Translation reranking using source phrase dependency features

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We describe a N-best reranking model based on features that combine source side dependency syntactical information and segmentation and alignment information. Specifically, we consider segmentation-aware ”phrase dependency” features.
Original languageEnglish
Title of host publicationProceedings of SSST-9, Ninth Workshop on Syntax, Semantics and Structure in Statistical Translation
PublisherAssociation for Computational Linguistics (ACL)
Pages57-60
Number of pages4
ISBN (Print)978-1-941643-41-9
Publication statusPublished - Jun 2015

Cite this