Papers by Judith Degen

2 papers
Harnessing the linguistic signal to predict scalar inferences (2020.acl-main)

Copied to clipboard

Challenge: Recent Bayesian game-theoretic models of pragmatic reasoning can predict the strength of scalar inferences by using linguistic features.
Approach: They propose to use a sentence encoder to predict the strength of scalar inferences by using a corpus of linguistic data.
Outcome: The proposed model infers previously established associations between linguistic features and inference strength, suggesting that it learns to use linguistic feature to predict pragmatic inferences.
Expectations over Unspoken Alternatives Predict Pragmatic Inferences (2023.tacl-1)

Copied to clipboard

Challenge: Scalar inferences (SI) are a signature example of how humans interpret language based on unspoken alternatives.
Approach: They propose to use context-driven expectations to explain scale-based inferences . they find that expectedness of a strong scalemate captures SI rates within and across scales - but only under meaning-based view of alternatives.
Outcome: The proposed model captures SI rates by expectedness of a strong scalemate as an alternative, but only under a meaning-based view of alternatives.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations