A Semantics-based communication system for dysphasic subjects

Abstract

Dysphasic subjects do not have complete linguistic abilities and only produce a weakly structured, topicalized language. They are offered artificial symbolic languages to help them communicate in a way more adapted to their linguistic abilities. After a structural analysis of a corpus of utterances from children with cerebral palsy, we define a semantic lexicon for such a symbolic language. We use it as the basis of a semantic analysis process able to retrieve an interpretation of the utterances. This semantic analyser is currently used in an application designed to convert iconic languages into natural language; it might find other uses in the field of language rehabilitation.

Modelling Semantic Association and Conceptual Inheritance for Semantic Analysis

“…A primitive version of the semantic analysis algorithm has been implemented in 1996 for rehabilitation purposes, within a French electronics firm (Thomson-CSF), in the frame of a software communication tool for speech-impaired people [8]. The evaluation led to acceptable performance in analysis accuracy (80.5 % of the sequences correctly analyzed on a benchmark of 200 samples).…”

“…We have proposed an approach to tackle this limitation [8]: a method to interpret sequences of isolated concepts by modelling the use of "natural" semantic knowledge is implemented. This allows to build knowledge networks from icons as is usually done from text.…”

Access to lexical knowledge in modular interpersonal communication aids

“…The current implementation of the UVDMM Module was not meant to provide full message translation (i.e., to produce a syntactically correct translation output); rather, it was intended as a lexical translation "backbone." However, lexical translational equivalence constitutes a concrete step toward the provision of multilingual message translation in AAC because lexical information is expected to play a central role with respect to other types of information (e.g., morphologic and syntactic) in message translation (Vaillant, 1997). In fact, for some symbol systems whose morphologic and syntactic characteristics are much simpler than those of natural languages, lexical information may be the only type of information available for the translation process.…”

“…The formal description, processing, and translation of symbol systems (e.g., Blissymbolics) have also been investigated (Guenthner, Kruger-Thielmann, Pasero, & Sabatier, 1993;Vaillant, 1997). Although there are proposals in the literature concerning the exploitation of already existing large-scale lexical resources in AAC (Zickus, McCoy, Demasco, & Pennington, 1995), at the moment such resources are available only for natural languages, and mainly for English.…”

Using semantic authoring for Blissymbols communication boards

“…In the last decade, several systems that integrate NLG techniques for AAC systems have been developed ((McCoy, 1997), (Vaillant, 1997) for example). These systems share a common architecture: a telegraphic input sequence (words or symbols) is first parsed, and then a grammatical sentence that represents the message is generated.…”