Research Area - Sign Language Technologies

Sign Language Technologies


In contrast to oral language, sign languages (SLs) are linguistic systems that are heavily based on iconicity to convey meaning. Within such a system, the sentence is uttered in three-dimensional space, where syntactic-semantic relations are expressed via a morpho-syntactic structuring, which is organised differently from orally articulated means. In this respect, any SL is an autonomous system, which does not exhibit direct shared properties and characteristics with orally articulated languages in the same geographical location, although some elements of language interference are to be found in the data of (mostly) young informants. Thus, a sign language is a visual-monitory natural language, which is organised into a rule-governed system that uses symbols to represent concepts and realized through positioning in three-dimensional space around a signer.

The key technologies currently under development in the domain of sign language research are related to robust recognition and generation of sign language and heavily depend upon sign language linguistic research and the related language technologies. At the same time, the state-of-the-art in sign language linguistics research is corpus-based, where the important characteristics of sign languages which make them an ideal study in multimodal communication are directly related to the three-dimensional nature of sign languages.

Accomplishments so far:


  • Methodology for large scale SL lexicon development
  • Methodology for terminology development in Greek Sign Language (GSL)

  • Methodology for Deaf user interfaces

  • Basic lexicon resources for GSL

  • Terminology resources in GSL

  • Core GSL grammar

  • Phonologically annotated lexical resources

  • An annotated corpus for GSL

  • A machine translation prototype for the language pair written Greek-GSL

  • A series of SL products and technologies (NOEMA, GSL children’s dictionary, DIOLKOS, I learn the signs, Finger Keyboard etc.)

Current R&D focus:

  • resources collection and annotation, with the goal to support development of lexicons, grammar models and educational software
  • machine translation, synthesis and recognition of sign language
  • linguistic analysis of GSL in view of a complete grammar description and grammar model to support sign recognition and sign synthesis
  • large-scale dynamic SL synthesis with improved avatar performance