Slicing your SL data into Basic Discourse Units (BDUs). Adapting the BDU model (syntax + prosody) to Signed Discourse
Temas
Detalles
This paper aims to propose a model for the segmentation of signed discourse by adapting the Basic Discourse Units (BDU) Model. This model was conceived for spoken data and allows the segmentation of both monologues and dialogues. It consists of three steps: delimiting syntactic units on the basis of the Dependency Grammar (DG), delimiting prosodic units on the basis of a set of acoustic cues, and finding the convergence point between syntactic and prosodic units in order to establish BDUs. A corpus containing data from French Belgian Sign Language (LSFB) will be firstly segmented according to the principles of the DG. After establishing a set of visual cues equivalent to the acoustic ones, a prosodic segmentation will be carried out independently. Finally, the convergence points between syntactic and prosodic units will give rise to BDUs. The ultimate goal of adapting the BDU Model to the signed modality is not only to allow the study of the position of discourse markers (DMs) as in the original model, but also to give an answer to a controversial issue in SL research such as the segmentation of SL corpus data, for which a satisfactory solution has not been found so far.
En Proceedings of the LREC2016 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining (pp. 81–88).