Generating summary sentences using Adversarially Regularized Autoencoders with conditional context

作者：

Highlights：

• We proposed a novel summary method by using code vector of autoencoder.

• Unsupervised abstractive summarization using Adversarially regularized autoencoder.

• Conditional model is proposed and enhanced performance for review summarization.

摘要

•We proposed a novel summary method by using code vector of autoencoder.•Unsupervised abstractive summarization using Adversarially regularized autoencoder.•Conditional model is proposed and enhanced performance for review summarization.

论文关键词：Text summarization,Review summarization,Sentence generation,Conditional model,Generative adversarial network

论文评审过程：Received 27 September 2018, Revised 6 April 2019, Accepted 7 April 2019, Available online 8 April 2019, Version of Record 13 April 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.04.014