In this paper, we present results of a project that investigated
the application of lexicon
based text retrieval techniques to Alternative and Augmentative Communication
(AAC). As
a practical outcome of this research, a communication aid based on message
retrieval by key
words was designed, implemented and evaluated. The message retrieval module
in the system
uses a large semantic lexicon, derived from the WordNet database, for query
expansion. Trials
have been carried out with the device to evaluate whether the approach
is suitable for AAC,
and to determine the semantic relations that lead to efficient
message retrieval. The first part
of this paper describes the background of the project and highlights the
retrieval requirements
for a communication aid, which differ considerably from the requirements
in standard text
retrieval. We then present the overall design of the WordKeys communication
aid and describe
the tasks of its sub-modules. We summarise trials that have been carried
out to determine the
effect of semantic query expansion on the success of message retrieval.
Evaluation results show
that information about word frequency can solve problems that occurred
in the semantic
query expansion because of taxonomies that have too many intermediate steps
between
closely related words. Finally, a user evaluation with the improved system
showed that full
text retrieval is an effective approach to message access in a communication
aid.