Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/8733
Title: iRANK : a rank-learn-combine framework for unsupervised ensemble ranking
Authors: Wei, F
Li, W 
Liu, S
Issue Date: 2010
Publisher: Wiley-Blackwell
Source: Journal of the American society for information science and technology, 2010, v. 61, no. 6, p. 1232-1243 How to cite?
Journal: Journal of the American Society for Information Science and Technology 
Abstract: The authors address the problem of unsupervised ensemble ranking. Traditional approaches either combine multiple ranking criteria into a unified representation to obtain an overall ranking score orto utilize certain rank fusion or aggregation techniques to combine the ranking results. Beyond the aforementioned "combine-thenrank" and "rank-then-combine" approaches, the authors propose a novel "rank-learn-combine" ranking framework, called Interactive Ranking (iRANK), which allows two base rankers to "teach" each other before combination during the ranking process by providing their own ranking results as feedback to the others to boost the ranking performance. This mutual ranking refinement process continues until the two base rankers cannot learn from each other any more. The overall performance is improved by the enhancement of the base rankers through the mutual learning mechanism. The authors further design two ranking refinement strategies to efficiently and effectively use the feedback based on reasonable assumptions and rational analysis. Although iRANK is applicable to many applications, as a case study, they apply this framework to the sentence ranking problem in query-focused summarization and evaluate its effectiveness on the DUC 2005 and 2006 data sets. The results are encouraging with consistent and promising improvements.
URI: http://hdl.handle.net/10397/8733
DOI: 10.1002/asi.21296
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

16
Last Week
0
Last month
0
Citations as of Jan 24, 2017

WEB OF SCIENCETM
Citations

12
Last Week
0
Last month
1
Citations as of Jan 21, 2017

Page view(s)

16
Last Week
1
Last month
Checked on Jan 22, 2017

Google ScholarTM

Check

Altmetric



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