A Study on Automatic Extraction of Core Sentences from Document using Word Cooccurrence Graph


The Transactions of the Korea Information Processing Society (1994 ~ 2000), Vol. 7, No. 11, pp. 3427-3437, Nov. 2000
10.3745/KIPSTE.2000.7.11.3427,   PDF Download:

Abstract

In this paper, we propose a method of core sentences extraction using word co-occurrence graph in order to summarize a document. For automatic extraction of core sentences, we construct a mean cluster from word co-occurrence graph, and find insistence which corresponds a purpose of author. And then we extract keywords by using relationship between mean cluster and insistence. Finally, core sentences are selected based on keywords and instances. The results are evaluated by comparing with manual extraction, and show that the extraction performance is improved about 10%.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
R. Je, K. R. Han, S. W. Sohn, K. W. Rim, "A Study on Automatic Extraction of Core Sentences from Document using Word Cooccurrence Graph," The Transactions of the Korea Information Processing Society (1994 ~ 2000), vol. 7, no. 11, pp. 3427-3437, 2000. DOI: 10.3745/KIPSTE.2000.7.11.3427.

[ACM Style]
Ryu Je, Kwang Rok Han, Seok Won Sohn, and Kee Wook Rim. 2000. A Study on Automatic Extraction of Core Sentences from Document using Word Cooccurrence Graph. The Transactions of the Korea Information Processing Society (1994 ~ 2000), 7, 11, (2000), 3427-3437. DOI: 10.3745/KIPSTE.2000.7.11.3427.