Paper: A Convex Alternative to IBM Model 2

ACL ID D13-1164
Title A Convex Alternative to IBM Model 2
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2013

The IBM translation models have been hugely influential in statistical machine translation; they are the basis of the alignment models used in modern translation systems. Exclud- ing IBM Model 1, the IBM translation mod- els, and practically all variants proposed in the literature, have relied on the optimization of likelihood functions or similar functions that are non-convex, and hence have multiple lo- cal optima. In this paper we introduce a con- vex relaxation of IBM Model 2, and describe an optimization algorithm for the relaxation based on a subgradient method combined with exponentiated-gradient updates. Our ap- proach gives the same level of alignment ac- curacy as IBM Model 2.