Modeling Naive Psychology of Characters in Simple Commonsense Stories

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 largescale dataset with rich low-level annotations and establishes baseline performance on several new tasks, suggesting avenues for future research.

Toward Comprehensive Understanding of a Sentiment Based on Human Motives

“…Our work is in line with studies attempting to identify relevant motives in texts (Ding and Riloff, 2018;Rashkin et al, 2018), aiming to equip machines with the ability to understand a more complete description of a situation and justify human decisions and actions. While Ding and Riloff (2018) and Rashkin et al (2018) specifically focus on predicate-argument tuples and artificial texts, respectively, our work analyzes real review sentences.…”

Ranking and Selecting Multi-Hop Knowledge Paths to Better Predict Human Needs

“…Data statistics is reported in Table 1. Rashkin et al (2018) report that there is low annotator agreement i.a. between the belonging and the approval class.…”

“…Our task is to automatically predict human needs of story characters given a story context. In this task, following the setup of Rashkin et al (2018), we explain the probable reasons for the expression of emotions by predicting appropriate categories from two theories of psychology: Hierarchy of needs (Maslow, 1943) and basic motives (Reiss, 2002). The task is defined as a multi-label classification problem with five coarse-grained (Maslow) and 19 fine-grained (Reiss) categories, respectively (see Fig.…”

“…In this paper we focus on the Modelling Naive Psychology of Characters in Simple Commonsense Stories dataset of Rashkin et al (2018), which contains annotations of a fully-specified chain of motivations and emotional reactions of characters for a collection of narrative stories. The stories are annotated with labels from multiple theories of psychology (Reiss, 2004;Maslow, 1943;Plutchik, 1980) to provide explanations for the emotional reactions of characters.…”

“…They also provide a richer representation of answers by building subgraphs of entities appearing in answers. In contrast, our work aims to provide information about missing links Rashkin et al (2018). between sentiment words in a text and underlying human needs by extracting relevant multi-hop paths from structured knowledge bases.…”