Learning to rank user intent
Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review
Standard
Proceedings of the 20th ACM international conference on Information and knowledge management . Association for Computing Machinery, Inc, 2011. p. 195-200.
Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - CHAP
T1 - Learning to rank user intent
AU - Giannopoulos, Giorgos
AU - Brefeld, Ulf
AU - Dalamagas, Theodore
AU - Sellis, Timos
PY - 2011
Y1 - 2011
N2 - Personalized retrieval models aim at capturing user interests to provide personalized results that are tailored to the respective information needs. User interests are however widely spread, subject to change, and cannot always be captured well, thus rendering the deployment of personalized models challenging. We take a different approach and study ranking models for user intent. We exploit user feedback in terms of click data to cluster ranking models for historic queries according to user behavior and intent. Each cluster is finally represented by a single ranking model that captures the contained search interests expressed by users. Once new queries are issued, these are mapped to the clustering and the retrieval process diversifies possible intents by combining relevant ranking functions. Empirical evidence shows that our approach significantly outperforms baseline approaches on a large corporate query log.
AB - Personalized retrieval models aim at capturing user interests to provide personalized results that are tailored to the respective information needs. User interests are however widely spread, subject to change, and cannot always be captured well, thus rendering the deployment of personalized models challenging. We take a different approach and study ranking models for user intent. We exploit user feedback in terms of click data to cluster ranking models for historic queries according to user behavior and intent. Each cluster is finally represented by a single ranking model that captures the contained search interests expressed by users. Once new queries are issued, these are mapped to the clustering and the retrieval process diversifies possible intents by combining relevant ranking functions. Empirical evidence shows that our approach significantly outperforms baseline approaches on a large corporate query log.
KW - Informatics
KW - Clickthrough data
KW - clustering
KW - ranking
KW - Relevance judgement
KW - Search behavior
KW - Business informatics
UR - http://www.scopus.com/inward/record.url?scp=83055168233&partnerID=8YFLogxK
U2 - 10.1145/2063576.2063609
DO - 10.1145/2063576.2063609
M3 - Article in conference proceedings
AN - SCOPUS:83055168233
SN - 978-1-4503-0717-8
SP - 195
EP - 200
BT - Proceedings of the 20th ACM international conference on Information and knowledge management
PB - Association for Computing Machinery, Inc
T2 - 20th ACM Conference on Information and Knowledge Management - CIKM '11
Y2 - 24 October 2011 through 28 October 2011
ER -