Long-Span Summarization via Local Attention and Content Selection

TL;DR

This paper introduces methods to improve long-span document summarization using local attention and content selection in transformer models, achieving state-of-the-art results efficiently on multiple datasets.

Contribution

It presents a novel combination of local self-attention and explicit content selection to enhance long document summarization with transformer models.

Findings

Achieves state-of-the-art ROUGE scores on Spotify Podcast, arXiv, and PubMed datasets.

Efficiently handles long documents without large-scale GPU resources.

Outperforms existing approaches in summarization quality.

Abstract

Transformer-based models have achieved state-of-the-art results in a wide range of natural language processing (NLP) tasks including document summarization. Typically these systems are trained by fine-tuning a large pre-trained model to the target task. One issue with these transformer-based models is that they do not scale well in terms of memory and compute requirements as the input length grows. Thus, for long document summarization, it can be challenging to train or fine-tune these models. In this work, we exploit large pre-trained transformer-based models and address long-span dependencies in abstractive summarization using two methods: local self-attention; and explicit content selection. These approaches are compared on a range of network configurations. Experiments are carried out on standard long-span summarization tasks, including Spotify Podcast, arXiv, and PubMed datasets. We demonstrate that by combining these methods, we can achieve state-of-the-art results on all three tasks in the ROUGE scores. Moreover, without a large-scale GPU card, our approach can achieve comparable or better results than existing approaches.