Transliteration by sequence labeling with lattice encodings and reranking

Authors:
Waleed Ammar;Chris Dyer;Noah A. Smith
Affiliations:
Mellon University Pittsburgh, PA;Mellon University Pittsburgh, PA;Mellon University Pittsburgh, PA
Venue:
NEWS '12 Proceedings of the 4th Named Entity Workshop
Year:
2012

Citing 7
Cited 1

Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Discriminative Reranking for Natural Language Parsing

ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Shallow parsing with conditional random fields

NAACL '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1
Using a maximum entropy model to build segmentation lattices for MT

NAACL '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Better k-best parsing

Parsing '05 Proceedings of the Ninth International Workshop on Parsing Technology
Substring-based transliteration with conditional random fields

NEWS '09 Proceedings of the 2009 Named Entities Workshop: Shared Task on Transliteration
cdec: a decoder, alignment, and learning framework for finite-state and context-free translation models

ACLDemos '10 Proceedings of the ACL 2010 System Demonstrations

Report of NEWS 2012 machine transliteration shared task

NEWS '12 Proceedings of the 4th Named Entity Workshop

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.