Adversarial Examples for Evaluating Reading Comprehension Systems

Citations Over TimeTop 1% of 2017 papers

Abstract

Standard accuracy metrics indicate that reading comprehension systems are making rapid progress, but the extent to which these systems truly understand language remains unclear.

Related Papers

• → Forensic science evidence in non-adversary criminal justice systems(2018)1 cited
• → Intent Driven Adversarial Modeling(2005)8 cited
• → Adversarial Cheap Talk(2022)2 cited
• → A Simple Yet Efficient Method for Adversarial Word-Substitute Attack(2022)