Paper: The Automatic Translation Of Discourse Structures

ACL ID A00-2002
Title The Automatic Translation Of Discourse Structures
Venue Annual Conference of the North American Chapter of the Association for Computational Linguistics
Session Main Conference
Year 2000

We empirically show that there are significant differ- ences between the discourse structure of Japanese texts and the discourse structure of their corre- sponding English translations. To improve trans- lation quality, we propose a computational model for rewriting discourse structures. When we train our model on a parallel corpus of manually built Japanese and English discourse structure trees, we learn to rewrite Japanese trees as trees that are closer to the natural English rendering than the orig- inal ones. 1 Motivation Almost all current MT systems process text one sen- tence at a time. Because of this limited focus, MT systems cannot re-group and re-order the clauses and sentences of an input text to achieve the most natural rendering in a target language. Yet, even between languag...