A Condense-then-Select Strategy for Text Summarization

TL;DR

This paper introduces a novel condense-then-select framework for text summarization that condenses sentences concurrently and uses document context to select the best candidates, improving information retention and summary quality.

Contribution

The proposed framework addresses the limitation of ignoring context in separate sentence compression by condensing sentences first and then selecting with context awareness.

Findings

Outperforms select-then-compress baseline on multiple datasets.

Effectively retains salient information during summarization.

Achieves higher ROUGE scores compared to existing methods.

Abstract

Select-then-compress is a popular hybrid, framework for text summarization due to its high efficiency. This framework first selects salient sentences and then independently condenses each of the selected sentences into a concise version. However, compressing sentences separately ignores the context information of the document, and is therefore prone to delete salient information. To address this limitation, we propose a novel condense-then-select framework for text summarization. Our framework first concurrently condenses each document sentence. Original document sentences and their compressed versions then become the candidates for extraction. Finally, an extractor utilizes the context information of the document to select candidates and assembles them into a summary. If salient information is deleted during condensing, the extractor can select an original sentence to retain the information. Thus, our framework helps to avoid the loss of salient information, while preserving the high efficiency of sentence-level compression. Experiment results on the CNN/DailyMail, DUC-2002, and Pubmed datasets demonstrate that our framework outperforms the select-then-compress framework and other strong baselines.