Paper Info
Title
Cumulative citation recommendation: classification vs. ranking
Abstract
Cumulative citation recommendation refers to the task of filtering a time-ordered corpus for documents that are highly relevant to a predefined set of entities. This task has been introduced at the TREC Knowledge Base Acceleration track in 2012, where two main families of approaches emerged: classification and ranking. In this paper we perform an experimental comparison of these two strategies using supervised learning with a rich feature set. Our main finding is that ranking outperforms classification on all evaluation settings and metrics. Our analysis also reveals that a ranking-based approach has more potential for future improvements.
Year
DOI
Venue
2013
10.1145/2484028.2484151
SIGIR
Keywords
Field
DocType
trec knowledge base acceleration,experimental comparison,future improvement,rich feature set,ranking-based approach,predefined set,main family,main finding,evaluation setting,cumulative citation recommendation
Knowledge base acceleration,Data mining,Information retrieval,Ranking,Ranking SVM,Computer science,Citation,Filter (signal processing),Supervised learning,Feature set
Conference
Citations 
PageRank 
References 
21
1.26
15
Authors
2
Name
Order
Citations
PageRank
Krisztian Balog11797113.68
Heri Ramampiaro215420.46