Chinese generation in a spoken dialogue translation system

  • Authors:
  • Hua Wu;Taiyi Huang;Chengqing Zong;Bo Xu

  • Affiliations:
  • Chinese Academy of Sciences, Beijing, China;Chinese Academy of Sciences, Beijing, China;Chinese Academy of Sciences, Beijing, China;Chinese Academy of Sciences, Beijing, China

  • Venue:
  • COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 2
  • Year:
  • 2000

Quantified Score

Hi-index 0.00

Visualization

Abstract

A Chinese generation module in a speech to speech dialogue translation system is presented here. The input of the generation module is the underspecified semantic representation. Its design is strongly influenced by the underspecification of the inputs and the necessity of real-time and robust processing. We design an efficient generation system comprising a task-oriented microplanner and a general surface realization module for Chinese. The microplanner performs the lexical and syntactic choice and makes inferences from the input and domain knowledge. The output of the microplanner is fully instantiated. This enables the surface realizer to traverse the input in a top-down, depth-first fashion, which in turn speeds the whole generation procedure. The surface realizer also combines the template method and deep generation technology in the same formalism. Preliminary results are also presented in this paper.