Generative Adversarial Network for Joint Headline and Summary Generation

Abstract

With the ever-increasing amount of electronic documents being generated, it is imperative to provide an intuitive headline and a concise summary of the document to help readers quickly get the gist without going through the all details. While humans have strong abilities to create headlines and generate summaries, the automatic text generation of this research field is still challenging due to the difficult language understanding and complex text synthesis. Moreover, human annotation for machine learning is another matter needed to be addressed. In this paper, we propose a joint model to resolve aforementioned issues simultaneously. To perform unsupervised training to reduce labor cost, we employ a generative adversarial network (GAN) without parallel training data. Considering that the headline and summary have strong relationship, we propose a joint model to learn better representations by including an additional type representation into the GAN. Experiments are conducted on the public dataset, NEWS-ROOM. The experimental results demonstrate that our approach is able to effectively create a reasonable headline as well as a concise summary.

Research on generating text summaries based on improved transformer

“…The model has achieved very significant results. the proposal of the Transformer【12】framework, because it has better parallel computing power and can obtain more features at the same time based on the attention mechanism, the model obtains good results when applied to text abstracts 【13】.Lin et al [14] can obtain reasonable and concise abstracts through joint titles and abstracts through generative adversarial networks, and many researchers have also explored the idea of convergence topics [15][16][17] for abstract generation and achieved ideal scientific results. With the emergence of a series of pre-trained models such as Bert [18][19] pre-trained models have achieved excellent results in the field of natural language processing.…”