# Unsupervised Extractive Summarization by Pre-training Hierarchical Transformers

arXiv: https://arxiv.org/abs/2010.08242 · HTML: https://mlsanity.com/paper/2010.08242/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Oct 2020.

## Built on by (most cited first, 16 of 16)

- [Pretrained Language Models for Text Generation: A Survey](https://mlsanity.com/paper/2105.10311/) (2021)
- [Long Document Summarization with Top-down and Bottom-up Inference](https://mlsanity.com/paper/2203.07586/) (2022)
- [Unsupervised Extractive Summarization using Pointwise Mutual Information](https://mlsanity.com/paper/2102.06272/) (2021)
- [Leveraging Locality in Abstractive Text Summarization](https://mlsanity.com/paper/2205.12476/) (2022)
- [Unsupervised Multi-Granularity Summarization](https://mlsanity.com/paper/2201.12502/) (2022)
- [An Efficient Coarse-to-Fine Facet-Aware Unsupervised Summarization Framework based on Semantic Blocks](https://mlsanity.com/paper/2208.08253/) (2022)
- [Survey of Query-based Text Summarization](https://mlsanity.com/paper/2211.11548/) (2022)
- [NextLevelBERT: Masked Language Modeling with Higher-Level Representations for Long Documents](https://mlsanity.com/paper/2402.17682/) (2024)
- [A New Sentence Extraction Strategy for Unsupervised Extractive Summarization Methods](https://mlsanity.com/paper/2112.03203/) (2021)
- [RTSUM: Relation Triple-based Interpretable Summarization with Multi-level Salience Visualization](https://mlsanity.com/paper/2310.13895/) (2023)
- [Bipartite Graph Pre-training for Unsupervised Extractive Summarization with Graph Convolutional Auto-Encoders](https://mlsanity.com/paper/2310.18992/) (2023)
- [Unsupervised Extractive Summarization with Learnable Length Control Strategies](https://mlsanity.com/paper/2312.06901/) (2023)
- [GAE-ISumm: Unsupervised Graph-Based Summarization of Indian Languages](https://mlsanity.com/paper/2212.12937/) (2022)
- [Improving Sentence Similarity Estimation for Unsupervised Extractive Summarization](https://mlsanity.com/paper/2302.12490/) (2023)
- [Efficient and Interpretable Compressive Text Summarisation with Unsupervised Dual-Agent Reinforcement Learning](https://mlsanity.com/paper/2306.03415/) (2023)
- [Inducing Causal Structure for Abstractive Text Summarization](https://mlsanity.com/paper/2308.12888/) (2023)

## Abstract (arXiv)

Unsupervised extractive document summarization aims to select important sentences from a document without using labeled summaries during training. Existing methods are mostly graph-based with sentences as nodes and edge weights measured by sentence similarities. In this work, we find that transformer attentions can be used to rank sentences for unsupervised extractive summarization. Specifically, we first pre-train a hierarchical transformer model using unlabeled documents only. Then we propose a method to rank sentences using sentence-level self-attentions and pre-training objectives. Experiments on CNN/DailyMail and New York Times datasets show our model achieves state-of-the-art performance on unsupervised summarization. We also find in experiments that our model is less dependent on sentence positions. When using a linear combination of our model and a recent unsupervised model explicitly modeling sentence positions, we obtain even better results.