Paper: Forest-to-String Statistical Translation Rules

ACL ID P07-1089
Title Forest-to-String Statistical Translation Rules
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2007
Authors

In this paper, we propose forest-to-string rules to enhance the expressive power of tree-to-string translation models. A forest- to-string rule is capable of capturing non- syntactic phrase pairs by describing the cor- respondence between multiple parse trees and one string. To integrate these rules into tree-to-string translation models, auxil- iary rules are introduced to provide a gen- eralization level. Experimental results show that, on the NIST 2005 Chinese-English test set, the tree-to-string model augmented with forest-to-string rules achieves a relative im- provement of 4.3% in terms of BLEU score over the original model which allows tree- to-string rules only.