Semantically-Informed Syntactic Machine Translation: A Tree-Grafting Approach

Abstract

We describe a unified and coherent syntactic framework for supporting a semanticallyinformed syntactic approach to statistical machine translation. Semantically enriched syntactic tags assigned to the target-language training texts improved translation quality. The resulting system significantly outperformed a linguistically naive baseline model (Hiero… (More)

Topics

9 Figures and Tables

Slides referencing similar topics