← Search

Anders Sandholm

2 accepted papers

2022

“Will You Find These Shortcuts?” A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification

EMNLP 2022main

Feature attribution a.k.a. input salience methods which assign an importance score to a feature are abundant but may produce surprisingly different results for the same model on the same input. While differences are expected if disparate definitions of importance are assumed, most methods claim to p…

Cited by 69SourcePDFScholar
2021

Analogy Training Multilingual Encoders

AAAI 2021technical

Language encoders encode words and phrases in ways that capture their local semantic relatedness, but are known to be globally inconsistent. Global inconsistency can seemingly be corrected for, in part, by leveraging signals from knowledge bases, but previous results are partial and limited to monol…