Trick Me If You Can: Adversarial Writing of Trivia Challenge Questions
share
Modern natural language processing systems have been touted as approaching human performance. However, existing datasets are imperfect tests. Examples are written with humans in mind, not computers, and often do not properly expose model limitations. We address this by developing a new process for crowdsourced annotation, adversarial writing, where humans interact with trained models and try to break them. Applying this annotation process to Trivia question answering yields a challenge set, which despite being easy for human players to answer, systematically stumps automated question answering systems. Diagnosing model errors on the evaluation data provides actionable insights to explore in developing more robust and generalizable question answering systems.
READ FULL TEXT