TY - GEN
T1 - Cluster-based focused retrieval
AU - Sheetrit, Eilon
AU - Kurland, Oren
N1 - Publisher Copyright:
© 2019 Association for Computing Machinery.
PY - 2019/11/3
Y1 - 2019/11/3
N2 - The focused retrieval task is to rank documents' passages by their presumed relevance to a query. Inspired by work on cluster-based document retrieval, we present a novel cluster-based focused retrieval method. The method is based on ranking clusters of similar passages using a learning-to-rank approach and transforming the cluster ranking to passage ranking. Empirical evaluation demonstrates the clear merits of the method.
AB - The focused retrieval task is to rank documents' passages by their presumed relevance to a query. Inspired by work on cluster-based document retrieval, we present a novel cluster-based focused retrieval method. The method is based on ranking clusters of similar passages using a learning-to-rank approach and transforming the cluster ranking to passage ranking. Empirical evaluation demonstrates the clear merits of the method.
UR - http://www.scopus.com/inward/record.url?scp=85075443328&partnerID=8YFLogxK
U2 - 10.1145/3357384.3358087
DO - 10.1145/3357384.3358087
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85075443328
T3 - International Conference on Information and Knowledge Management, Proceedings
SP - 2305
EP - 2308
BT - CIKM 2019 - Proceedings of the 28th ACM International Conference on Information and Knowledge Management
T2 - 28th ACM International Conference on Information and Knowledge Management, CIKM 2019
Y2 - 3 November 2019 through 7 November 2019
ER -