Meltem Kelepir

Building machine-readable knowledge representations for Turkish sign language generation

This article proposes a representation scheme for depicting the Turkish Sign Language (TID) electronically for use in an automated machine translation system whose basic aim is to translate the Turkish primary school educational materials to TID. The main contribution of the article is the introduction of a machine-readable knowledge representation for TID for the first time in the literature. Like many resource-poor languages, TID lacks electronic language resources usable in computerized systems. The utilization of the proposed scheme for resource creation is also provided in this article by two means: an interactive online dictionary platform for TID and an ELAN add-on for corpus creation.

SignGram Blueprint : A Guide to Sign Language Grammar Writing

Current grammatical knowledge about particular sign languages is fragmentary and of varying reliability, and it appears scattered in scientific publications where the description is often intertwined with the analysis. In general, comprehensive grammars are a rarity. The SignGram Blueprint is an innovative tool for the grammar writer: a full-fledged guide to describing all components of the grammars of sign languages in a thorough and systematic way, and with the highest scientific standards. The work builds on the existing knowledge in Descriptive Linguistics, but also on the insights from Theoretical Linguistics. It consists of two main parts running in parallel: the Checklist with all the grammatical features and phenomena the grammar writer can address, and the accompanying Manual with the relevant background information (definitions, methodological caveats, representative examples, tests, pointers to elicitation materials and bibliographical references). The areas covered are Phonology, Morphology, Lexicon, Syntax and Meaning. The Manual is endowed with hyperlinks that connect information across the work and with a pop-up glossary. The SignGram Blueprint will be a landmark for the description of sign language grammars in terms of quality and quantity.