Join or Log in
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. To reward systems with real language understanding abilities, we propose an adversarial evaluation scheme for the Stanford Question Answering Dataset (SQuAD).
[1707.07328] Adversarial Examples for Evaluating Reading Comprehension Systems 
Added 10 months ago by Francis Tseng
Show info
[1707.07328] Adversarial Examples for Evaluating Reading Comprehension Systems 
Info
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. To reward systems with real language understanding abilities, we propose an adversarial evaluation scheme for the Stanford Question Answering Dataset (SQuAD).
1 Connection