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

Lixing Zhu; Runcong Zhao; Lin Gui; Yulan He

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

Lixing Zhu, Runcong Zhao, Lin Gui, Yulan He^*

^*Corresponding author for this work

Informatics

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

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.

Original language	English
Title of host publication	Findings of the Association for Computational Linguistics: EMNLP 2023
Publisher	Association for Computational Linguistics (ACL)
Publication status	Accepted/In press - 7 Oct 2023

Cite this

@inbook{c5bdcac6a748478b98e910a014ef7db3,

title = "Are NLP Models Good at Tracing Thoughts: An Overview of Narrative Understanding",

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.",

author = "Lixing Zhu and Runcong Zhao and Lin Gui and Yulan He",

year = "2023",

month = oct,

day = "7",

language = "English",

booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",

publisher = "Association for Computational Linguistics (ACL)",

}

TY - CHAP

T1 - Are NLP Models Good at Tracing Thoughts: An Overview of Narrative Understanding

AU - Zhu, Lixing

AU - Zhao, Runcong

AU - Gui, Lin

AU - He, Yulan

PY - 2023/10/7

Y1 - 2023/10/7

N2 - 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.

AB - 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.

M3 - Conference paper

BT - Findings of the Association for Computational Linguistics: EMNLP 2023

PB - Association for Computational Linguistics (ACL)

ER -

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

Abstract

Fingerprint

Cite this