GSum: A General Framework for Guided Neural Abstractive Summarization

Abstract

Neural abstractive summarization models are flexible and can produce coherent summaries, but they are sometimes unfaithful and can be difficult to control. While previous studies attempt to provide different types of guidance to control the output and increase faithfulness, it is not clear how these strategies compare and contrast to each other. In this paper, we propose a general and extensible guided summarization framework (GSum) that can effectively take different kinds of external guidance as input, and we perform experiments across several different varieties. Experiments demonstrate that this model is effective, achieving state-of-the-art performance according to ROUGE on 4 popular summarization datasets when using highlighted sentences as guidance. In addition, we show that our guided model can generate more faithful summaries and demonstrate how different types of guidance generate qualitatively different summaries, lending a degree of controllability to the learned models.

arXiv commentNAACL 2021

References in corpus (5)

• Teaching Machines to Read and Comprehend
• A Deep Reinforced Model for Abstractive Summarization
• SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents
• WikiHow: A Large Scale Text Summarization Dataset
• Abstractive Summarization with Combination of Pre-trained Sequence-to-Sequence and Saliency Models

Cited by in corpus (5)

• RetrievalSum: A Retrieval Enhanced Framework for Abstractive Summarization
• Text Summarization with Latent Queries
• Improving Factual Consistency of Abstractive Summarization on Customer Feedback
• TSSuBERT: Tweet Stream Summarization Using BERT
• Cross-lingual Transfer of Abstractive Summarizer to Less-resource Language