Paper: A Novel Graph-based Compact Representation of Word Alignment

ACL ID P13-2064
Title A Novel Graph-based Compact Representation of Word Alignment
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2013
Authors

In this paper, we propose a novel compact representation called weighted bipartite hypergraph to exploit the fertility model, which plays a critical role in word align- ment. However, estimating the probabili- ties of rules extracted from hypergraphs is an NP-complete problem, which is com- putationally infeasible. Therefore, we pro- pose a divide-and-conquer strategy by de- composing a hypergraph into a set of inde- pendent subhypergraphs. The experiments show that our approach outperforms both 1-best and n-best alignments.