Multi-lingual translation of spontaneously spoken language in a limited domain

Authors:
Alon Lavie;Donna Gates;Marsal Gavaldà;Laura Mayfield;Alex Waibel;Lori Levin
Affiliations:
Carnegie Mellon University, Pittsburgh, PA;Carnegie Mellon University, Pittsburgh, PA;Carnegie Mellon University, Pittsburgh, PA;Carnegie Mellon University, Pittsburgh, PA;Carnegie Mellon University, Pittsburgh, PA;Carnegie Mellon University, Pittsburgh, PA
Venue:
COLING '96 Proceedings of the 16th conference on Computational linguistics - Volume 1
Year:
1996

Citing 5
Cited 6

An efficient augmented-context-free parsing algorithm

Computational Linguistics
End-to-End Evaluation in JANUS: A Speech-to-speech Translation System

ECAI '96 Workshop on Dialogue Processing in Spoken Language Systems
Discourse processing of dialogues with multiple threads

ACL '95 Proceedings of the 33rd annual meeting on Association for Computational Linguistics
An integrated heuristic scheme for partial parse evaluation

ACL '94 Proceedings of the 32nd annual meeting on Association for Computational Linguistics
The generalized LR parser/compiler V8-4: a software package for practical NL projects

COLING '90 Proceedings of the 13th conference on Computational linguistics - Volume 1

A Controlled Skip Parser

Machine Translation
Statistical Translation of Text and Speech: First Results with the RWTH System

Machine Translation
Improving translation through contextual information

ACL '98 Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and Eighth Conference of the European Chapter of the Association for Computational Linguistics
An interactive domain independent approach to robust dialogue interpretation

COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 2
Optimal ambiguity packing in context-free parsers with interleaved unification

New developments in parsing technology
Improving performance of transfer-driven machine translation with extra-linguistic information from context, situation and environment

IJCAI'97 Proceedings of the Fifteenth international joint conference on Artifical intelligence - Volume 2

Quantified Score

Hi-index	0.00

Visualization

Abstract

JANUS is a multi-lingual speech-to-speech translation system designed to facilitate communication between two parties engaged in a spontaneous conversation in a limited domain. In an attempt to achieve both robustness and translation accuracy we use two different translation components: the GLR module, designed to be more accurate, and the Phoenix module, designed to be more robust. We analyze the strengths and weaknesses of each of the approaches and describe our work on combining them. Another recent focus has been on developing a detailed end-to-end evaluation procedure to measure the performance and effectiveness of the system. We present our most recent Spanish-to-English performance evaluation results.