HellaSwag: Can a Machine Really Finish Your Sentence?

Citations Over TimeTop 1% of 2019 papers

Abstract

introduced a new task of commonsense natural language inference: given an event description such as "A woman sits at a piano," a machine must select the most likely followup: "She sets her fingers on the keys." With the introduction of BERT (Devlin et al., 2018), near human-level performance was reached. Does this mean that machines can perform human level commonsense inference?

Related Papers

• → Recent Advances in Adversarial Training for Adversarial Robustness(2021)43 cited
• → Who is Responsible for Adversarial Defense?(2021)1 cited
• → Selective Adversarial Behavior(2011)
• → 18. The Adoption of the essential features of the adversarial system(2013)
• → 7 Adversarial Experts(2001)