Event2Mind: Commonsense Inference on Events, Intents, and Reactions

TL;DR

Event2Mind introduces a new task for commonsense inference about events, focusing on understanding participants' intents and reactions, supported by a large crowdsourced dataset and baseline neural models.

Contribution

The paper presents a novel inference task, a large annotated corpus, and baseline neural models for reasoning about event participants' intents and reactions.

Findings

Neural models can effectively infer intents and reactions for unseen events.

The dataset covers 25,000 diverse everyday event phrases.

Commonsense inference reveals implicit gender biases in movie scripts.

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.