We investigate using gradient descent methods for learning ranking functions; we propose a simple probabilistic cost function, and we introduce RankNet, an implementation of these ideas using a neural network to model the underlying ranking function. We present test results on toy data and on data from a commercial internet search engine.
%0 Conference Paper
%1 Burges05
%A Burges, Chris
%A Shaked, Tal
%A Renshaw, Erin
%A Lazier, Ari
%A Deeds, Matt
%A Hamilton, Nicole
%A Hullender, Greg
%B ICML '05: Proceedings of the 22nd international conference on Machine learning
%C New York, NY, USA
%D 2005
%I ACM
%K learning ranking
%P 89--96
%R http://doi.acm.org/10.1145/1102351.1102363
%T Learning to rank using gradient descent
%U http://portal.acm.org/citation.cfm?id=1102351.1102363
%X We investigate using gradient descent methods for learning ranking functions; we propose a simple probabilistic cost function, and we introduce RankNet, an implementation of these ideas using a neural network to model the underlying ranking function. We present test results on toy data and on data from a commercial internet search engine.
%@ 1-59593-180-5
@inproceedings{Burges05,
abstract = {We investigate using gradient descent methods for learning ranking functions; we propose a simple probabilistic cost function, and we introduce RankNet, an implementation of these ideas using a neural network to model the underlying ranking function. We present test results on toy data and on data from a commercial internet search engine.},
added-at = {2008-09-23T16:11:08.000+0200},
address = {New York, NY, USA},
author = {Burges, Chris and Shaked, Tal and Renshaw, Erin and Lazier, Ari and Deeds, Matt and Hamilton, Nicole and Hullender, Greg},
biburl = {https://www.bibsonomy.org/bibtex/2a00e5dd434027770eae311854b0bc88a/mkroell},
booktitle = {ICML '05: Proceedings of the 22nd international conference on Machine learning},
description = {Learning to rank using gradient descent},
doi = {http://doi.acm.org/10.1145/1102351.1102363},
interhash = {700415055c8bc48d64de26303b25533c},
intrahash = {a00e5dd434027770eae311854b0bc88a},
isbn = {1-59593-180-5},
keywords = {learning ranking},
location = {Bonn, Germany},
pages = {89--96},
publisher = {ACM},
timestamp = {2008-12-23T14:20:24.000+0100},
title = {Learning to rank using gradient descent},
url = {http://portal.acm.org/citation.cfm?id=1102351.1102363},
year = 2005
}