# A Hierarchical Structured Self-Attentive Model for Extractive Document Summarization (HSSAS)

arXiv: https://arxiv.org/abs/1805.07799 · HTML: https://mlsanity.com/paper/1805.07799/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 May 2018.

## Built on by (most cited first, 9 of 9)

- [Generative Artificial Intelligence: A Systematic Review and Applications](https://mlsanity.com/paper/2405.11029/) (2024)
- [MemSum: Extractive Summarization of Long Documents Using Multi-Step Episodic Markov Decision Processes](https://mlsanity.com/paper/2107.08929/) (2021)
- [Does Head Label Help for Long-Tailed Multi-Label Text Classification](https://mlsanity.com/paper/2101.09704/) (2021)
- [Extractive Research Slide Generation Using Windowed Labeling Ranking](https://mlsanity.com/paper/2106.03246/) (2021)
- [Detect and Classify -- Joint Span Detection and Classification for Health Outcomes](https://mlsanity.com/paper/2104.07789/) (2021)
- [Interpreting Song Lyrics with an Audio-Informed Pre-trained Language Model](https://mlsanity.com/paper/2208.11671/) (2022)
- [Sparse-softmax: A Simpler and Faster Alternative Softmax Transformation](https://mlsanity.com/paper/2112.12433/) (2021)
- [Multi-head Sequence Tagging Model for Grammatical Error Correction](https://mlsanity.com/paper/2410.16473/) (2024)
- [Comparing Approaches to Automatic Summarization in Less-Resourced Languages](https://mlsanity.com/paper/2512.24410/) (2025)

## Abstract (arXiv)

The recent advance in neural network architecture and training algorithms have shown the effectiveness of representation learning. The neural network-based models generate better representation than the traditional ones. They have the ability to automatically learn the distributed representation for sentences and documents. To this end, we proposed a novel model that addresses several issues that are not adequately modeled by the previously proposed models, such as the memory problem and incorporating the knowledge of document structure. Our model uses a hierarchical structured self-attention mechanism to create the sentence and document embeddings. This architecture mirrors the hierarchical structure of the document and in turn enables us to obtain better feature representation. The attention mechanism provides extra source of information to guide the summary extraction. The new model treated the summarization task as a classification problem in which the model computes the respective probabilities of sentence-summary membership. The model predictions are broken up by several features such as information content, salience, novelty and positional representation. The proposed model was evaluated on two well-known datasets, the CNN / Daily Mail, and DUC 2002. The experimental results show that our model outperforms the current extractive state-of-the-art by a considerable margin.