Searching for Effective Neural Extractive Summarization: What Works and What's Next

Abstract

The recent years have seen remarkable success in the use of deep neural networks on text summarization. However, there is no clear understanding of \textit{why} they perform so well, or \textit{how} they might be improved. In this paper, we seek to better understand how neural extractive summarization systems could benefit from different types of model architectures, transferable knowledge and learning schemas. Additionally, we find an effective way to improve current frameworks and achieve the state-of-the-art result on CNN/DailyMail by a large margin based on our observations and analyses. Hopefully, our work could provide more clues for future research on extractive summarization.

arXiv commentAccepted by ACL 2019 (oral); Project homepage: http://pfliu.com/InterpretSum/

References in corpus (7)

• Sequence to Sequence Learning with Neural Networks
• Teaching Machines to Read and Comprehend
• A Deep Reinforced Model for Abstractive Summarization
• Convolutional Neural Networks for Sentence Classification
• SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents
• Reasoning about Entailment with Neural Attention
• Order Matters: Sequence to sequence for sets

Cited by in corpus (5)

• RetrievalSum: A Retrieval Enhanced Framework for Abstractive Summarization
• Enhancing Scientific Papers Summarization with Citation Graph
• AREDSUM: Adaptive Redundancy-Aware Iterative Sentence Ranking for Extractive Document Summarization
• Fact-level Extractive Summarization with Hierarchical Graph Mask on BERT
• Reference and Document Aware Semantic Evaluation Methods for Korean Language Summarization