Are NLP Models Good at Tracing Thoughts: An Overview of Narrative Understanding

Lixing Zhu, Runcong Zhao, Lin Gui, Yulan He

Submission Type: Regular Long Paper

Submission Track: NLP Applications

Submission Track 2: Machine Learning for NLP

Keywords: Narrative Understanding, Reading Comprehension, Summarization, Question Answering

TL;DR: This paper surveys narrative understanding and provides insights into possible new tasks.

Abstract: Narrative understanding involves capturing the author's cognitive processes, providing insights into their knowledge, intentions, beliefs, and desires. Although large language models (LLMs) excel in generating grammatically coherent text, their ability to comprehend the author's thoughts remains uncertain. This limitation hinders the practical applications of narrative understanding. In this paper, we conduct a comprehensive survey of narrative understanding tasks, thoroughly examining their key features, definitions, taxonomy, associated datasets, training objectives, evaluation metrics, and limitations. Furthermore, we explore the potential of expanding the capabilities of modularized LLMs to address novel narrative understanding tasks. By framing narrative understanding as the retrieval of the author's imaginative cues that outline the narrative structure, our study introduces a fresh perspective on enhancing narrative comprehension.

Submission Number: 4527