An empirical study of the impact of idioms on phrase based statistical machine translation of english to Brazilian-Portuguese

Giancarlo D. Salton, Robert J. Ross, John D. Kelleher

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper describes an experiment to evaluate the impact of idioms on Statistical Machine Translation (SMT) process using the language pair English/Brazilian-Portuguese. Our results show that on sentences containing idioms a standard SMT system achieves about half the BLEU score of the same system when applied to sentences that do not contain idioms. We also provide a short error analysis and outline our planned work to overcome this limitation.

Original languageEnglish
Title of host publicationProceedings of the 3rd Workshop on Hybrid Approaches to Translation, HyTra 2014 at the 14th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2014
EditorsRafael E. Banchs, Marta R. Costa-Jussa, Reinhard Rapp, Patrik Lambert, Kurt Eberle, Bogdan Babych
PublisherAssociation for Computational Linguistics (ACL)
Pages36-41
Number of pages6
ISBN (Electronic)9781937284893
DOIs
Publication statusPublished - 2014
Event3rd Workshop on Hybrid Approaches to Translation, HyTra 2014 at the 14th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2014 - Gothenburg, Sweden
Duration: 27 Apr 2014 → …

Publication series

NameProceedings of the 3rd Workshop on Hybrid Approaches to Translation, HyTra 2014 at the 14th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2014

Conference

Conference3rd Workshop on Hybrid Approaches to Translation, HyTra 2014 at the 14th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2014
Country/TerritorySweden
CityGothenburg
Period27/04/14 → …

Keywords

  • idioms
  • Statistical Machine Translation
  • English
  • Brazilian-Portuguese
  • BLEU score
  • error analysis

Fingerprint

Dive into the research topics of 'An empirical study of the impact of idioms on phrase based statistical machine translation of english to Brazilian-Portuguese'. Together they form a unique fingerprint.

Cite this