"Going on a vacation" takes longer than "Going for a walk": A Study of Temporal Commonsense Understanding
This work addresses a limitedly studied but crucial problem for natural language processing, focusing on temporal aspects like duration and order, and is incremental as it builds on existing commonsense understanding efforts.
The paper tackles the problem of temporal commonsense understanding in natural language by defining five classes and creating the MCTACO dataset via crowdsourcing. It finds that current methods lag behind human performance by about 20% on this dataset.
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.