Searching for Effective Neural Extractive Summarization: What Works and What’s Next
TL
TL;DR
This paper seeks to better understand how neural extractive summarization systems could benefit from different types of model architectures, transferable knowledge and learning schemas, and finds an effective way to improve the current framework.
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 why they perform so well, or 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. Besides, we find an effective way to improve the current framework and achieve the state-of-the-art result on CNN/DailyMail by a large margin based on our observations and analysis. Hopefully, our work could provide more hints for future research on extractive summarization.
References37 items
1
Content Selection in Deep Learning Models of Summarization
2
Transformer-XL: Language Modeling with Longer-Term Dependency
3
BanditSum: Extractive Summarization as a Contextual Bandit
4
Dissecting Contextual Word Embeddings: Architecture and Representation
5