conftrace_

hypothesis-only bia

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

natural language inference (2) ensemble adversary (1) cross-dataset transfer (1) dataset artifact (1) probabilistic method (1) sentence representation (1) bias reduction (1) spurious correlation (1) adversarial training (1) model robustness (1)

Papers

Avoiding the Hypothesis-Only Bias in Natural Language Inference via Ensemble Adversarial Training EMNLP 2020 Don’t Take the Premise for Granted: Mitigating Artifacts in Natural Language Inference ACL 2019