Are NLP Models Good at Tracing Thoughts: An Overview of Narrative Understanding
This is an incremental survey that addresses the challenge of narrative comprehension for AI applications, potentially improving tasks like story analysis and author intent detection.
The paper tackles the problem of whether NLP models can trace author thoughts in narrative understanding, finding that LLMs have limitations in comprehending cognitive processes despite excelling in text generation, and it introduces a new perspective by framing narrative understanding as retrieving imaginative cues.
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.