Modelling a Parallel Corpus of French and French Belgian Sign Language

Modelling a Parallel Corpus of French and French Belgian Sign Language (LSFB) Laurence Meurant, Maxime Gobert, Anthony Cleve LSFB-Lab, PReCISE research center, PReCISE research center University of Namur - rue de Bruxelles, 61 - 5000 Namur - Belgium laurence.meurant@unamur.be, maxime.gobert@unamur.be, anthony.cleve@unamur.be Abstract The overarching objective underlying this research is to develop an online tool, based on a parallel corpus of French Belgian Sign Language (LSFB) and written Belgian French. This tool is aimed to assist various set of tasks related to the comparison of LSFB and French, to the benefit of general users as well as teachers in bilingual schools, translators and interpreters, as well as linguists. These tasks include (1) the comprehension of LSFB or French texts, (2) the production of LSFB or French texts, (3) the translation between LSFB and French in both directions and (4) the contrastive analysis of these languages. The first step of investigation aims at creating an unidirectional French-LSFB concordancer, able to align a one- or multiple-word expression from the French translated text with its corresponding expressions in the videotaped LSFB productions. We aim at testing the efficiency of this concordancer for the extraction of a dictionary of meanings in context. In this paper, we will present the modelling of the different data sources at our disposal and specifically the way they interact with one another. Keywords: Sign language, written language, parallel corpus 1. Linguistic Resources and Sign Languages Sign languages (SLs) are among the less-resourced lan- guages of the world, due to the combined impact of var- ious factors including their status as minority languages, the lack of written form of these visual-gestural languages, and their only recent official acceptance and recognition in the society. Research in SL linguistics is generally consid- ered to have begun with the works of Tervoort (1953) and Stokoe (1960). The foundation of the Sign Language Lin- guistics Society in 2004 symbolized that research on SLs had become a worldwide effort. The digital revolution has had an important impact on the knowledge of SLs since it opened, in the early 2000s only, the possibility to de- velop Corpus Linguistics on sign languages by collecting, archiving, annotating and documenting large scale video- taped data (Johnston, 2010). Nowadays, annotating SL data remains a manual and time- consuming task. The basic annotation task consists in iden- tifying in the signing flow each sign type, or lemma, and associating it to a written gloss (an ID-gloss) so that each lemma is labelled with the same and unique gloss through- out the data. This slow process is unavoidable at this stage because the amount of data needs to be enlarged in order to automate the process in a short future. We hypothesize that building our parallel corpus and its concordancer will contribute to this movement towards automated annotation. In 2015, the first online, large scale and searchable corpus of LSFB was published (Meurant, 2015)1. This resource is not only essential to the linguistic description of LSFB, but also a potential wealth of information …

Content truncated to 500 words