[CV in pdf]
I'm currently a 6th year PhD student supervised by Professor W. Bruce Croft at the Center for Intelligent Information Retrieval (CIIR), School of Computer Science, University of Massachusetts Amherst.
I'm interested in both theoretical and practical information retrieval problems. My thesis focuses on search result diversification. In particular, I propose a proportionality-based approach which achieves diversity by optimizing for proportionality in the search results.
The idea of diversification is impractical without the ability to automatically infer the set of topics associated with user queries. I introduce a novel term-based representation for query topics. It makes the task of topic generation simpler and more manageable, thereby improving diversification effectiveness.
I have also done some work related to query reformulation using anchor text as a "pseudo" query log. The idea is that anchor text and the urls that they point to are similar to queries and clicks. As such, anchor text can be a good alternative to query logs for certain applications. Although I only study anchor text, bookmark data is another potential source.
Last but not least, I'm also interested in applying machine learning algorithms to facilitate retrieval. In fact, I develop and maintain RankLib, a java open source library of learning to rank algorithms.
- RankLib - A library of learning to rank algorithms
- V. Dang and W.B. Croft: "Term Level Search Result Diversification". In Proceedings of SIGIR, pp. 603-612, 2013 [pdf]
- V. Dang, M. Bendersky and W.B. Croft: "Two-Stage Learning to Rank for Information Retrieval". In Proceedings of ECIR, pp. 423-434, 2013 [pdf]
- V. Dang, G. Kumaran and A. Troy: "Domain Dependent Query Reformulation for Web Search". In Proceedings of CIKM, pp. 1045-1054, 2012 [pdf]
- V. Dang, X. Xue and W.B. Croft: "Inferring Query Aspects from Reformulations Using Clustering". In Proceedings of CIKM, pp. 2117-2120, 2011 [pdf]
- V. Dang and W.B. Croft: "Diversity by Proportionality: An Election-based Approach to Search Result Diversification". In Proceedings of SIGIR, pp. 65-74, 2012 [pdf]
- V. Dang, M. Bendersky and W.B. Croft: "Learning to Rank Query Reformulations". In Proceedings of SIGIR, pp. 807-808, 2010 [pdf]
- V. Dang and W.B. Croft: "Feature Selection for Document Ranking using Best First Search and Coordinate Ascent". In Proceedings of SIGIR Workshop on Feature Generation and Selection for Information Retrieval, 2010 [pdf]
- V. Dang and W.B. Croft: "Query Reformulation Using Anchor Text". In Proceedings of WSDM, pp. 41-50, 2010 [pdf]
- V. Dang and A. Aizawa: "Multi-class Named Entity Recognition via Bootstrapping with Dependency Tree-based Patterns". In Proceedings of PAKDD, pp. 76-87, 2008 [pdf]