A new dataset and surprisal-based metric estimate that roughly 20% of naturally occurring generic sentences are weak generalisations and that generics are more context-sensitive than explicit quantifiers.
Hwang, Kathleen McKeown, and Sarah-Jane Leslie
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Generics are puzzling. Can language models find the missing piece?
A new dataset and surprisal-based metric estimate that roughly 20% of naturally occurring generic sentences are weak generalisations and that generics are more context-sensitive than explicit quantifiers.