Paper: Are Very Large N-Best Lists Useful for SMT?

ACL ID N07-2015
Title Are Very Large N-Best Lists Useful for SMT?
Venue Human Language Technologies
Session Short Paper
Year 2007
Authors

This paper describes an efficient method to extract large n-best lists from a word graph produced by a statistical machine translation system. The extraction is based on the k shortest paths algorithm which is efficient even for very large k. We show that, although we can generate large amounts of distinct translation hypothe- ses, these numerous candidates are not able to significantly improve overall sys- tem performance. We conclude that large n-best lists would benefit from better dis- criminating models.