Paper: Detecting Narrativity to Improve English to French Translation of Simple Past Verbs

ACL ID W13-3305
Title Detecting Narrativity to Improve English to French Translation of Simple Past Verbs
Venue Discourse in Machine Translation
Session
Year 2013
Authors

The correct translation of verb tenses en- sures that the temporal ordering of events in the source text is maintained in the tar- get text. This paper assesses the utility of automatically labeling English Simple Past verbs with a binary discursive fea- ture, narrative vs. non-narrative, for sta- tistical machine translation (SMT) into French. The narrativity feature, which helps deciding which of the French past tenses is a correct translation of the En- glish Simple Past, can be assigned with about 70% accuracy (F1). The narrativity feature improves SMT by about 0.2 BLEU points when a factored SMT system is trained and tested on automatically labeled English-French data. More importantly, manual evaluation shows that verb tense translation and verb choice are improved by respectively 9....