Target Type Identification for Entity-Bearing Queries
This work addresses query understanding in search engines, but it is incremental as it extends a previous publication.
The paper tackled the problem of automatically detecting target types for entity-bearing queries to improve retrieval performance, and their supervised learning approach outperformed existing methods by a remarkable margin.
Identifying the target types of entity-bearing queries can help improve retrieval performance as well as the overall search experience. In this work, we address the problem of automatically detecting the target types of a query with respect to a type taxonomy. We propose a supervised learning approach with a rich variety of features. Using a purpose-built test collection, we show that our approach outperforms existing methods by a remarkable margin. This is an extended version of the article published with the same title in the Proceedings of SIGIR'17.