Bottom-Up Abstractive Summarization

TL;DR

This paper introduces a bottom-up approach for abstractive summarization that uses a content selector to improve content selection and compression, resulting in more fluent and accurate summaries with minimal training data.

Contribution

It proposes a simple, effective bottom-up attention method that enhances content selection in neural summarization, outperforming previous end-to-end models.

Findings

Significant ROUGE score improvements on CNN-DM and NYT datasets.

Effective with as few as 1,000 training sentences.

Simpler and more accurate than existing content selection methods.

Abstract

Neural network-based methods for abstractive summarization produce outputs that are more fluent than other techniques, but which can be poor at content selection. This work proposes a simple technique for addressing this issue: use a data-efficient content selector to over-determine phrases in a source document that should be part of the summary. We use this selector as a bottom-up attention step to constrain the model to likely phrases. We show that this approach improves the ability to compress text, while still generating fluent summaries. This two-step process is both simpler and higher performing than other end-to-end content selection models, leading to significant improvements on ROUGE for both the CNN-DM and NYT corpus. Furthermore, the content selector can be trained with as little as 1,000 sentences, making it easy to transfer a trained summarizer to a new domain.