Prior derivation models for formally syntax-based translation using linguistically syntactic parsing and tree kernels

Abstract

This paper presents an improved formally syntax-based SMT model, which is enriched by linguistically syntactic knowledge obtained from statistical constituent parsers. We propose a linguistically-motivated prior derivation model to score hypothesis derivations on top of the baseline model during the translation decoding. Moreover, we devise a fast training algorithm to achieve such improved models based on tree kernel methods. Experiments on an English-to-Chinese task demonstrate that our proposed models outperformed the baseline formally syntax-based models, while both of them achieved significant improvements over a state-of-the-art phrase-based SMT system.