Temporal Reasoning in Natural Language Inference
2020pp. 4070–4078
Citations Over TimeTop 10% of 2020 papers
Abstract
We introduce five new natural language inference (NLI) datasets focused on temporal reasoning. We recast four existing datasets annotated for event duration-how long an event lasts-and event ordering-how events are temporally arranged-into more than one million NLI examples. We use these datasets to investigate how well neural models trained on a popular NLI corpus capture these forms of temporal reasoning.
Related Papers
- Analysis of Actual Duration by Effecting Elements to Duration Estimate - Focused on Standard Duration of the Office Building Construction -(2002)
- → A Guide to Fixed Income Portfolio Management Using Risk Duration, Reward Duration, and Duration Ratio as Alternatives to Effective Duration and Convexity(2007)
- Discussion about the Duration of the Guarantee(2004)
- → Subjective Duration(2007)
- → Subjective Duration(1999)