A regression framework for learning ranking functions using relative relevance judgments
Z. Zheng, K. Chen, G. Sun, и H. Zha. Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval, стр. 287--294. New York, NY, USA, ACM, (2007)
DOI: 10.1145/1277741.1277792
Аннотация
Effective ranking functions are an essential part of commercial search engines. We focus on developing a regression framework for learning ranking functions for improving relevance of search engines serving diverse streams of user queries. We explore supervised learning methodology from machine learning, and we distinguish two types of relevance judgments used as the training data: 1) absolute relevance judgments arising from explicit labeling of search results; and 2) relative relevance judgments extracted from user click throughs of search results or converted from the absolute relevance judgments. We propose a novel optimization framework emphasizing the use of relative relevance judgments. The main contribution is the development of an algorithm based on regression that can be applied to objective functions involving preference data, i.e., data indicating that a document is more relevant than another with respect to a query. Experimental results are carried out using data sets obtained from a commercial search engine. Our results show significant improvements of our proposed methods over some existing methods.
Описание
A regression framework for learning ranking functions using relative relevance judgments
%0 Conference Paper
%1 zheng2007regression
%A Zheng, Zhaohui
%A Chen, Keke
%A Sun, Gordon
%A Zha, Hongyuan
%B Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval
%C New York, NY, USA
%D 2007
%I ACM
%K implicit-feedback learning-to-rank pairwise-approach regression social-search
%P 287--294
%R 10.1145/1277741.1277792
%T A regression framework for learning ranking functions using relative relevance judgments
%U http://doi.acm.org/10.1145/1277741.1277792
%X Effective ranking functions are an essential part of commercial search engines. We focus on developing a regression framework for learning ranking functions for improving relevance of search engines serving diverse streams of user queries. We explore supervised learning methodology from machine learning, and we distinguish two types of relevance judgments used as the training data: 1) absolute relevance judgments arising from explicit labeling of search results; and 2) relative relevance judgments extracted from user click throughs of search results or converted from the absolute relevance judgments. We propose a novel optimization framework emphasizing the use of relative relevance judgments. The main contribution is the development of an algorithm based on regression that can be applied to objective functions involving preference data, i.e., data indicating that a document is more relevant than another with respect to a query. Experimental results are carried out using data sets obtained from a commercial search engine. Our results show significant improvements of our proposed methods over some existing methods.
%@ 978-1-59593-597-7
@inproceedings{zheng2007regression,
abstract = {Effective ranking functions are an essential part of commercial search engines. We focus on developing a regression framework for learning ranking functions for improving relevance of search engines serving diverse streams of user queries. We explore supervised learning methodology from machine learning, and we distinguish two types of relevance judgments used as the training data: 1) absolute relevance judgments arising from explicit labeling of search results; and 2) relative relevance judgments extracted from user click throughs of search results or converted from the absolute relevance judgments. We propose a novel optimization framework emphasizing the use of relative relevance judgments. The main contribution is the development of an algorithm based on regression that can be applied to objective functions involving preference data, i.e., data indicating that a document is more relevant than another with respect to a query. Experimental results are carried out using data sets obtained from a commercial search engine. Our results show significant improvements of our proposed methods over some existing methods.},
acmid = {1277792},
added-at = {2011-07-26T20:00:25.000+0200},
address = {New York, NY, USA},
author = {Zheng, Zhaohui and Chen, Keke and Sun, Gordon and Zha, Hongyuan},
biburl = {https://www.bibsonomy.org/bibtex/2504941bbbe0c0bc3204e7db9b1516d04/beate},
booktitle = {Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval},
description = {A regression framework for learning ranking functions using relative relevance judgments},
doi = {10.1145/1277741.1277792},
interhash = {029a5360fe03061ca3ed877acfadb81e},
intrahash = {504941bbbe0c0bc3204e7db9b1516d04},
isbn = {978-1-59593-597-7},
keywords = {implicit-feedback learning-to-rank pairwise-approach regression social-search},
location = {Amsterdam, The Netherlands},
numpages = {8},
pages = {287--294},
publisher = {ACM},
series = {SIGIR '07},
timestamp = {2011-07-26T20:00:25.000+0200},
title = {A regression framework for learning ranking functions using relative relevance judgments},
url = {http://doi.acm.org/10.1145/1277741.1277792},
year = 2007
}