A simple, fast strategy for weighted alignment hypergraph

Abstract

Weighted alignment hypergraph [4] is potentially useful for statistical machine translation, because it is the first study to simultaneously exploit the compact representation and fertility model of word alignment. Since estimating the probabilities of rules extracted from hypergraphs is an NP-complete problem, they propose a divide-andconquer strategy by decomposing a hypergraph into a set of independent subhypergraphs. However, they employ a Bull's algorithm to enumerate all consistent alignments for each rule in each subhypergraph, which is very time-consuming especially for the rules that contain non-terminals. This limits the applicability of this method to the syntax translation models, the rules of which contain many non-terminals (e.g. SCFG rules). In response to this problem, we propose an inside-outside algorithm to efficiently enumerate the consistent alignments. Experimental results show that our method is twice as fast as the Bull's algorithm. In addition, the efficient dynamic programming algorithm makes our approach applicable to syntax-based translation models. © Springer-Verlag Berlin Heidelberg 2013.