Sequence Generative Adversarial Network for Chinese Social Media Text Summarization
- 1 November 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4620-4625
Abstract
Although the sequence-to-sequence models have achieved state-of-the-art performance in many summarization datasets, there are still some problems in the processing of Chinese social media text, such as short sentences, lack of coherence and accuracy. These issues are caused by two factors: the principle of the RNN-based sequence-to-sequence model is maximum likelihood estimation, which will lead to gradient vanishing or exploding when generating long summaries; the text in the Chinese social media is long and noisy, for which it is very difficult to generate high-quality summaries. To solve these issues, we apply a sequence generative adversarial network framework. The framework includes generator and discriminator, in which generator is used to generate summaries and discriminator is used to evaluate generated summaries. The softargmax layer is used as a connection layer to guarantee the co-training of generator and discriminator. Experiments are carried out on Large Scale Chinese Social Media Text Summarization Dataset. The length of the sentence, ROUGE score and artificial score of summary's quality are used to evaluate the generated summaries. The result shows that the sentences in the summaries generated by our model are longer and have higher accuracy.Keywords
This publication has 11 references indexed in Scilit:
- Review on Abstractive Text Summarization Techniques (ATST) for single and multi documents2018
- Diversity-Promoting GAN: A Cross-Entropy Based Generative Adversarial Network for Diversified Text Generation2018
- An Overview of Text SummarizationInternational Journal of Computer Applications, 2017
- Improving Semantic Relevance for Sequence-to-Sequence Learning of Chinese Social Media Text Summarization2017
- An extractive text summarization technique for Bengali document(s) using K-means clustering algorithm2017
- Deep Recurrent Generative Decoder for Abstractive Text Summarization2017
- Long Short-Term Memory-Networks for Machine Reading2016
- Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond2016
- LCSTS: A Large Scale Chinese Short Text Summarization Dataset2015
- A Neural Attention Model for Abstractive Sentence Summarization2015