# Sparse Optimization for Unsupervised Extractive Summarization of Long Documents with the Frank-Wolfe Algorithm

arXiv: https://arxiv.org/abs/2208.09454 · HTML: https://mlsanity.com/paper/2208.09454/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 42 references that are in the map.
- First posted on arXiv 19 Aug 2022.

## Builds on (most cited first, 12 of 12)

- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [A Neural Attention Model for Abstractive Sentence Summarization](https://mlsanity.com/paper/1509.00685/) (2015)
- [SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents](https://mlsanity.com/paper/1611.04230/) (2016)
- [Neural Summarization by Extracting Sentences and Words](https://mlsanity.com/paper/1603.07252/) (2016)
- [Better Summarization Evaluation with Word Embeddings for ROUGE](https://mlsanity.com/paper/1508.06034/) (2015)
- [Content Selection in Deep Learning Models of Summarization](https://mlsanity.com/paper/1810.12343/) (2018)
- [Extractive Summarization of Long Documents by Combining Global and Local Context](https://mlsanity.com/paper/1909.08089/) (2019)
- [Scalable Sparse Subspace Clustering by Orthogonal Matching Pursuit](https://mlsanity.com/paper/1507.01238/) (2015)
- [Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models](https://mlsanity.com/paper/1701.03185/) (2017)
- [Learning-Based Single-Document Summarization with Compression and Anaphoricity Constraints](https://mlsanity.com/paper/1603.08887/) (2016)
- [Text Generation with Exemplar-based Adaptive Decoding](https://mlsanity.com/paper/1904.04428/) (2019)
- [Efficient Summarization with Read-Again and Copy Mechanism](https://mlsanity.com/paper/1611.03382/) (2016)

## Abstract (arXiv)

We address the problem of unsupervised extractive document summarization, especially for long documents. We model the unsupervised problem as a sparse auto-regression one and approximate the resulting combinatorial problem via a convex, norm-constrained problem. We solve it using a dedicated Frank-Wolfe algorithm. To generate a summary with k sentences, the algorithm only needs to execute ≈ k iterations, making it very efficient. We explain how to avoid explicit calculation of the full gradient and how to include sentence embedding information. We evaluate our approach against two other unsupervised methods using both lexical (standard) ROUGE scores, as well as semantic (embedding-based) ones. Our method achieves better results with both datasets and works especially well when combined with embeddings for highly paraphrased summaries.