Christopher Potts

3 paper cards in Mova's library · 2010–2025

Christopher Potts wrote 3 of the papers Mova reads, in 2010–2025; often with Atticus Geiger, Christopher D. Manning, Kyle Mahowald.

The profile is the library's match of the name; two people with one name are not always told apart.

Papers

Causal Interventions Reveal Shared Structure Across English Filler–Gap Constructions (2025)
The paper asks whether a language model uses one shared mechanism for several English filler–gap constructions (embedded wh-questions, matrix wh-questions, relative clauses, clefts, pseudo-clefts, topicalization).
Neural Natural Language Inference Models Partially Embed Theories of Lexical Entailment and Negation (2020)
The question is whether neural NLI models learn how negation reverses lexical entailment: "dance" entails "move", but "not move" does not entail "not dance".
Was It Good? It Was Provocative.'' Learning the Meaning of Scalar Adjectives (2010)
Indirect answers to yes/no questions often do not say "yes" or "no" outright. "Was it good? It was provocative" leaves the answer open, while "It was great" does not. The authors mine two kinds of evidence. First, scale order between gradable adjectives comes from online IMDB reviews: a word's expected star rating…