Modeling Human Mental States with an Entity-based Narrative Graph

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4916–4926 June 6–11, 2021. ©2021 Association for Computational Linguistics 4916 Modeling Human Mental States with an Entity-based Narrative Graph I-Ta Lee, Maria Leonor Pacheco, Dan Goldwasser Department of Computer Science Purdue University West Lafayette, IN, USA {lee2226, pachecog, dgoldwas}@purdue.edu Abstract Understanding narrative text requires captur- ing characters’ motivations, goals, and mental states. This paper proposes an Entity-based Narrative Graph (ENG) to model the internal- states of characters in a story. We explicitly model entities, their interactions and the con- text in which they appear, and learn rich rep- resentations for them. We experiment with different task-adaptive pre-training objectives, in-domain training, and symbolic inference to capture dependencies between different deci- sions in the output space. We evaluate our model on two narrative understanding tasks: predicting character mental states, and desire fulfillment, and conduct a qualitative analysis. 1 Introduction Understanding narrative text requires modeling the motivations, goals and internal states of the char- acters described in it. These elements can help explain intentional behavior and capture causal con- nections between the characters’ actions and their goals. While this is straightforward for humans, machine readers often struggle as a correct anal- ysis relies on making long range common-sense inferences over the narrative text. Providing the ap- propriate narrative representation for making such inferences is therefore a key component. In this paper, we suggest a novel narrative representation model and evaluate it on two narrative understand- ing tasks, analyzing the characters’ mental states and motivations (Abdul-Mageed and Ungar, 2017; Rashkin et al., 2018; Chen et al., 2020), and desire fulfillment (Chaturvedi et al., 2016; Rahimtoroghi et al., 2017). We follow the observation that narrative under- standing requires an expressive representation cap- turing the context in which events appear and the interactions between characters’ states. To clarify, consider the short story in Fig. 1. The desire ex- pression appears early in the story and provides the context explaining the protagonist’s actions. Evaluating the fulfilment status of this expression, Cindy really likes apples. She wanted to try something new with them. She decided to try to make baked apples for the first time. She gathered everything she needed and began cooking. It's now her favorite apple dish! Desire Expression: try something new with them Motivation (Reiss): Curiosity Emotion (Plutchik): Joy, Anticipation Desire Fulfilled! Motivation (Reiss): Independence Emotion (Plutchik): Joy Figure 1: Narrative Example which tends to appear towards the end of the story, requires models that can reason over the desire ex- pression (“trying something new”), its target (“ap- ples”) and the outcome of the protagonist’s actions (“it’s now her favorite apple dish!”). Capturing the interaction between the motivation underlying the desire expression (in Fig. 1, CURIOSITY) and the emotions (in Fig. 1, ANTICIPATION) likely to be invoked by the motivation can help ensure the consistency of this analysis and improve its quality. To meet this challenge, we suggest a graph- contextualized representation for entity states. …

Content truncated to 500 words