OrderSum: Semantic Sentence Ordering for Extractive Summarization

TL;DR

OrderSum introduces a novel approach to extractive summarization that emphasizes the semantic ordering of sentences, significantly improving summary coherence and quality.

Contribution

The paper presents OrderSum, a new model that incorporates sentence order into embeddings and training objectives, advancing extractive summarization methods.

Findings

Achieves state-of-the-art ROUGE-L score of 30.52 on CNN/DailyMail

Outperforms previous models by 2.54 in ROUGE-L score

Effectively models sentence order to enhance summary coherence

Abstract

There are two main approaches to recent extractive summarization: the sentence-level framework, which selects sentences to include in a summary individually, and the summary-level framework, which generates multiple candidate summaries and ranks them. Previous work in both frameworks has primarily focused on improving which sentences in a document should be included in the summary. However, the sentence order of extractive summaries, which is critical for the quality of a summary, remains underexplored. In this paper, we introduce OrderSum, a novel extractive summarization model that semantically orders sentences within an extractive summary. OrderSum proposes a new representation method to incorporate the sentence order into the embedding of the extractive summary, and an objective function to train the model to identify which extractive summary has a better sentence order in the semantic space. Extensive experimental results demonstrate that OrderSum obtains state-of-the-art performance in both sentence inclusion and sentence order for extractive summarization. In particular, OrderSum achieves a ROUGE-L score of 30.52 on CNN/DailyMail, outperforming the previous state-of-the-art model by a large margin of 2.54.