Paper: Revisiting Optimal Decoding for Machine Translation IBM Model 4

ACL ID N09-2002
Title Revisiting Optimal Decoding for Machine Translation IBM Model 4
Venue Human Language Technologies
Session Short Paper
Year 2009
Authors
  • Sebastian Riedel (Research Organization of Information and System, Japan; University of Tokyo, Tokyo Japan)
  • James Clarke (University of Illinois at Urbana-Champaign, Urbana IL)

This paper revisits optimal decoding for statis- tical machine translation using IBM Model 4. We show that exact/optimal inference using Integer Linear Programming is more practical than previously suggested when used in con- junction with the Cutting-Plane Algorithm. In our experiments we see that exact inference can provide a gain of up to one BLEU point for sentences of length up to 30 tokens.