Prof. Michael Rung-Tsong Lyu, Prof. Irwin King and Dr. Hongbo Deng won the Vannevar Bush Best Paper Award at JCDL 2012 (6/2012)
Congratulations to Prof. Michael Rung-Tsong Lyu, Prof. Irwin King, their graduated Ph.D student Dr. Hongbo Deng and their co-author Prof. Jiawei Han! They have been awarded the Vannevar Bush Best Paper Award for their paper, titled "Modeling and Exploiting Heterogeneous Bibliographic Networks for Expertise Ranking", which was presented at the 12th ACM/IEEE-CS Joint Conference on Digital Libraries (JCDL) in Washington DC., USA, June 10-14 2012. JCDL is the most influential international conference on digital libraries. A total of 202 papers were received this year for the competition. This paper won the only Vannevar Bush Best Paper Award.
The paper was awarded for its contributions to expertise ranking. Recently expertise retrieval has received increasing interests in both academia and industry. Finding experts with demonstrated expertise for a given query is a nontrivial task especially from a large- scale Web 2.0 system. The paper proposes a joint regularization framework to enhance expertise retrieval by exploiting and modeling heterogeneous networks. To exploit these heterogeneous networks efficiently, the paper investigates and formulates three hypotheses to capture unique characteristics of different graphs, including directed and undirected graphs, and then mathematically models those hypotheses by developing regularization constraints on top of document-centric model. The experimental results show that the proposed approach can achieve significantly better results than the state-of-the-art models.
Ref link: http://jcdl.org/awards.php
Recently expertise retrieval has received increasing interests in both academia and industry. Finding experts with demonstrated expertise for a given query is a nontrivial task especially from a large-scale Web 2.0 systems, such as question answering and bibliography data, where users are actively publishing useful content online, interacting with each other, and forming social networks in various ways, leading to heterogeneous networks in addition to the large amounts of textual content information. Many approaches have been proposed and shown to be useful for expertise ranking. However, most of these methods only consider the textual documents while ignoring heterogeneous network structures or can merely integrate with one additional kind of information. None of them can fully exploit the characteristics of heterogeneous networks. In this paper, we propose a joint regularization framework to enhance expertise retrieval by modeling heterogeneous networks as regularization constraints on top of document-centric model. We argue that multi-typed linking edges reveal valuable information which should be treated differently. Motivated by this intuition, we formulate three hypotheses to capture unique characteristics for different graphs, and mathematically model those hypotheses jointly with the document and other information. To illustrate our methodology, we apply the framework to expert finding applications using a bibliography dataset with 1.1 million papers and 0.7 million authors. The experimental results show that our proposed approach can achieve significantly better results than the baseline and other enhanced models.