Paper: Exact Decoding of Phrase-Based Translation Models through Lagrangian Relaxation

ACL ID D11-1003
Title Exact Decoding of Phrase-Based Translation Models through Lagrangian Relaxation
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2011
Authors

This paper describes an algorithm for exact decoding of phrase-based translation models, based on Lagrangian relaxation. The method recovers exact solutions, with certificates of optimality, on over 99% of test examples. The method is much more efficient than ap- proaches based on linear programming (LP) or integer linear programming (ILP) solvers: these methods are not feasible for anything other than short sentences. We compare our method to MOSES (Koehn et al., 2007), and give precise estimates of the number and mag- nitude of search errors that MOSES makes.