Machine interpretation

Abstract

This article,1discusses the problems of machine translation focusing on a special task, i.e. automatic dialogue interpreting. In the translation of spoken discourse, there is an increasing tendency to use pragmatic information which is commonly associated with speech or dialogue acts in order to handle the problems encountered in speech processing.After discussing some characteristics of spoken language as well as principal constraints operating on speech-to-speech translation, we will give a very brief overview of existing approaches, and then switch to the extended description of a sample solution within the VERBMOBIL-Project where transfer is assisted by a dialogue-act component. The last section describes how, with limited use of available information, transfer based on dialogue acts might result in new solutions for existing problems.

Is machine interpreting interpreting?

“…The fact that the founding editors of that new journal chose to include a paper on "machine interpretation" in the very first issue, alongside such topics as consecutive and simultaneous conference interpreting, remote interpreting, sign language interpreting and community interpreting, can be viewed as yet another effort at mapping the field of interpreting studies, which would thus include machine interpreting as a major area of research. The article by Jekat and Klein (1996), both affiliated with the computer science department of Hamburg University within the Verbmobil project, discusses "problems and some solutions" in machine interpreting with a focus on "dialogue acts", informed by speech act theory. It is followed in the second issue of Interpreting Vol.…”

“…This is also reflected in the present review of work on machine interpreting to date. Many of the relevant approaches and challenges in computational research and development are described in the comprehensive volume by Wahlster (2000a) on the Verbmobil project, including the basic structure of computer systems for speech-to-speech translation (see also Jekat 2015). That 'architecture' comprises three components or sequential stages: speech recognition (SR), interlingual transfer, and speech synthesis.…”