Distraction-Based Neural Networks for Document Summarization

TL;DR

This paper introduces distraction-based neural network models for document summarization, which improve understanding of long documents by encouraging models to traverse diverse content, achieving state-of-the-art results without feature engineering.

Contribution

The paper presents a novel distraction mechanism in neural networks that enhances document-level modeling for summarization, especially for long texts, surpassing previous methods.

Findings

Models achieve state-of-the-art performance on large datasets.

Distraction modeling significantly benefits long document summarization.

No feature engineering required for the proposed models.

Abstract

Distributed representation learned with neural networks has recently shown to be effective in modeling natural languages at fine granularities such as words, phrases, and even sentences. Whether and how such an approach can be extended to help model larger spans of text, e.g., documents, is intriguing, and further investigation would still be desirable. This paper aims to enhance neural network models for such a purpose. A typical problem of document-level modeling is automatic summarization, which aims to model documents in order to generate summaries. In this paper, we propose neural models to train computers not just to pay attention to specific regions and content of input documents with attention models, but also distract them to traverse between different content of a document so as to better grasp the overall meaning for summarization. Without engineering any features, we train the models on two large datasets. The models achieve the state-of-the-art performance, and they significantly benefit from the distraction modeling, particularly when input documents are long.