Paper: Effective Use of Function Words for Rule Generalization in Forest-Based Translation

ACL ID P11-1003
Title Effective Use of Function Words for Rule Generalization in Forest-Based Translation
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2011
Authors

In the present paper, we propose the ef- fective usage of function words to generate generalized translation rules for forest-based translation. Given aligned forest-string pairs, we extract composed tree-to-string translation rules that account for multiple interpretations of both aligned and unaligned target func- tion words. In order to constrain the ex- haustive attachments of function words, we limit to bind them to the nearby syntactic chunks yielded by a target dependency parser. Therefore, the proposed approach can not only capture source-tree-to-target-chunk cor- respondences butcan also use forest structures that compactly encode an exponential num- ber of parse trees to properly generate target function words during decoding. Extensive experiments involving large-scale English-t...