Paper: Improving Pronoun Translation for Statistical Machine Translation

ACL ID E12-3001
Title Improving Pronoun Translation for Statistical Machine Translation
Venue Annual Meeting of The European Chapter of The Association of Computational Linguistics
Session Student Session
Year 2012

Machine Translation is a well?established field, yet the majority of current systems translate sentences in isolation, losing valu- able contextual information from previ- ously translated sentences in the discourse. One important type of contextual informa- tion concerns who or what a coreferring pronoun corefers to (i.e., its antecedent). Languages differ significantly in how they achieve coreference, and awareness of an- tecedents is important in choosing the cor- rect pronoun. Disregarding a pronoun?s an- tecedent in translation can lead to inappro- priate coreferring forms in the target text, seriously degrading a reader?s ability to un- derstand it. This work assesses the extent to which source-language annotation of coreferring pronouns can improve English?Czech Sta- tistical Machin...