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

arXiv: https://arxiv.org/abs/2412.00810 · HTML: https://mlsanity.com/paper/2412.00810/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 36 references that are in the map.
- First posted on arXiv 1 Dec 2024.

## Builds on (most cited first, 5 of 5)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Summarize, Outline, and Elaborate: Long-Text Generation via Hierarchical Supervision from Extractive Summaries](https://mlsanity.com/paper/2010.07074/) (2020)
- [Synchronized Video Storytelling: Generating Video Narrations with Structured Storyline](https://mlsanity.com/paper/2405.14040/) (2024)
- [Compressing Long Context for Enhancing RAG with AMR-based Concept Distillation](https://mlsanity.com/paper/2405.03085/) (2024)
- [Outline Generation: Understanding the Inherent Content Structure of Documents](https://mlsanity.com/paper/1905.10039/) (2019)

## Abstract (arXiv)

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.