A Survey of QUD Models for Discourse Processing

TL;DR

This survey reviews various Question Under Discussion (QUD) models in discourse processing, highlighting their applications to written texts and exploring their connections with other discourse frameworks like RST, PDTB, and SDRT.

Contribution

It provides a comprehensive summary of existing QUD models, compares their relationships with mainstream discourse frameworks, and suggests directions for future research.

Findings

QUD models are increasingly used in discourse analysis.

Connections between QUD and frameworks like RST, PDTB, SDRT are explored.

The survey identifies open questions for further study.

Abstract

Question Under Discussion (QUD), which is originally a linguistic analytic framework, gains increasing attention in the community of natural language processing over the years. Various models have been proposed for implementing QUD for discourse processing. This survey summarizes these models, with a focus on application to written texts, and examines studies that explore the relationship between QUD and mainstream discourse frameworks, including RST, PDTB and SDRT. Some questions that may require further study are suggested.