Research Area:  Machine Learning

Abstract:

Understanding time is crucial for understanding events expressed in natural language. Because people rarely say the obvious, it is often necessary to have commonsense knowledge about various temporal aspects of events, such as duration, frequency, and temporal order. However, this important problem has so far received limited attention. This paper systematically studies this temporal commonsense problem. Specifically, we define five classes of temporal commonsense, and use crowdsourcing to develop a new dataset, MCTACO, that serves as a test set for this task. We find that the best current methods used on MCTACO are still far behind human performance, by about 20%, and discuss several directions for improvement. We hope that the new dataset and our study here can foster more future research on this topic.

Keywords:  
Natural language
Commonsense knowledge
Temporal aspects
Temporal commonsense problem
MCTACO

Author(s) Name:  Ben Zhou, Daniel Khashabi, Qiang Ning, Dan Roth

Publisher name:  arXiv.1909.03065

DOI:  10.48550/arXiv.1909.03065

Volume Information:  

Paper Link:   https://arxiv.org/abs/1909.03065