Paper: Dealing with Spurious Ambiguity in Learning ITG-based Word Alignment

ACL ID P11-2066
Title Dealing with Spurious Ambiguity in Learning ITG-based Word Alignment
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2011
Authors

Word alignment has an exponentially large search space, which often makes exact infer- ence infeasible. Recent studies have shown that inversion transduction grammars are rea- sonable constraints for word alignment, and that the constrained space could be efficiently searched using synchronous parsing algo- rithms. However, spurious ambiguity may oc- cur in synchronous parsing and cause prob- lems in both search efficiency and accuracy. In this paper, we conduct a detailed study of the causes of spurious ambiguity and how it ef- fects parsing and discriminative learning. We also propose a variant of the grammar which eliminates those ambiguities. Our grammar shows advantages over previous grammars in both synthetic and real-world experiments.