Adapting Static and Contextual Representations for Policy Gradient-Based Summarization

Considering the ever-growing volume of electronic documents made available in our daily lives, the need for an efficient tool to capture their gist increases as well. Automatic text summarization, which is a process of shortening long text and extracting valuable information, has been of great interest for decades. Due to the difficulties of semantic understanding and the requirement of large training data, the development of this research field is still challenging and worth investigating. In this paper, we propose an automated text summarization approach with the adaptation of static and contextual representations based on an extractive approach to address the research gaps. To better obtain the semantic expression of the given text, we explore the combination of static embeddings from GloVe (Global Vectors) and the contextual embeddings from BERT (Bidirectional Encoder Representations from Transformer) and GPT (Generative Pre-trained Transformer) based models. In order to reduce human annotation costs, we employ policy gradient reinforcement learning to perform unsupervised training. We conduct empirical studies on the public dataset, Gigaword. The experimental results show that our approach achieves promising performance and is competitive with various state-of-the-art approaches.