Multi-source translation methods
Lane Schwartz · 2008
Multi-parallel corpora provide a potentially rich resource for machine translation. This pa-per surveys existing methods for utilizing such resources, including hypothesis ranking and system combination techniques. We find that despite significant research into system com-bination, relatively little is know about how best to translate when multiple parallel source languages are available. We provide results to show that the MAX multilingual multi-source hypothesis ranking method presented by Och and Ney (2001) does not reliably improve translation quality when a broad range of lan-guage pairs are considered. We also show that the PROD multilingual multi-source hypoth-esis ranking method of Och and Ney (2001) cannot be used with standard phrase-based translation engines, due to a high number of unreachable hypotheses. Finally, we present an oracle experiment which shows that cur-rent hypothesis ranking methods fall far short of the best results reachable via sentence-level ranking. 1