Processing linguistic data for GSL structure representation

The here presented work reports on incorporation of a core grammar of Greek Sign Language (GSL) into a Greek to GSL conversion tool. The output of conversion feeds a signing avatar, enabling dynamic sign synthesis. Efficient conversion is of significant importance in order to support access to e-content by the Greek deaf community, given that the conversion tool may well be integrated into various applications, which require linguistic knowledge. The converter is built upon standard principles of Machine Translation (MT) and matches Greek parsed input to equivalent GSL output. The transfer module makes use of NLP techniques to enrich linear sign concatenation with GSL-specific complex features uttered both manually and non-manually. GSL features are either checked against properties coded in a lexicon DB for base signs or they are generated by grammar rules. The GSL computational grammar is based on natural data analysis in order to capture the generative characteristics of the language. The conversion grammar of the transfer module, however, makes use of a number of heuristic solutions. This is implicated by the type of input for conversion, which derives from a statistical shallow parser, so that various semantic features have to be retrieved by mere grouping of lemmata. However, this type of input is directly connected with the requirement for fast processing of vast amounts of linguistic information.