Date of Original Version

7-2012

Type

Conference Proceeding

Journal Title

Proceedings of the Named Entity Workshop (NEWS)

First Page

66

Last Page

70

Rights Management

Copyright 2012 ACL

Abstract or Description

We consider the task of generating transliterated word forms. To allow for a wide range of interacting features, we use a conditional random field (CRF) sequence labeling model. We then present two innovations: a training objective that optimizes toward any of a set of possible correct labels (since more than one transliteration is often possible for a particular input), and a k-best reranking stage to incorporate nonlocal features. This paper presents results on the Arabic-English transliteration task of the NEWS 2012 workshop.

Share

COinS
 

Published In

Proceedings of the Named Entity Workshop (NEWS), 66-70.