A Source Dependency Model for Statistical Machine Translation.
Deyi Xiong, Min Zhang, Ai Ti Aw, Haizhou Li · 2009
In the formally syntax-based MT, a hierar-chical tree generated by synchronous CFG rules associates the source sentence with the target sentence. In this paper, we propose a source dependency model to estimate the probability of the hierarchical tree generated in decoding. We develop this source depen-dency model from word-aligned corpus, with-out using any linguistically motivated pars-ing. Our experimental results show that in-tegrating the source dependency model into the formally syntax-based machine transla-tion significantly improves the performance on Chinese-to-English translation tasks. 1