DeepAI AI Chat
Log In Sign Up

W-RST: Towards a Weighted RST-style Discourse Framework

06/04/2021
by   Patrick Huber, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

11/13/2018

Domain Agnostic Real-Valued Specificity Prediction

Sentence specificity quantifies the level of detail in a sentence, chara...
06/04/2019

Evaluating Discourse in Structured Text Representations

Discourse structure is integral to understanding a text and is helpful i...
09/02/2018

Modeling Topical Coherence in Discourse without Supervision

Coherence of text is an important attribute to be measured for both manu...
08/06/2020

Foundations of Reasoning with Uncertainty via Real-valued Logics

Real-valued logics underlie an increasing number of neuro-symbolic appro...
04/08/2023

Importance Sampling BRDF Derivatives

We propose a set of techniques to efficiently importance sample the deri...
03/27/2013

Knowledge and Uncertainty

One purpose -- quite a few thinkers would say the main purpose -- of see...
03/14/2018

SUSTain: Scalable Unsupervised Scoring for Tensors and its Application to Phenotyping

This paper presents a new method, which we call SUSTain, that extends re...