What makes an entity salient in discourse?
This addresses the problem of understanding entity salience in discourse for linguists and NLP researchers, but it is incremental as it builds on prior approaches without a major breakthrough.
The paper investigates how linguistic cues signal entity salience in discourse, using a graded measure based on summary-worthiness across 24 English genres, and finds that salience involves multiple factors across all linguistic levels with no single generalization.
Entities in discourse vary broadly in salience: main participants, objects and locations are noticeable and memorable, while tangential ones are less important and quickly forgotten, raising questions about how humans signal and infer relative salience. Using a graded operationalization of salience based on summary-worthiness in multiple summaries of a discourse, this paper explores data from 24 spoken and written genres of English to extract a multifactorial complex of overt and implicit linguistic cues, such as recurring subjecthood or definiteness, discourse relations and hierarchy across utterances, as well as pragmatic functional inferences based on genre and communicative intent. Tackling the question 'how is the degree of salience expressed for each and every entity mentioned?' our results show that while previous approaches to salience all correlate with our salience scores to some extent, no single generalization is without exceptions, and the phenomenon cuts across all levels of linguistic representation.