William Berkeley Sheffield — accepted AI-conference papers

2025

Is It JUST Semantics? A Case Study of Discourse Particle Understanding in LLMs

William Berkeley Sheffield, Kanishka Misra, Valentina Pyatkin, Ashwini Deo, Kyle Mahowald, Junyi Jessy Li

ACL 2025finding

Discourse particles are crucial elements that subtly shape the meaning of text. These words, often polyfunctional, give rise to nuanced and often quite disparate semantic/discourse effects,as exemplified by the diverse uses of the particle *just* (e.g., exclusive, temporal, emphatic). This work inve…

Cited by 0 Source ↗PDF ↗Scholar ↗

2023

Elaborative Simplification as Implicit Questions Under Discussion

Yating Wu, William Berkeley Sheffield, Kyle Mahowald, Junyi Jessy Li

EMNLP 2023long main

Automated text simplification, a technique useful for making text more accessible to people such as children and emergent bilinguals, is often thought of as a monolingual translation task from complex sentences to simplified sentences using encoder-decoder models. This view fails to account for elab…

Cited by 0 Source ↗Scholar ↗