Exploiting multi-lingual text potentialities in EBMT systems

Translating documents from a source to a target language is a repetitive activity. The attempt to automate such a difficult task has been a long-term scientific dream. Among the several types of approaches in machine translation (MT), one of the most promising paradigms is example-based machine translation (EBMT). An EBMT system translates by analogy, using past translations to translate other similar source-language material into the target language. In this paper, we introduce EXTRA (EXample-based TRanslation Assistant), a complete EBMT system that exploits some innovative ideas in information retrieval and multilingual text management to effectively and efficiently extract useful suggestions from past translations and present them to the translator. This work has been developed as a joint work with the LOGOS group, a worldwide leader in multilingual document translation.