Content

Hide video with translation into sign language
Switch to fixed-width version
Česká verze této stránky English

Paper details

A Methodology for Automatic Sign Language Dictionary Creation


Ing. Jakub Kanis Ph.D.
University of West Bohemia, Plzeň


PhDr. Petr Peňáz
Teiresias Centre, Masaryk University


Ing. Pavel Campr
University of West Bohemia, Plzeň


Ing. Marek Hrúz
University of West Bohemia, Plzeň



Abstract

In this article we present the the sign language dictionary being developed by a research team of University of West Bohemia, Masaryk University and Palacký University. The aim is to create both an explanatory and a translation dictionary with respect to the linguistic needs. The dictionary is designed as an on-line application with access for all registered users who compose a hierarchical structure to ensure a lexicographic consistency of the dictionary content. The basic structure of the dictionary is proposed to meet linguistic criteria of both spoken and sign languages. We use written text to represent spoken languages and several representations are supported for sign languages: videos, images, HamNoSys, SignWriting and an interactive 3D avatar. To decrease the time required for data collection and publishing in the dictionary we use computer vision methods. We detect the boundaries of the dictionary entry. If the entry is a single sign we analyze the manual component of the performed sign for automatic categorization. The content is being created by linguists using both new and already existing data. Later on the dictionary will be opened to the users with possibility to add, modify and comment data. We expect that this possibility of on-line elicitation will increase the number of informants, cover more regions, and make the elicitation cheaper and the evaluation easier.

For the full paper and presentation material as well as the record of the presentation please sign in.

top