Translating Structured Documents
George Foster, Pierre Isabelle, Roland Kühn · 2010
Machine Translation traditionally treats doc-uments as sets of independent sentences. In many genres, however, documents are highly structured, and their structure contains infor-mation that can be used to improve transla-tion quality. We present a preliminary ap-proach to document translation that uses struc-tural features to modify the behaviour of a language model, at sentence-level granularity. To our knowledge, this is the first attempt to incorporate structural information into statis-tical MT. In experiments on structured En-glish/French documents from the Hansard cor-pus, we demonstrate small but statistically sig-nificant improvements. 1