Don’t Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization

Citations Over TimeTop 1% of 2018 papers

Abstract

We introduce extreme summarization, a new single-document summarization task which does not favor extractive strategies and calls for an abstractive modeling approach. The idea is to create a short, one-sentence news summary answering the question "What is the article about?". We collect a real-world, large scale dataset for this task by harvesting online articles from the British Broadcasting Corporation (BBC). We 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 longrange 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. 1

Related Papers

• Multilingual Summarization Evaluation without Human Models(2010)
• On the Applications of the Experience Summarization in Modern Teaching and Research(2000)
• → Dynamic Summarization: Another Stride Towards Summarization(2007)
• → Dynamic Summarization: Another Stride Towards Summarization(2007)