Hostname: page-component-76fb5796d-9pm4c Total loading time: 0 Render date: 2024-04-26T04:47:25.032Z Has data issue: false hasContentIssue false

The rôle of natural language processing in alternative and augmentative communication

Published online by Cambridge University Press:  01 March 1998

ALAN NEWELL
Affiliation:
Applied Computing, University of Dundee, Dundee, Scotland; e-mail: afn@mic.dundee.ac.uk
STEFAN LANGER
Affiliation:
CIS, University of Munich, München, Germany; e-mail: stef@cis.uni-muenchen.de
MARIANNE HICKEY
Affiliation:
Applied Computing, University of Dundee, Dundee, Scotland; e-mail: mhickey@mic.dundee.ac.uk

Abstract

Alternative and Augmentative Communication (AAC) for people with speech and language disorders is an interesting and challenging application field for research in Natural Language Processing. Further advances in the development of AAC systems require robust language processing techniques and versatile linguistic knowledge bases. Also NLP research can benefit from studying the techniques used in this field and from the user-centred methodologies used to develop and evaluate AAC systems. Until recently, however, apart from some exceptions, there was little scientific exchange between the two research areas. This paper aims to make a contribution to closing this gap. We will argue that current interest in language use, which can be shown by the large amount of research on comprehensive dictionaries and on corpora processing, makes the results of NLP research more relevant to AAC. We will also show that the increasing interest of AAC researchers in NLP is having positive results. To situate research on communication aids, the first half of this paper gives an overview of the AAC research field. The second half is dedicated to an overview of research prototype systems and commercially available communication aids that specifically involve more advanced language processing techniques.

Type
Research Article
Copyright
1998 Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)