# What is this Article about? Extreme Summarization with Topic-aware Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1907.08722 · HTML: https://mlsanity.com/paper/1907.08722/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2019.

## Built on by (most cited first, 8 of 8)

- [Deep Transfer Learning & Beyond: Transformer Language Models in Information Systems Research](https://mlsanity.com/paper/2110.08975/) (2021)
- [CNewSum: A Large-scale Chinese News Summarization Dataset with Human-annotated Adequacy and Deducibility Level](https://mlsanity.com/paper/2110.10874/) (2021)
- [Abstractive Summarization Guided by Latent Hierarchical Document Structure](https://mlsanity.com/paper/2211.09458/) (2022)
- [A Single Example Can Improve Zero-Shot Data Generation](https://mlsanity.com/paper/2108.06991/) (2021)
- [Unsupervised Extractive Summarization by Human Memory Simulation](https://mlsanity.com/paper/2104.08392/) (2021)
- [DeepTitle -- Leveraging BERT to generate Search Engine Optimized Headlines](https://mlsanity.com/paper/2107.10935/) (2021)
- [Generating Summaries for Scientific Paper Review](https://mlsanity.com/paper/2109.14059/) (2021)
- ['Don't Get Too Technical with Me': A Discourse Structure-Based Framework for Science Journalism](https://mlsanity.com/paper/2310.15077/) (2023)

## Abstract (arXiv)

We introduce 'extreme summarization', a new single-document summarization task which aims at creating a short, one-sentence news summary answering the question ``What is the article about?''. We argue that extreme summarization, by nature, is not amenable to extractive strategies and requires an abstractive modeling approach. In the hope of driving research on this task further: (a) we collect a real-world, large scale dataset by harvesting online articles from the British Broadcasting Corporation (BBC); and (b) propose a novel abstractive model which is conditioned on the article's topics and based entirely on convolutional neural networks. We demonstrate experimentally that this architecture captures long-range dependencies in a document and recognizes pertinent content, outperforming an oracle extractive system and state-of-the-art abstractive approaches when evaluated automatically and by humans on the extreme summarization dataset.