Y. Yue, and T. Joachims. Proceedings of the 25th international conference on Machine learning, page 1224--1231. New York, NY, USA, ACM, (2008)
DOI: 10.1145/1390156.1390310
Abstract
In many retrieval tasks, one important goal involves retrieving a diverse set of results (e.g., documents covering a wide range of topics for a search query). First of all, this reduces redundancy, effectively showing more information with the presented results. Secondly, queries are often ambiguous at some level. For example, the query "Jaguar" can refer to many different topics (such as the car or feline). A set of documents with high topic diversity ensures that fewer users abandon the query because no results are relevant to them. Unlike existing approaches to learning retrieval functions, we present a method that explicitly trains to diversify results. In particular, we formulate the learning problem of predicting diverse subsets and derive a training method based on structural SVMs.
%0 Conference Paper
%1 Yue:2008:PDS:1390156.1390310
%A Yue, Yisong
%A Joachims, Thorsten
%B Proceedings of the 25th international conference on Machine learning
%C New York, NY, USA
%D 2008
%I ACM
%K thema:playlistpredictionviametricembedding
%P 1224--1231
%R 10.1145/1390156.1390310
%T Predicting diverse subsets using structural SVMs
%U http://doi.acm.org/10.1145/1390156.1390310
%X In many retrieval tasks, one important goal involves retrieving a diverse set of results (e.g., documents covering a wide range of topics for a search query). First of all, this reduces redundancy, effectively showing more information with the presented results. Secondly, queries are often ambiguous at some level. For example, the query "Jaguar" can refer to many different topics (such as the car or feline). A set of documents with high topic diversity ensures that fewer users abandon the query because no results are relevant to them. Unlike existing approaches to learning retrieval functions, we present a method that explicitly trains to diversify results. In particular, we formulate the learning problem of predicting diverse subsets and derive a training method based on structural SVMs.
%@ 978-1-60558-205-4
@inproceedings{Yue:2008:PDS:1390156.1390310,
abstract = {In many retrieval tasks, one important goal involves retrieving a diverse set of results (e.g., documents covering a wide range of topics for a search query). First of all, this reduces redundancy, effectively showing more information with the presented results. Secondly, queries are often ambiguous at some level. For example, the query "Jaguar" can refer to many different topics (such as the car or feline). A set of documents with high topic diversity ensures that fewer users abandon the query because no results are relevant to them. Unlike existing approaches to learning retrieval functions, we present a method that explicitly trains to diversify results. In particular, we formulate the learning problem of predicting diverse subsets and derive a training method based on structural SVMs.},
acmid = {1390310},
added-at = {2013-11-08T17:22:18.000+0100},
address = {New York, NY, USA},
author = {Yue, Yisong and Joachims, Thorsten},
biburl = {https://www.bibsonomy.org/bibtex/2cfdcc4d2b416b2155358e4fe2ebebe75/florian.pf},
booktitle = {Proceedings of the 25th international conference on Machine learning},
description = {Predicting diverse subsets using structural SVMs},
doi = {10.1145/1390156.1390310},
interhash = {6f59947cc79cf7bebafbf0c7f1d2196c},
intrahash = {cfdcc4d2b416b2155358e4fe2ebebe75},
isbn = {978-1-60558-205-4},
keywords = {thema:playlistpredictionviametricembedding},
location = {Helsinki, Finland},
numpages = {8},
pages = {1224--1231},
publisher = {ACM},
series = {ICML '08},
timestamp = {2013-11-08T17:22:18.000+0100},
title = {Predicting diverse subsets using structural SVMs},
url = {http://doi.acm.org/10.1145/1390156.1390310},
year = 2008
}