Improving statistical machine translation for a speech-to-speech translation task

Stephan Vogel, Alicia Tribble

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

7 Citations (Scopus)

Abstract

In this paper we investigate if statistical machine translation (SMT) is possible when only a small bilingual corpus is available for training the system. Using additional knowledge sources which are not domain-specific improves the performance of the system considerably. We present results on a speech translation task for German to English. Automatic and human evaluation are used to compare the performance of the SMT system to an interlingua-based translation system.

Original languageEnglish
Title of host publication7th International Conference on Spoken Language Processing, ICSLP 2002
PublisherInternational Speech Communication Association
Pages1901-1904
Number of pages4
Publication statusPublished - 2002
Externally publishedYes
Event7th International Conference on Spoken Language Processing, ICSLP 2002 - Denver, United States
Duration: 16 Sep 200220 Sep 2002

Other

Other7th International Conference on Spoken Language Processing, ICSLP 2002
CountryUnited States
CityDenver
Period16/9/0220/9/02

    Fingerprint

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Cite this

Vogel, S., & Tribble, A. (2002). Improving statistical machine translation for a speech-to-speech translation task. In 7th International Conference on Spoken Language Processing, ICSLP 2002 (pp. 1901-1904). International Speech Communication Association.