Distributed language modeling for N-best list re-ranking

Ying Zhang, Almut Silja Hildebrand, Stephan Vogel

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

34 Citations (Scopus)

Abstract

In this paper we describe a novel distributed language model for N-best list re-ranking. The model is based on the client/server paradigm where each server hosts a portion of the data and provides information to the client. This model allows for using an arbitrarily large corpus in a very efficient way. It also provides a natural platform for relevance weighting and selection. We applied this model on a 2.97 billion-word corpus and re-ranked the N-best list from Hiero, a state-of-theart phrase-based system. Using BLEU as a metric, the re-ranked translation achieves a relative improvement of 4.8%, significantly better than the model-best translation.

Original languageEnglish
Title of host publicationCOLING/ACL 2006 - EMNLP 2006
Subtitle of host publication2006 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages216-223
Number of pages8
ISBN (Print)1932432736, 9781932432732
DOIs
Publication statusPublished - 1 Jan 2006
Event11th Conference on Empirical Methods in Natural Language Proceessing, EMNLP 2006, Held in Conjunction with COLING/ACL 2006 - Sydney, NSW, Australia
Duration: 22 Jul 200623 Jul 2006

Publication series

NameCOLING/ACL 2006 - EMNLP 2006: 2006 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference

Other

Other11th Conference on Empirical Methods in Natural Language Proceessing, EMNLP 2006, Held in Conjunction with COLING/ACL 2006
CountryAustralia
CitySydney, NSW
Period22/7/0623/7/06

    Fingerprint

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Information Systems

Cite this

Zhang, Y., Hildebrand, A. S., & Vogel, S. (2006). Distributed language modeling for N-best list re-ranking. In COLING/ACL 2006 - EMNLP 2006: 2006 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference (pp. 216-223). (COLING/ACL 2006 - EMNLP 2006: 2006 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference). Association for Computational Linguistics (ACL). https://doi.org/10.3115/1610075.1610108