Event2Mind
Commonsense Inference on Events, Intents and Reactions

Quick links:  [ACL paper]   [ACL poster]   [download dataset]   [contact us]

For research or press inquiries, contact Hannah and/or Maarten.


see caption

Abstract

We investigate a new commonsense inference task: given an event described in a short free-form text ("X drinks coffee in the morning"), a system reasons about the likely intents ("X wants to stay awake") and reactions ("X feels alert") of the event’s participants. To support this study, we construct a new crowdsourced corpus of 25,000 event phrases covering a diverse range of everyday events and situations. We report baseline performance on this task, demonstrating that neural encoder-decoder models can successfully compose embedding representations of previously unseen events and reason about the likely intents and reactions of the event participants. In addition, we demonstrate how commonsense inference on people’s intents and reactions can help unveil the implicit gender inequality prevalent in modern movie scripts.


Browse our event annotations

Select an event and see our annotations:

No event selected

see caption see caption
Examples of commonsense inference on mental states of event participants. In the third example event, common sense tells us that Y is likely to feel betrayed as a result of X reading their diary.

see caption see caption
Two scene description snippets from Juno (2007, top) and Pretty Woman (1990, bottom).

Read our paper for more:
Hannah Rashkin, Maarten Sap, Emily Allaway, Noah A. Smith, & Yejin Choi (2018).
Event2Mind: Commonsense Inference on Events, Intents and Reactions. ACL [view pdf]