Currently most statistical machine translation systems make use of alignments as a first step in the process of training the actual translation models. Several researchers have investigated how to improve the alignment quality, with the (intuitive) assumption that better alignments increase the translation quality. In this paper we will investigate this assumption and show that this is not alwa...

Nowadays, most of the statistical translation systems are based in phrases (i.e. groups of words). Here, we study different improvements to the standard phrasebased translation system. We describe a modified method for the phrase extraction which deals with larger phrases while keeping a reasonable number of phrases. We also propose additional features which lead to a clear improvement in the p...

This paper describes statistical machine translation system of ISTIC used in the evaluation campaign of the patent machine translation task at NTCIR-9. In this year's evaluation, we participated in patent machine translation task for ChineseEnglish. Here we mainly describe the overview of the system, the primary modules, the key techniques and the evaluation results.

In this paper, we re-visit the foundations of the statistical approach to machine translation and study two forms of the Bayes decision rule: the common rule for minimizing the number of string errors and a novel rule for minimizing the number of symbol errors. The Bayes decision rule for minimizing the number of string errors is widely used, but its justification is rarely questioned. We study...

We present the results of the WMT13 shared tasks, which included a translation task, a task for run-time estimation of machine translation quality, and an unofficial metrics task. This year, 143 machine translation systems were submitted to the ten translation tasks from 23 institutions. An additional 6 anonymized systems were included, and were then evaluated both automatically and manually, i...

In this year’s CLEF submissions we focus on using a state-of-the-art statistical machine translation approach for ad-hoc cross-language retrieval. Our machine translation approach is phrase-based as opposed to statistical word-based approaches that have been previously used for query translation in cross-language IR. The phrase translation probabilities were estimated by using the Europarl corp...