Speech translation performance of statistical dependency transduction and semantic similarity transduction

Authors:
Hiyan Alshawi;Shona Douglas
Affiliations:
AT&T Labs - Research, Florham Park, NJ;AT&T Labs - Research, Florham Park, NJ
Venue:
S2S '02 Proceedings of the ACL-02 workshop on Speech-to-speech translation: algorithms and systems - Volume 7
Year:
2002

Citing 8
Cited 0

Identifying word correspondence in parallel texts

HLT '91 Proceedings of the workshop on Speech and Natural Language
How may I help you?

Speech Communication - Special issue on interactive voice technology for telecommunication applications (IVITA '96)
The String-to-String Correction Problem

Journal of the ACM (JACM)
An efficient context-free parsing algorithm

Communications of the ACM
Head-Transducer Models for Speech Translation and TheirAutomatic Acquisition from Bilingual Data

Machine Translation
Learning dependency translation models as collections of finite-state head transducers

Computational Linguistics - Special issue on finite-state methods in NLP
The mathematics of statistical machine translation: parameter estimation

Computational Linguistics - Special issue on using large corpora: II
Distributional clustering of English words

ACL '93 Proceedings of the 31st annual meeting on Association for Computational Linguistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we compare the performance of two methods for speech translation. One is a statistical dependency transduction model using head transducers, the other a case-based transduction model involving a lexical similarity measure. Examples of translated utterance transcriptions are used in training both models, though the case-based model also uses semantic labels classifying the source utterances. The main conclusion is that while the two methods provide similar translation accuracy under the experimental conditions and accuracy metric used, the statistical dependency transduction method is significantly faster at computing translations.