Difference between revisions of "Text Summarization Using Wikipedia"

From Wikipedia Quality
Jump to: navigation, search
(+ wikilinks)
(infobox)
Line 1: Line 1:
 +
{{Infobox work
 +
| title = Text Summarization Using Wikipedia
 +
| date = 2014
 +
| authors = [[Yogesh Sankarasubramaniam]]<br />[[Krishnan Ramanathan]]<br />[[Subhankar Ghosh]]
 +
| doi = 10.1016/j.ipm.2014.02.001
 +
| link = http://www.sciencedirect.com/science/article/pii/S0306457314000119
 +
}}
 
'''Text Summarization Using Wikipedia''' - scientific work related to [[Wikipedia quality]] published in 2014, written by [[Yogesh Sankarasubramaniam]], [[Krishnan Ramanathan]] and [[Subhankar Ghosh]].
 
'''Text Summarization Using Wikipedia''' - scientific work related to [[Wikipedia quality]] published in 2014, written by [[Yogesh Sankarasubramaniam]], [[Krishnan Ramanathan]] and [[Subhankar Ghosh]].
  
 
== Overview ==
 
== Overview ==
 
Abstract Automatic text summarization has been an active field of research for many years. Several approaches have been proposed, ranging from simple position and word-frequency methods, to learning and graph based algorithms. The advent of human-generated knowledge bases like [[Wikipedia]] offer a further possibility in text summarization – they can be used to understand the input text in terms of salient concepts from the knowledge base. In this paper, authors study a novel approach that leverages Wikipedia in conjunction with graph-based ranking. Authors approach is to first construct a bipartite sentence–concept graph, and then rank the input sentences using iterative updates on this graph. Authors consider several models for the bipartite graph, and derive convergence properties under each model. Then, authors take up personalized and query-focused summarization, where the sentence ranks additionally depend on user interests and queries, respectively. Finally, authors present a Wikipedia-based multi-document summarization algorithm. An important feature of the proposed algorithms is that they enable real-time incremental summarization – users can first view an initial summary, and then request additional content if interested. Authors evaluate the performance of proposed summarizer using the ROUGE metric, and the results show that leveraging Wikipedia can significantly improve summary quality. Authors also present results from a user study, which suggests that using incremental summarization can help in better understanding news articles.
 
Abstract Automatic text summarization has been an active field of research for many years. Several approaches have been proposed, ranging from simple position and word-frequency methods, to learning and graph based algorithms. The advent of human-generated knowledge bases like [[Wikipedia]] offer a further possibility in text summarization – they can be used to understand the input text in terms of salient concepts from the knowledge base. In this paper, authors study a novel approach that leverages Wikipedia in conjunction with graph-based ranking. Authors approach is to first construct a bipartite sentence–concept graph, and then rank the input sentences using iterative updates on this graph. Authors consider several models for the bipartite graph, and derive convergence properties under each model. Then, authors take up personalized and query-focused summarization, where the sentence ranks additionally depend on user interests and queries, respectively. Finally, authors present a Wikipedia-based multi-document summarization algorithm. An important feature of the proposed algorithms is that they enable real-time incremental summarization – users can first view an initial summary, and then request additional content if interested. Authors evaluate the performance of proposed summarizer using the ROUGE metric, and the results show that leveraging Wikipedia can significantly improve summary quality. Authors also present results from a user study, which suggests that using incremental summarization can help in better understanding news articles.

Revision as of 10:31, 14 December 2019


Text Summarization Using Wikipedia
Authors
Yogesh Sankarasubramaniam
Krishnan Ramanathan
Subhankar Ghosh
Publication date
2014
DOI
10.1016/j.ipm.2014.02.001
Links
Original

Text Summarization Using Wikipedia - scientific work related to Wikipedia quality published in 2014, written by Yogesh Sankarasubramaniam, Krishnan Ramanathan and Subhankar Ghosh.

Overview

Abstract Automatic text summarization has been an active field of research for many years. Several approaches have been proposed, ranging from simple position and word-frequency methods, to learning and graph based algorithms. The advent of human-generated knowledge bases like Wikipedia offer a further possibility in text summarization – they can be used to understand the input text in terms of salient concepts from the knowledge base. In this paper, authors study a novel approach that leverages Wikipedia in conjunction with graph-based ranking. Authors approach is to first construct a bipartite sentence–concept graph, and then rank the input sentences using iterative updates on this graph. Authors consider several models for the bipartite graph, and derive convergence properties under each model. Then, authors take up personalized and query-focused summarization, where the sentence ranks additionally depend on user interests and queries, respectively. Finally, authors present a Wikipedia-based multi-document summarization algorithm. An important feature of the proposed algorithms is that they enable real-time incremental summarization – users can first view an initial summary, and then request additional content if interested. Authors evaluate the performance of proposed summarizer using the ROUGE metric, and the results show that leveraging Wikipedia can significantly improve summary quality. Authors also present results from a user study, which suggests that using incremental summarization can help in better understanding news articles.