SummCoder: An unsupervised framework for extractive text summarization based on deep auto-encoders
作者：
Highlights：
• An unsupervised text summarization framework based on deep neural networks.
• Vector representation of sentences using recurrent neural networks.
• Summary generated using three sentence features relevance, novelty and position.
• Deep auto-encoders are exploited for computing sentence content relevance.
• A new text summarization dataset is introduced from darknet domains.
摘要
•An unsupervised text summarization framework based on deep neural networks.•Vector representation of sentences using recurrent neural networks.•Summary generated using three sentence features relevance, novelty and position.•Deep auto-encoders are exploited for computing sentence content relevance.•A new text summarization dataset is introduced from darknet domains.
论文关键词：Extractive text summarization,Auto-encoder,Deep learning,Sentence embedding,TOR darknet,Extractive summarization
论文评审过程：Received 22 August 2018, Revised 26 March 2019, Accepted 27 March 2019, Available online 30 March 2019, Version of Record 12 April 2019.
论文官网地址：https://doi.org/10.1016/j.eswa.2019.03.045
