A Novel Translation Framework Based on Rhetorical Structure Theory
Mei Tu, Yu Zhou, Chengqing Zong · 2014
Rhetorical structure theory (RST) is widely used for discourse understanding, which repre-sents a discourse as a hierarchically semantic structure. In this paper, we propose a novel translation framework with the help of RST. In our framework, the translation process mainly includes three steps: 1) Source RST-tree ac-quisition: a source sentence is parsed into an RST tree; 2) Rule extraction: translation rules are extracted from the source tree and the tar-get string via bilingual word alignment; 3) RST-based translation: the source RST-tree is translated with translation rules. Experi-ments on Chinese-to-English show that our RST-based approach achieves improvements of 2.3/0.77/1.43 BLEU points on NIST04/NIST05/CWMT2008 respectively. 1