Towards Unification of Discourse Annotation Frameworks
This addresses a long-standing issue in natural language processing for researchers and practitioners by potentially improving discourse analysis, but it is incremental as it builds on existing frameworks without introducing a new paradigm.
The paper tackles the problem of unifying different discourse annotation frameworks (RST, PDTB, SDRT) to leverage existing corpora and achieve synergy, proposing to use automatic methods for unification and evaluate it with structural complexity and downstream tasks.
Discourse information is difficult to represent and annotate. Among the major frameworks for annotating discourse information, RST, PDTB and SDRT are widely discussed and used, each having its own theoretical foundation and focus. Corpora annotated under different frameworks vary considerably. To make better use of the existing discourse corpora and achieve the possible synergy of different frameworks, it is worthwhile to investigate the systematic relations between different frameworks and devise methods of unifying the frameworks. Although the issue of framework unification has been a topic of discussion for a long time, there is currently no comprehensive approach which considers unifying both discourse structure and discourse relations and evaluates the unified framework intrinsically and extrinsically. We plan to use automatic means for the unification task and evaluate the result with structural complexity and downstream tasks. We will also explore the application of the unified framework in multi-task learning and graphical models.