Using hybrid methods and resources in semantic-based transfer
Bianka Buschbeck-Wolf, Michael Dorna · Amsterdam studies in the theory and history of linguistic science. Series 4, Current issues in linguistic theory · 2000
This paper presents ongoing work on the development of the semantic transfer component of the multi-lingual speech-to-speech MT system Verbmobil. It focuses on the use of symbolic and statistical methods for the acquisition of semantic transfer rules, the disambiguation of translational ambiguities and the selection of appropriate rule candidates at runtime. 1 Introduction In this paper we describe how a combination of different methods and resources is used for the development of the transfer component of Verbmobil (Dorna & Emele 96b). Verbmobil (Wahlster 93) is a multi-lingual speech-to-speech MT system that is applied to the task of translating spoken language in the domain of appointment scheduling and travel planning. Currently, the system includes modules for German, English and Japanese. Over the last decades, neither pure stochastic approaches to machine translation (MT), such as the statistical approach (Brown et al. 90) or example-based MT (Sato & Nagao 90; Sumita et al. ...