Japanese-to-English translation with normalized English corpus exhibited the reduction of word-error-rate by 8 % and the improvement of subjective evaluation from 70 % into 72.5%. 1.

This paper describes a decoding algorithm for statistical machine translation based on phrases. In the past, the solution to the decoding problem were inspired from that of speech recognizers, translating each input word into one or more output words generating in left-to-right direction. The algorithm presented here iteratively constructs phrases or chunks of cepts until all the input words are consumed. This behavior resulted in computational complexity higher than those with left-to-right constraints, though the translation accuracy is better from the Japanese-to-English translation experiments. 1.

In this paper we study a set of problems that are of considerable importance to Statistical Machine Translation (SMT) but which have not been addressed satisfactorily by the SMT research community. Over the last