CLJul 19, 2019

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

arXiv:1907.08722v118 citations
Originality Highly original
AI Analysis

This addresses the problem of generating concise, abstractive summaries for news articles, which is incremental as it builds on existing summarization research with a new task and model.

The paper tackles extreme summarization, a task to generate one-sentence news summaries answering 'What is the article about?', by introducing a topic-aware convolutional neural network model that outperforms oracle extractive and state-of-the-art abstractive methods, as shown in automatic and human evaluations on a new BBC dataset.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes