2 papers
cs.AI2023
Pragmatic Reasoning Unlocks Quantifier Semantics for Foundation Models
Yiyuan Li, Rakesh R. Menon, Sayan Ghosh +1
Generalized quantifiers (e.g., few, most) are used to indicate the proportions predicates are satisfied (for example, some apples are red). One way to interpret quantifier semantic…
cs.CL2021
Adversarial Scrubbing of Demographic Information for Text Classification
Somnath Basu Roy Chowdhury, Sayan Ghosh, Yiyuan Li +3
Contextual representations learned by language models can often encode undesirable attributes, like demographic associations of the users, while being trained for an unrelated targ…