Can I read W-RST: Towards a Weighted RST-style Discourse Framework on EtoBox?

W-RST: Towards a Weighted RST-style Discourse Framework by Huber, Patrick; Xiao, Wen; Carenini, Giuseppe is a scholarly article available to read on EtoBox.

What is W-RST: Towards a Weighted RST-style Discourse Framework about?

Aiming for a better integration of data-driven and linguistically-inspired approaches, we explore whether RST Nuclearity, assigning a binary assessment of importance between text segments, can be replaced by automatically generated, real-valued scores, in what we call a Weighted-RST framework. In particular, we find that weighted discourse trees from auxiliary tasks can benefit key NLP downstream applications, compared to nuclearity-centered approaches. We further show that real-valued importance distributions partially and interestingly align with the assessment and uncertainty of human annotators.

Author

Huber, Patrick; Xiao, Wen; Carenini, Giuseppe

Published

2021

Language

EN