The Janus-III Translation System: Speech-to-Speech Translation in Multiple Domains

  • Authors:
  • Lori Levin;Alon Lavie;Monika Woszczyna;Donna Gates;Marsal Gavaldá;Detlef Koll;Alex Waibel

  • Affiliations:
  • Language Technologies Institute, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA 15213-3891, USA;Language Technologies Institute, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA 15213-3891, USA;Language Technologies Institute, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA 15213-3891, USA;Language Technologies Institute, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA 15213-3891, USA;Language Technologies Institute, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA 15213-3891, USA;Language Technologies Institute, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA 15213-3891, USA;Language Technologies Institute, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA 15213-3891, USA

  • Venue:
  • Machine Translation
  • Year:
  • 2000

Quantified Score

Hi-index 0.00

Visualization

Abstract

The Janus-III system translates spoken languages in limiteddomains. The current research focus is on expanding beyond tasksinvolving a single limited semantic domain to significantly broaderand richer domains. To achieve this goal, The MT components of oursystem have been engineered to build and manipulate multi-domain parselattices that are based on modular grammars for multiple semanticdomains. This approach yields solutions to several problems includingmulti-domain disambiguation, segmentation of spoken utterances intosentence units, modularity of system design, and re-use of earliersystems with incompatible output.