Recent advances in <i>click model</i> have positioned it as an effective approach to estimate document relevance based on user behavior in web search. Yet, few works have been conducted to explore the use of click model to help web search ranking. In this paper, we focus on learning a ranking function by taking the results from a click model into account. Thus, besides the editorial relevance data arising from the explicit manually labeled search result by experts, we also have the estimated relevance data that is automatically inferred from click models based on user search behavior. We carry out extensive experiments on large-scale commercial datasets and demonstrate the effectiveness of the proposed methods.
%0 Conference Paper
%1 wang2010explore
%A Wang, Dong
%A Chen, Weizhu
%A Wang, Gang
%A Zhang, Yuchen
%A Hu, Botao
%B Proceedings of the 19th ACM international conference on Information and knowledge management
%C New York, NY, USA
%D 2010
%I ACM
%K clickdata clickthrough implicit-feedback learning-to-rank model ranking search
%P 1417--1420
%R 10.1145/1871437.1871636
%T Explore click models for search ranking
%U http://doi.acm.org/10.1145/1871437.1871636
%X Recent advances in <i>click model</i> have positioned it as an effective approach to estimate document relevance based on user behavior in web search. Yet, few works have been conducted to explore the use of click model to help web search ranking. In this paper, we focus on learning a ranking function by taking the results from a click model into account. Thus, besides the editorial relevance data arising from the explicit manually labeled search result by experts, we also have the estimated relevance data that is automatically inferred from click models based on user search behavior. We carry out extensive experiments on large-scale commercial datasets and demonstrate the effectiveness of the proposed methods.
%@ 978-1-4503-0099-5
@inproceedings{wang2010explore,
abstract = {Recent advances in <i>click model</i> have positioned it as an effective approach to estimate document relevance based on user behavior in web search. Yet, few works have been conducted to explore the use of click model to help web search ranking. In this paper, we focus on learning a ranking function by taking the results from a click model into account. Thus, besides the editorial relevance data arising from the explicit manually labeled search result by experts, we also have the estimated relevance data that is automatically inferred from click models based on user search behavior. We carry out extensive experiments on large-scale commercial datasets and demonstrate the effectiveness of the proposed methods.},
acmid = {1871636},
added-at = {2011-07-29T14:42:43.000+0200},
address = {New York, NY, USA},
author = {Wang, Dong and Chen, Weizhu and Wang, Gang and Zhang, Yuchen and Hu, Botao},
biburl = {https://www.bibsonomy.org/bibtex/25642b4ab6ef449fa7a84b0c4901e8e58/beate},
booktitle = {Proceedings of the 19th ACM international conference on Information and knowledge management},
description = {Explore click models for search ranking},
doi = {10.1145/1871437.1871636},
interhash = {691bd4d774190881fb0f1dda05fda8dd},
intrahash = {5642b4ab6ef449fa7a84b0c4901e8e58},
isbn = {978-1-4503-0099-5},
keywords = {clickdata clickthrough implicit-feedback learning-to-rank model ranking search},
location = {Toronto, ON, Canada},
numpages = {4},
pages = {1417--1420},
publisher = {ACM},
series = {CIKM '10},
timestamp = {2011-07-29T14:42:43.000+0200},
title = {Explore click models for search ranking},
url = {http://doi.acm.org/10.1145/1871437.1871636},
year = 2010
}