In this paper, we present a novel approach to combine the outputs of multiple MT engines into a consensus translation. In contrast to previous Multi-Engine Machine Translation (MEMT) techniques, we do not rely on word alignments of output hypotheses, but prepare the input sentence for multi-engine processing. We do this by using a recursive decomposition algorithm that produces simple chunks as input to the MT engines. A consensus translation is produced by combining the best chunk translations, selected through majority voting, a trigram language model score and a confidence score assigned to each MT engine. We report statistically significant relative improvements of up to 9 % BLEU score in experiments (English→Spanish) carried out on an 800sentence test set extracted from the Penn-II Treebank. 1

Abstract This chapter has two main aims: (i) to present the state-of-the-art in Machine Translation (MT), namely Phrase-Based Statistical MT, together with the major competing paradigms used in MT research and development today; and (ii) to provide an overview of the MT research carried out by my team here at DCU, characterised here in terms of ‘hybrid MT’. In addition, we provide our views on the directions that MT research might take in the near future, and conclude the chapter with lists of further reading for the interested reader.

for the Language Pair Italian-English This paper reports on an experiment investigating how effective free online machine translation (MT) is in helping Internet users to access the contents of websites written only in languages they do not know. This study explores the extent to which using Internet-based MT tools affects the confidence of web-surfers in the reliability of the information they find on websites available only in languages unfamiliar to them. The results of a case study for the language pair Italian-English involving 101 participants show that the chances of identifying correctly basic information (i.e. understanding the nature of websites and finding contact telephone numbers from their web-pages) are consistently enhanced to varying degrees (up to nearly 20%) by translating online content into a familiar language. In addition, confidence ratings given by users to the reliability and accuracy of the information they find are significantly higher (with increases between 5 and 11%) when they translate websites into their preferred language with free online MT services.

In this article, we describe our experiences with modifying and applying AnswerFinder, a generic question answering system that was originally designed to perform textbased question answering in English only, to multi-lingual question answering. In particular, we participated in the Dutch-English task. To enable handling of Dutch questions, we added a machine translation phase, where we used Systran to provide the Dutch to English translations. The translated questions were passed verbatim to AnswerFinder. Additionally, a simple form of anaphora resolution was implemented and since AnswerFinder did not have a document retrieval phase, this was added as well. The document retrieval system used is based on Xapian and simply searches for relevant documents based on the words in the question. Due to the nature and quality of the translated questions and the lack of tuning, we expected (and received) low quality results. The main purpose of our participation was to investigate the flexibility, portability, and scalability of the generic question answering system.

We present our initial strategy for Spanish-to-Basque MultiEngine Machine Translation, a language pair with very different structure and word order and with no huge parallel corpus available. This hybrid proposal is based on the combination of three different MT paradigms: Example-Based MT, Statistical MT and Rule-Based MT. We have evaluated the system, reporting automatic evaluation metrics for a corpus in a test domain. The first results obtained are encouraging. 1