2 papers
cs.CL2024
What Makes Language Models Good-enough?
Daiki Asami, Saku Sugawara
Psycholinguistic research suggests that humans may build a representation of linguistic input that is 'good-enough' for the task at hand. This study examines what architectural fea…
cs.CL2023
PROPRES: Investigating the Projectivity of Presupposition with Various Triggers and Environments
Daiki Asami, Saku Sugawara
What makes a presupposition of an utterance -- information taken for granted by its speaker -- different from other pragmatic inferences such as an entailment is projectivity (e.g.…