Identifying the target types of entity-bearing queries can help improveretrieval performance as well as the overall search experience. In this work,we address the problem of automatically detecting the target types of a querywith respect to a type taxonomy. We propose a supervised learning approach witha rich variety of features. Using a purpose-built test collection, we show thatour approach outperforms existing methods by a remarkable margin. This is anextended version of the article published with the same title in theProceedings of SIGIR'17.
展开▼