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

performance
Speech-to-speech Translation
Statistical Machine Translation
evaluation
knowledge
Translation System
Machine Translation System
Evaluation
Interlingua

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.

Improving statistical machine translation for a speech-to-speech translation task. / Vogel, Stephan; Tribble, Alicia.

7th International Conference on Spoken Language Processing, ICSLP 2002. International Speech Communication Association, 2002. p. 1901-1904.

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

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. International Speech Communication Association, pp. 1901-1904, 7th International Conference on Spoken Language Processing, ICSLP 2002, Denver, United States, 16/9/02.
Vogel S, Tribble A. Improving statistical machine translation for a speech-to-speech translation task. In 7th International Conference on Spoken Language Processing, ICSLP 2002. International Speech Communication Association. 2002. p. 1901-1904
Vogel, Stephan ; Tribble, Alicia. / Improving statistical machine translation for a speech-to-speech translation task. 7th International Conference on Spoken Language Processing, ICSLP 2002. International Speech Communication Association, 2002. pp. 1901-1904
@inproceedings{c07ab77e4a784c40a17c918ce49ff788,
title = "Improving statistical machine translation for a speech-to-speech translation task",
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.",
author = "Stephan Vogel and Alicia Tribble",
year = "2002",
language = "English",
pages = "1901--1904",
booktitle = "7th International Conference on Spoken Language Processing, ICSLP 2002",
publisher = "International Speech Communication Association",

}

TY - GEN

T1 - Improving statistical machine translation for a speech-to-speech translation task

AU - Vogel, Stephan

AU - Tribble, Alicia

PY - 2002

Y1 - 2002

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85009260461&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85009260461&partnerID=8YFLogxK

M3 - Conference contribution

SP - 1901

EP - 1904

BT - 7th International Conference on Spoken Language Processing, ICSLP 2002

PB - International Speech Communication Association

ER -