DocumentCode :
3274739
Title :
Using Complex Networks for Language Processing: The Case of Summary Evaluation
Author :
Pardo, Thiago Alexandre Salgueiro ; Antiqueira, Lucas ; Nunes, Maria Das Gracas Volpe ; Oliveira, Osvaldo N., Jr. ; da Fontoura Costa, L.
Author_Institution :
Inst. de Cienc. Mat. e de Comput., Univ. de Sao Paulo, Sao Paulo
Volume :
4
fYear :
2006
fDate :
25-28 June 2006
Firstpage :
2678
Lastpage :
2682
Abstract :
The ability to access embedded knowledge makes complex networks extremely promising for natural language processing, which normally requires deep knowledge representation that is not accessible with first-order statistics. In this paper, we demonstrate that features of complex networks, which have been shown to correlate with text quality, can be used to evaluate summaries. The metrics are the average degree, cluster coefficient, and the extent to which the dynamics of network growth deviates from a straight line. They were found to be much smaller for the high-quality, manual summaries, and increased for automatic summaries, thus pointing to a loss of quality, as expected. We also discuss the comparative performance of automatic summarizers.
Keywords :
complex networks; knowledge representation; natural language processing; complex networks; knowledge representation; natural language processing; summary evaluation; Complex networks; Computer networks; Computer science; Embedded computing; IP networks; Knowledge representation; Natural language processing; Natural languages; Social network services; Statistics;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Communications, Circuits and Systems Proceedings, 2006 International Conference on
Conference_Location :
Guilin
Print_ISBN :
0-7803-9584-0
Electronic_ISBN :
0-7803-9585-9
Type :
conf
DOI :
10.1109/ICCCAS.2006.285222
Filename :
4064469
Link To Document :
بازگشت