Paper Info
Title
Be Relevant, Non-Redundant, And Timely: Deep Reinforcement Learning For Real-Time Event Summarization
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.
Year
Venue
DocType
2020
national conference on artificial intelligence
Conference
Volume
ISSN
Citations 
34
2159-5399
0
PageRank 
References 
Authors
0.34
0
6
Name
Order
Citations
PageRank
Min Yang17720.41
Chengming Li26310.60
Fei Sun300.34
Zhou Zhao477390.87
Ying Shen555.49
Chenglin Wu601.01