Publication
The paper presents machine translation experiments from English to Czech with a large amount of manually annotated discourse connectives. The gold-standard discourse relation annotation leads to better translation performance in ranges of 4–60% for some ambiguous English connectives and helps to find correct syntactical constructs in Czech for less ambiguous connectives. Automatic scoring confirms the stability of the newly built discourse-aware translation systems. Error analysis and human translation evaluation point to the cases where the annotation was most and where less helpful.
Lesly Sadiht Miculicich Werlen
Sebastian Maerkl, Ragunathan Bava Ganesh
Johan Auwerx, Kristina Schoonjans, Felix Naef, Xiaoxu Li, Hao Li, Wen Gao, Nagammal Neelagandan, Yang Li, Amélia Lalou, Yuan Liu