Combining Outputs from Multiple Machine Translation Systems

Currently there are several approaches to machine translation (MT) based on different paradigms; e.g., phrasal, hierarchical and syntax-based. These three approaches yield similar translation accuracy despite using fairly different levels of linguistic knowledge. The availability of such a variety of systems has led to a growing interest toward finding better translations by combining outputs from multiple systems. This paper describes three different approaches to MT system combination. These combination methods operate on sentence, phrase and word level exploiting information from ¤ -best lists, system scores and target-to-source phrase alignments. The word-level combination provides the most robust gains but the best results on the development test sets (NIST MT05 and the newsgroup portion of GALE 2006 dry-run) were achieved by combining all three methods.

• Type: Conference
• Year: 2007
• Where: NAACL
• Authors: Antti-Veikko I. Rosti, Necip Fazil Ayan, Bing Xiang, Spyridon Matsoukas, Richard M. Schwartz, Bonnie J. Dorr
• Keywords: Combination Methods, Computational Linguistics, NAACL 2007, Similar Translation Accuracy, Target-to-source Phrase Alignments