How to Train Your Agent to Read and Write

Authors

  • Li Liu South China University of Technology Pazhou Laboratory
  • Mengge He South China University of Technology
  • Guanghui Xu South China University of Technology
  • Mingkui Tan South China University of Technology Key Laboratory of Big Data and Intelligent Robot, Ministry of Education
  • Qi Wu University of Adelaide

Keywords:

Generation

Abstract

Reading and writing research papers is one of the most privileged abilities that a qualified researcher should master. However, it is difficult for new researchers (e.g., students) to fully grasp this ability. It would be fascinating if we could train an intelligent agent to help people read and summarize papers, and perhaps even discover and exploit the potential knowledge clues to write novel papers. Although there have been existing works focusing on summarizing (i.e., reading) the knowledge in a given text or generating (i.e., writing) a text based on the given knowledge, the ability of simultaneously reading and writing is still under development. Typically, this requires an agent to fully understand the knowledge from the given text materials and generate correct and fluent novel paragraphs, which is very challenging in practice. In this paper, we propose a Deep ReAder-Writer (DRAW) network, which consists of a Reader that can extract knowledge graphs (KGs) from input paragraphs and discover potential knowledge, a graph-to-text Writer that generates a novel paragraph, and a Reviewer that reviews the generated paragraph from three different aspects. Extensive experiments show that our DRAW network outperforms considered baselines and several state-of-the-art methods on AGENDA and M-AGENDA datasets. Our code and supplementary are released at https://github.com/menggehe/DRAW.

Downloads

Published

2021-05-18

How to Cite

Liu, L., He, M., Xu, G., Tan, M., & Wu, Q. (2021). How to Train Your Agent to Read and Write. Proceedings of the AAAI Conference on Artificial Intelligence, 35(15), 13397-13405. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17581

Issue

Section

AAAI Technical Track on Speech and Natural Language Processing II