M-SENSE: Modeling Narrative Structure in Short Personal Narratives Using Protagonist's Mental Representations

TL;DR

This paper introduces M-SENSE, a model that analyzes characters' mental states and linguistic features to automatically detect key narrative elements like climax and resolution in short personal stories.

Contribution

It presents a novel approach combining mental state inference and linguistic analysis for modeling narrative structure, along with a new annotated dataset.

Findings

Significant improvement over prior baselines in identifying climax and resolution.

Effective integration of mental state representations with semantic embeddings.

Demonstrates the importance of cognitive-linguistic links in narrative understanding.

Abstract

Narrative is a ubiquitous component of human communication. Understanding its structure plays a critical role in a wide variety of applications, ranging from simple comparative analyses to enhanced narrative retrieval, comprehension, or reasoning capabilities. Prior research in narratology has highlighted the importance of studying the links between cognitive and linguistic aspects of narratives for effective comprehension. This interdependence is related to the textual semantics and mental language in narratives, referring to characters' motivations, feelings or emotions, and beliefs. However, this interdependence is hardly explored for modeling narratives. In this work, we propose the task of automatically detecting prominent elements of the narrative structure by analyzing the role of characters' inferred mental state along with linguistic information at the syntactic and semantic levels. We introduce a STORIES dataset of short personal narratives containing manual annotations of key elements of narrative structure, specifically climax and resolution. To this end, we implement a computational model that leverages the protagonist's mental state information obtained from a pre-trained model trained on social commonsense knowledge and integrates their representations with contextual semantic embed-dings using a multi-feature fusion approach. Evaluating against prior zero-shot and supervised baselines, we find that our model is able to achieve significant improvements in the task of identifying climax and resolution.