A special issue of the leading Anglo/French journal Traitement Automatique des Langues has just been published, co-edited by Prof. Donia Scott (OU Computing), and including a paper reporting an experiment from Clara Mancini’s doctoral thesis “Cinematic Hypertext”.
The special issue editorial surveys the convergence of discourse and NLP for document-processing:
This introduction tracks the evolution of the definition and role of discourse issues in NLP from the knowledge-intensive “discourse understanding” methods of the 80’s to the recent concern with “accessing contents” in vast document bases via data-intensive methods. As text/discourse linguistics moves toward corpus approaches, also in connection with the development of large text bases and of computational instruments, we explore potential new forms of convergence.
Clara’s paper, co-authored with Donia and myself is entitled: “Visualising discourse coherence in non-linear documents”:
To produce coherent linear documents, natural language generation systems have traditionally exploited the structuring role of textual discourse markers such as relational and referential phrases. These coherence markers of the traditional notion of text, however, do not work in non-linear documents: a new set of graphical devices is needed together with formation rules to govern their usage, supported by sound theoretical frameworks. If in linear documents graphical devices such as layout and formatting complement textual devices in the expression of discourse coherence, in non-linear documents they play a more important role. In this paper, we present our theoretical and empirical work in progress, which explores new possibilities for expressing coherence in the generation of hypertext documents.
TAL Special Issue: Discours et document : traitements automatiques
Visualising discourse coherence in non-linear documents