Event2Mind: Commonsense Inference on Events, Intents, and Reactions
This addresses the problem of understanding human behavior and biases in AI systems, though it is incremental as it builds on existing neural models for a new task.
The paper tackles the task of commonsense inference on events, intents, and reactions by constructing a corpus of 25,000 event phrases and showing that neural encoder-decoder models can effectively reason about these aspects, with an application revealing implicit gender inequality in movie scripts.
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.