Overlapping phrase-level translation rules in an SMT engine

Alicia Tribble, Stephan Vogel, Alex Waibel

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

1 Citation (Scopus)

Abstract

In this paper we explore a technique for adding longer phrase translation pairs to a Statistical Machine Translation (SMT) system. New phrases are generated by merging existing phrase-level alignments that have overlapping words on both the source and target sides. The effect on translation qualify is reported for an Arabic-English system in die news domain.

Original languageEnglish
Title of host publicationNLP-KE 2003 - 2003 International Conference on Natural Language Processing and Knowledge Engineering, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages574-579
Number of pages6
ISBN (Print)0780379020, 9780780379022
DOIs
Publication statusPublished - 2003
Externally publishedYes
EventInternational Conference on Natural Language Processing and Knowledge Engineering, NLP-KE 2003 - Beijing, China
Duration: 26 Oct 200329 Oct 2003

Other

OtherInternational Conference on Natural Language Processing and Knowledge Engineering, NLP-KE 2003
CountryChina
CityBeijing
Period26/10/0329/10/03

    Fingerprint

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Software

Cite this

Tribble, A., Vogel, S., & Waibel, A. (2003). Overlapping phrase-level translation rules in an SMT engine. In NLP-KE 2003 - 2003 International Conference on Natural Language Processing and Knowledge Engineering, Proceedings (pp. 574-579). [1275971] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/NLPKE.2003.1275971