Sign Language (SL) corpora can be made in vivo (in natural conditions, with or without guidelines) or in vitro (in a laboratory, with guidelines), like speech corpora. While some effort has been made to standardise on corpus metadata with the IMDI project, there is not such norm for SL corpus elaboration: the methodology depends on the research goal. Our aim is to create a 3D French SL (LSF) corpus to be used in different types of software, thus the signs must be considered without context. To fit our specific goals, we have decided on the following methodology: First of all we look for a referent gestuel: a deaf person, whose first language is LSF and whose signing corresponds to what is needed for the infographic part of the process (see step five). The referent gestuel has been chosen by the team's infographist. It is important to keep the same referent gestuel for all the lexicon, in order to keep a consistency in the 3D corpus. Then, for each scientific topic we consider, we look for an expert: a deaf person, whose first language is FSL and who is aware of the terminology used in the field. Because we want many topics corpus, we work with different experts. Thirdly we organise a meeting with the referent gestuel, the expert and, if necessary, other specialists of the topic we are working on, so they can discuss each meaning of each concept and sign it the as accurately as possible. The next step is to film the referent gestuel two views of the referent gestuel (frontal view and side view). Lastly we animate the 3D avatar by copying each frame of the video, using 3DSMax software. This 3D corpus will be used in at least three different informational pieces of software. One that can be used in railway stations to inform deaf users in LSF about the delay of a train or any other problem. Another application will be a dictionary: We are developing a LSF-French dictionary where signs would be given in a the form of a 3D avatar. A third example is to display an Embodied Conversational Agent (ECA) on our laboratory website so that our research topics can be explained in LSF if wanted. References Michael Filhol, Annelies Braffort et Laurence Bolot (to appear), Signing Avatar: Say hello to Elsi! In: Gesture in Human- Computer Interaction and Simulation, selected revised papers of the 7th International Gesture Workshop (GW’07), LNCS LNAI, Springer. Onno Crasborn & Thomas Hanke (2003), Metadata for sign language corpora. Background document for an ECHO workshop, 8 + 9 May 2003, Nijmegen University.
@inproceedings{segouat:08010:sign-lang:lrec,
author = {Segouat, J{\'e}r{\'e}mie and Braffort, Annelies and Bolot, Laurence and Choisier, Annick and Filhol, Michael and Verrecchia, Cyril},
title = {Building {3D} {French} {Sign} {Language} lexicon},
pages = {174--177},
editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge},
booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora},
maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)},
publisher = {{European Language Resources Association (ELRA)}},
address = {Marrakech, Morocco},
day = {1},
month = jun,
year = {2008},
language = {english},
url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08010.pdf}
}
| Verrecchia, Cyril