Modeling Naive Psychology of Characters in Simple Commonsense Stories

TL;DR

This paper introduces a new dataset and annotation framework for modeling characters' naive psychology in simple stories, aiming to improve machine understanding of unspoken mental states and motivations.

Contribution

It provides a large-scale, richly annotated dataset of mental states in stories and establishes baseline performance for related reasoning tasks.

Findings

New dataset with detailed mental state annotations

Baseline models demonstrate initial performance on reasoning tasks

Framework enables future research in story understanding and psychology modeling

Abstract

Understanding a narrative requires reading between the lines and reasoning about the unspoken but obvious implications about events and people's mental states - a capability that is trivial for humans but remarkably hard for machines. To facilitate research addressing this challenge, we introduce a new annotation framework to explain naive psychology of story characters as fully-specified chains of mental states with respect to motivations and emotional reactions. Our work presents a new large-scale dataset with rich low-level annotations and establishes baseline performance on several new tasks, suggesting avenues for future research.