Does referent predictability affect the choice of referential form? A computational approach using masked coreference resolution
Laura Aina, Xixian Liao, Gemma Boleda, Matthijs Westera

TL;DR
This paper investigates how the predictability of a referent influences the choice of referring expression form, using a novel masked coreference resolution model to estimate referent predictability and analyze its effect on mention form.
Contribution
It introduces a new masked coreference resolution approach to better estimate referent predictability and demonstrates its impact on the choice of referential form.
Findings
Higher predictability correlates with less informative, shorter referring expressions.
The model achieves standard coreference resolution performance while improving predictability estimates.
Predictability influences both the morphosyntactic type and length of referring expressions.
Abstract
It is often posited that more predictable parts of a speaker's meaning tend to be made less explicit, for instance using shorter, less informative words. Studying these dynamics in the domain of referring expressions has proven difficult, with existing studies, both psycholinguistic and corpus-based, providing contradictory results. We test the hypothesis that speakers produce less informative referring expressions (e.g., pronouns vs. full noun phrases) when the context is more informative about the referent, using novel computational estimates of referent predictability. We obtain these estimates training an existing coreference resolution system for English on a new task, masked coreference resolution, giving us a probability distribution over referents that is conditioned on the context but not the referring expression. The resulting system retains standard coreference resolution…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Natural Language Processing Techniques · Speech and dialogue systems
MethodsTest
