Information Retrieval
My main focus in information retrieval is currently investigating neural models for ranking models for document retrieval and open-domain question answering. I also work extensively on temporal information retrieval and enrichment of textual knowledge sources like Wikipedia.
While searching for articles published over time, a key preference is to retrieve documents which cover the important aspects from important points in time which is different from standard search behavior. To support such a search strategy, we introduce the notion of a Historical Query Intent to explicitly model a historian’s search task and define an aspect-time diversification problem over news archives. We present novel algorithms and build a search system called HistDiv over 20 years of New York Times, that explicitly models the aspects and important time windows based on a historian’s information seeking behavior.
Publications
[1] Distant supervision in BERT-based Adhoc Document Retrieval.. Koustav Rudra, Avishek Anand. In CIKM 2020 (to appear)..
[2] Modeling Event Importance for Ranking Daily News Events.. Vinay Setty, Abhijit Anand, Arunav Mishra, Avishek Anand. In WSDM 2017..
[3] Fine-Grained Citation Span Detection for References in Wikipedia.. Besnik Fetahu, Katja Markert, Avishek Anand. In EMNLP 2017..
[4] Discovering Entities with Just a Little Help from You.. Jaspreet Singh, Johannes Hoffart, Avishek Anand. In CIKM 2016..
[5] Finding News Citations for Wikipedia.. Besnik Fetahu, Katja Markert, Wolfgang Nejdl, Avishek Anand. In CIKM 2016..
[6] Balancing Novelty and Salience: Adaptive Learning to Rank Entities for Timeline Summarization of High-impact Events.. Tuan Tran, Nattiya Kahnabua, Claudia Niederee, Avishek Anand. In CIKM 2015..
[7] Index Maintenance for Time-Travel Text Search.. Avishek Anand, Srikanta Bedathur, Klaus Berberich, Ralf Schenkel. In SIGIR 2012..