DocumentCode :
63243
Title :
Summarization Based on Task-Oriented Discourse Parsing
Author :
Xun Wang ; Yoshida, Yasuhisa ; Hirao, Tsutomu ; Nagata, Masaaki ; Sudoh, Katsuhito
Author_Institution :
NTT Commun. Sci. Labs., Kyoto, Japan
Volume :
23
Issue :
8
fYear :
2015
fDate :
Aug. 2015
Firstpage :
1358
Lastpage :
1367
Abstract :
Previous research demonstrates that discourse relations can help generate high-quality summaries. Existing studies usually adopt existing discourse parsers directly with no modifications, hence cannot take full advantage of discourse parsing. This paper describes a new single document summarization system. In contrast to previous work, we train a discourse parser specially for summarization by using summaries. The training data are dynamically changed during the training phase to enable the parser to grab the text units that are important for summaries. A special tree-based summary extraction algorithm is designed to work with the new parser. The proposed system enables us to combine discourse parsing and summarization in a unified scheme. Experiments on both the RST-DT and DUC2001 datasets show the effectiveness of the proposed method.
Keywords :
document handling; feature extraction; grammars; trees (mathematics); DUC2001 datasets; RST-DT; discourse parser; single document summarization system; task-oriented discourse parsing; training data; tree-based summary extraction algorithm; Algorithm design and analysis; Gold; Heuristic algorithms; IEEE transactions; Standards; Training; Training data; Discourse parsing; discourse relations; summarization;
fLanguage :
English
Journal_Title :
Audio, Speech, and Language Processing, IEEE/ACM Transactions on
Publisher :
ieee
ISSN :
2329-9290
Type :
jour
DOI :
10.1109/TASLP.2015.2432573
Filename :
7106466
Link To Document :
بازگشت