Be Relevant, Non-Redundant, and Timely: Deep Reinforcement Learning for Real-Time Event Summarization

Authors

  • Min Yang Chinese Academy of Sciences
  • Chengming Li Chinese Academy of Sciences
  • Fei Sun Alibaba Group
  • Zhou Zhao Zhejiang University
  • Ying Shen Peking University Shenzhen Graduate School
  • Chenglin Wu Deep Wisdom

DOI:

https://doi.org/10.1609/aaai.v34i05.6483

Abstract

Real-time event summarization is an essential task in natural language processing and information retrieval areas. Despite the progress of previous work, generating relevant, non-redundant, and timely event summaries remains challenging in practice. In this paper, we propose a Deep Reinforcement learning framework for real-time Event Summarization (DRES), which shows promising performance for resolving all three challenges (i.e., relevance, non-redundancy, timeliness) in a unified framework. Specifically, we (i) devise a hierarchical cross-attention network with intra- and inter-document attentions to integrate important semantic features within and between the query and input document for better text matching. In addition, relevance prediction is leveraged as an auxiliary task to strengthen the document modeling and help to extract relevant documents; (ii) propose a multi-topic dynamic memory network to capture the sequential patterns of different topics belonging to the event of interest and temporally memorize the input facts from the evolving document stream, avoiding extracting redundant information at each time step; (iii) consider both historical dependencies and future uncertainty of the document stream for generating relevant and timely summaries by exploiting the reinforcement learning technique. Experimental results on two real-world datasets have demonstrated the advantages of DRES model with significant improvement in generating relevant, non-redundant, and timely event summaries against the state-of-the-arts.

Downloads

Published

2020-04-03

How to Cite

Yang, M., Li, C., Sun, F., Zhao, Z., Shen, Y., & Wu, C. (2020). Be Relevant, Non-Redundant, and Timely: Deep Reinforcement Learning for Real-Time Event Summarization. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05), 9410-9417. https://doi.org/10.1609/aaai.v34i05.6483

Issue

Section

AAAI Technical Track: Natural Language Processing