First steps towards multi-engine machine translation

We motivate our contribution to the shared MT task as a first step towards an inte-grated architecture that combines advan-tages of statistical and knowledge-based approaches. Translations were generated using the Pharaoh decoder with tables de-rived from the provided alignments for all four languages, and for three of them us-ing web-based and locally installed com-mercial systems. We then applied statis-tical and heuristic algorithms to select the most promising translation out of each set of candidates obtained from a source sen-tence. Results and possible refinements are discussed. 1 Motivation and Long-term Perspective ”The problem of robust, efficient and reliable speech-to-speech translation can only be cracked by the combined muscle of deep and shallow pro-cessing approaches. ” (Wahlster, 2001) Although this statement has been coined in the context of VerbMo-bil, aiming at translation for direct communication, it appears also realistic for many other translation scenarios, where demands on robustness, coverage, or adaptability on the input side and quality on the output side go beyond today’s technological possi-bilities. The increasing availability of MT engines and the need for better quality has motivated con-siderable efforts to combine multiple engines into one “super-engine ” that is hopefully better than any of its ingredients, an idea pionieered in (Frederking and Nirenburg, 1994). So far, the larger group of related publications has focused on the task of se-lecting, from a set of translation candidates obtained from different engines, one translation that looks most promising (Tidhar and Küssner, 2000; Akiba et al., 2001; Callison-Burch and Flournoy, 2001; Ak-iba et al., 2002; Nomoto, 2004). But also the more challenging problem of decomposing the candidates and re-assembling from the pieces a new sentence, hopefully better than any of the given inputs, has recently gained considerable attention (Rayner an