Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/74363
Title: Improving multi-document summarization via text classification
Authors: Cao, Z 
Li, W 
Li, S
Wei, F
Issue Date: 2017
Publisher: AAAI Press
Source: 31st AAAI Conference on Artificial Intelligence, AAAI 2017, 2017, p. 3053-3059 How to cite?
Abstract: Developed so far, multi-document summarization has reached its bottleneck due to the lack of sufficient training data and diverse categories of documents. Text classification just makes up for these deficiencies. In this paper, we propose a novel summarization system called TCSum, which leverages plentiful text classification data to improve the performance of multi-document summarization. TCSum projects documents onto distributed representations which act as a bridge between text classification and summarization. It also utilizes the classification results to produce summaries of different styles. Extensive experiments on DUC generic multidocument summarization datasets show that, TCSum can achieve the state-of-the-art performance without using any hand-crafted features and has the capability to catch the variations of summary styles with respect to different text categories. Copyright
URI: http://hdl.handle.net/10397/74363
Appears in Collections:Conference Paper

Show full item record

SCOPUSTM   
Citations

28
Citations as of May 18, 2020

Page view(s)

65
Last Week
3
Last month
Citations as of May 24, 2020

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.