Automatic Text Summarization Using Deep Reinforcement Learning and Beyond


  • Gang Sun Fuyang Normal University
  • Zhongxin Wang Fuyang Normal University
  • Jia Zhao Fuyang Normal University



AI, DRL, ROUGE metric, text summarization


In the era of big data, information overload problems are becoming increasingly prominent. It is challenging
for machines to understand, compress and filter massive text information through the use of artificial intelligence
technology. The emergence of automatic text summarization mainly aims at solving the problem of
information overload, and it can be divided into two types: extractive and abstractive. The former finds some
key sentences or phrases from the original text and combines them into a summarization; the latter needs a
computer to understand the content of the original text and then uses the readable language for the human to
summarize the key information of the original text. This paper presents a two-stage optimization method for
automatic text summarization that combines abstractive summarization and extractive summarization. First,
a sequence-to-sequence model with the attention mechanism is trained as a baseline model to generate initial
summarization. Second, it is updated and optimized directly on the ROUGE metric by using deep reinforcement
learning (DRL). Experimental results show that compared with the baseline model, Rouge-1, Rouge-2,
and Rouge-L have been increased on the LCSTS dataset and CNN/DailyMail dataset.