DiscoSum: Discourse-aware News Summarization

TL;DR

DiscoSum is a new discourse-aware summarization method that improves news summaries by maintaining narrative structure and adapting to different social media styles, validated through human and automatic evaluations.

Contribution

The paper introduces a novel discourse schema and an algorithm that incorporates discourse structure into news summarization, enhancing narrative fidelity and stylistic flexibility.

Findings

DiscoSum outperforms baseline models in maintaining narrative coherence.

The approach effectively adapts summaries to various social media formats.

Human and automatic evaluations confirm the method's efficacy.

Abstract

Recent advances in text summarization have predominantly leveraged large language models to generate concise summaries. However, language models often do not maintain long-term discourse structure, especially in news articles, where organizational flow significantly influences reader engagement. We introduce a novel approach to integrating discourse structure into summarization processes, focusing specifically on news articles across various media. We present a novel summarization dataset where news articles are summarized multiple times in different ways across different social media platforms (e.g. LinkedIn, Facebook, etc.). We develop a novel news discourse schema to describe summarization structures and a novel algorithm, DiscoSum, which employs beam search technique for structure-aware summarization, enabling the transformation of news stories to meet different stylistic and structural demands. Both human and automatic evaluation results demonstrate the efficacy of our approach in maintaining narrative fidelity and meeting structural requirements.