Text summarization using unsupervised deep learning

作者：

Highlights：

• Unsupervised extractive summarization of emails using a deep auto-encoder with excellent performance.

• Ensemble Noisy Auto-Encoder runs noisy inputs through one trained network, enhancing performance.

• Summaries are highly informative and semantically similar to human abstracts.

摘要

•Unsupervised extractive summarization of emails using a deep auto-encoder with excellent performance.•Ensemble Noisy Auto-Encoder runs noisy inputs through one trained network, enhancing performance.•Summaries are highly informative and semantically similar to human abstracts.

论文关键词：Deep Learning,Query-oriented Summarization,Extractive Summarization,Ensemble Noisy Auto-Encoder

论文评审过程：Received 19 May 2016, Revised 1 August 2016, Accepted 10 October 2016, Available online 12 October 2016, Version of Record 20 October 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2016.10.017