Long text outline generation: Chinese text outline based on unsupervised framework and large language mode

TL;DR

This paper introduces a novel unsupervised framework combined with large language models for generating coherent outlines of very long Chinese texts by segmenting chapters and summarizing each segment.

Contribution

It proposes a new method that integrates graph-based chapter segmentation with large models for outline generation in Chinese, addressing limitations of existing approaches on long texts.

Findings

Outperforms existing deep learning and large models in segmentation accuracy.

Produces more readable and coherent outlines for long Chinese texts.

Effective in segmenting chapters and summarizing plot segments.

Abstract

Outline generation aims to reveal the internal structure of a document by identifying underlying chapter relationships and generating corresponding chapter summaries. Although existing deep learning methods and large models perform well on small- and medium-sized texts, they struggle to produce readable outlines for very long texts (such as fictional works), often failing to segment chapters coherently. In this paper, we propose a novel outline generation method for Chinese, combining an unsupervised framework with large models. Specifically, the method first generates chapter feature graph data based on entity and syntactic dependency relationships. Then, a representation module based on graph attention layers learns deep embeddings of the chapter graph data. Using these chapter embeddings, we design an operator based on Markov chain principles to segment plot boundaries. Finally, we employ a large model to generate summaries of each plot segment and produce the overall outline. We evaluate our model based on segmentation accuracy and outline readability, and our performance outperforms several deep learning models and large models in comparative evaluations.