Neural Extractive Summarization with Side Information

Abstract

Most extractive summarization methods focus on the main body of the document from which sentences need to be extracted. However, the gist of the document may lie in side information, such as the title and image captions which are often available for newswire articles. We propose to explore side information in the context of single-document extractive summarization. We develop a framework for single-document summarization composed of a hierarchical document encoder and an attention-based extractor with attention over side information. We evaluate our model on a large scale news dataset. We show that extractive summarization with side information consistently outperforms its counterpart that does not use any side information, in terms of both informativeness and fluency.

9 pages

References in corpus (3)

• Sequence to Sequence Learning with Neural Networks
• Natural Language Processing (almost) from Scratch
• SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents

Cited by in corpus (11)

• Deconvolutional Paragraph Representation Learning
• Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization
• Sequence-Based Extractive Summarisation for Scientific Articles
• Automatic Generation of Chinese Short Product Titles for Mobile Display
• An Effective Contextual Language Modeling Framework for Speech Summarization with Augmented Features
• Weakly-Supervised Opinion Summarization by Leveraging External Information
• Reference and Document Aware Semantic Evaluation Methods for Korean Language Summarization
• Goal-Driven Sequential Data Abstraction
• IndoSum: A New Benchmark Dataset for Indonesian Text Summarization
• Ranking sentences from product description & bullets for better search
• An Unsupervised Semantic Sentence Ranking Scheme for Text Documents