Probabilistic Model for Example-based Machine Translation
Eiji Aramaki, Sadao Kurohashi, Hideki Kashioka, Naoto Kato · 2005
Example-based machine translation (EBMT) systems, so far, rely on heuristic measures in re-trieving translation examples. Such a heuristic measure costs time to adjust, and might make its algorithm unclear. This paper presents a probabilistic model for EBMT. Under the pro-posed model, the system searches the transla-tion example combination which has the high-est probability. The proposed model clearly for-malizes EBMT process. In addition, the model can naturally incorporate the context similarity of translation examples. The experimental re-sults demonstrate that the proposed model has a slightly better translation quality than state-of-the-art EBMT systems. 1