Đang chuẩn bị liên kết để tải về tài liệu:
Báo cáo khoa học: "Minimum Bayes-risk System Combination"

We present minimum Bayes-risk system combination, a method that integrates consensus decoding and system combination into a unified multi-system minimum Bayes-risk (MBR) technique. Unlike other MBR methods that re-rank translations of a single SMT system, MBR system combination uses the MBR decision rule and a linear combination of the component systems’ probability distributions to search for the minimum risk translation among all the finite-length strings over the output vocabulary. | Minimum Bayes-risk System Combination Jesus Gonzalez-Rubio Institute Tecnologico de Informatica U. Politecnica de Valencia 46022 Valencia Spain jegonzalez@iti.upv.es Alfons Juan Francisco Casacuberta D. de Sistemas Informaticos y Computation U. Politecnica de Valencia 46022 Valencia Spain ajuan fcn @dsic.upv.es Abstract We present minimum Bayes-risk system combination a method that integrates consensus decoding and system combination into a unified multi-system minimum Bayes-risk MBR technique. Unlike other MBR methods that re-rank translations of a single SMT system MBR system combination uses the MBR decision rule and a linear combination of the component systems probability distributions to search for the minimum risk translation among all the finite-length strings over the output vocabulary. We introduce expected BLEU an approximation to the BLEU score that allows to efficiently apply MBR in these conditions. MBR system combination is a general method that is independent of specific SMT models enabling us to combine systems with heterogeneous structure. Experiments show that our approach bring significant improvements to single-system-based MBR decoding and achieves comparable results to different state-of-the-art system combination methods. 1 Introduction Once statistical models are trained a decoding approach determines what translations are finally selected. Two parallel lines of research have shown consistent improvements over the max-derivation decoding objective which selects the highest probability derivation. Consensus decoding procedures select translations for a single system with a minimum Bayes risk MBR Kumar and Byrne 2004 . System combination procedures on the other hand generate translations from the output of multiple component systems by combining the best fragments of these outputs Frederking and Nirenburg 1268 1994 . In this paper we present minimum Bayes risk system combination a technique that unifies these two approaches by learning a .