Phrase-based statistical machine translation as a Traveling Salesman Problem

Abstract

An efficient decoding algorithm is a crucial element of any statistical machine translation system. Some researchers have noted certain similarities between SMT decoding and the famous Traveling Salesman Problem; in particular (Knight, 1999) has shown that any TSP instance can be mapped to a sub-case of a word-based SMT model, demonstrating NP-hardness of the decoding task. In this paper, we focus on the reverse mapping, showing that any phrase-based SMT decoding problem can be directly reformulated as a TSP. The transformation is very natural, deepens our understanding of the decoding problem, and allows direct use of any of the powerful existing TSP solvers for SMT decoding. We test our approach on three datasets, and compare a TSP-based decoder to the popular beam-search algorithm. In all cases, our method provides competitive or better performance. © 2009 ACL and AFNLP.