Efficient Dynamic Programming Search Algorithms for Phrase-Based SMT

Abstract

This paper presents a series of efficient dynamic-programming (DP) based algorithms for phrase-based decoding and alignment computation in statistical machine translation (SMT). The DP-based decoding algorithms are analyzed in terms of shortest path-finding algorithms, where the similarity to DP-based decoding algorithms in speech recognition is demonstrated. The paper contains the following original contributions: 1) the DP-based decoding algorithm in (Tillmann and Ney, 2003) is extended in a formal way to handle phrases and a novel pruning strategy with increased translation speed is presented 2) a novel alignment algorithm is presented that computes a phrase alignment efficiently in the case that it is consistent with an underlying word alignment. Under certain restrictions, both algorithms handle MT-related problems efficiently that are generally NP complete (Knight, 1999).