Yukun Zheng, Yiqun Liu, Zhen Fan, Cheng Luo, Qingyao Ai, Min Zhang and Shaoping Ma
Document ranking is one of the core problems in information retrieval studies. Given a textual query, the goal of document ranking is to find relevant documents with respect to the query in the whole collection. Recently, researchers in the Information Retrieval(IR) community have proposed a number of neural ranking models to improve the performance of document ranking. However, the success of deep neural networks has not been widely observed in adhocretrieval ( Pang, Lan, Guo, Xu, & Cheng, 2017a ). One of the reasons lies in the shortage of
Christina Lioma, Birger Larsen and Peter Ingwersen
general, the last study recording how users specified term dependence was from 2005 ( Jansen, Spink, & Pedersen, 2005 ).
On the contrary, algorithmic approaches to detect and process term dependence have been explored much more in IR, for instance in ad-hocretrieval ( Lioma & van Rijsbergen, 2008 ), patent retrieval ( Jochim, Lioma, & Schütze, 2011 ), domain-specific retrieval on physics academic literature ( Lioma, Kothari, & Schuetze, 2011 ), or more formally using logic ( Lioma, Larsen, Schütze, & Ingwersen, 2010 ). A recent comprehensive overview is given in