What makes an entity salient in discourse?

TL;DR

This study investigates how various linguistic and structural features influence entity salience at the discourse level across different genres, revealing complex interactions and the importance of discourse structure and semantics.

Contribution

It extends utterance-level prominence predictors to discourse-level salience, analyzing their interaction with entity features across diverse genres.

Findings

Utterance-level predictors correlate with discourse salience.

Discourse structure and semantics are more robust predictors than morphosyntactic features.

Genre and communicative intent significantly modulate salience factors.

Abstract

Entities in discourse vary in salience: main participants, objects and locations stay prominent, while others are quickly forgotten, raising questions about how humans signal and infer discourse-level salience. Using a graded operationalization of discourse-level salience based on summary-worthiness in multiple summaries, this paper investigates whether predictors of utterance-level prominence extend to the discourse level, and how they interact across 24 spoken and written genres of English. We examine features including grammatical function, definiteness, entity type, linear order, discourse relations and hierarchy, and referential structure, as well as the impact of genre. Our results show that utterance-level predictors significantly correlate with discourse-level salience, but interact with and are modulated by entity-level factors such as frequency and dispersion across the document. Multifactorial models reveal that no single factor determines salience; rather, discourse-structural and semantic features prove more robust than morphosyntactic ones, with substantial variation by genre and communicative intent.