Unsupervised Rank Aggregation with Domain-Specific Expertise
Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence. Pages 1101-1105.
Abstract
Consider the setting where a panel of judges is repeatedly asked to (partially) rank sets of objects according to given criteria, and assume that the judges' expertise depends on the objects' domain. Learning to aggregate their rankings with the goal of producing a better joint ranking is a fundamental problem in many areas of Information Retrieval and Natural Language Processing, amongst others. However, supervised ranking data is generally difficult to obtain, especially if coming from multiple domains. Therefore, we propose a framework for learning to aggregate votes of constituent rankers with domain specific expertise without supervision. We apply the learning framework to the settings of aggregating full rankings and aggregating top-k lists, demonstrating significant improvements over a domain-agnostic baseline in both cases.Alexandre Klementiev, Dan Roth, Kevin Small, Ivan Titov
@inproceedings{ijcai2009p186,
title = {Unsupervised Rank Aggregation with Domain-Specific Expertise},
author = {Klementiev, Alexandre and Roth, Dan and Small, Kevin and Titov, Ivan},
booktitle = {Proceedings of the Twenty-First International Joint Conference on
Artificial Intelligence, {IJCAI-09}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Hiroaki Kitano},
pages = {1101--1105},
year = {2009},
url = {https://ijcai.org/proceedings/2009/186},
}
TY - CPAPER TI - Unsupervised Rank Aggregation with Domain-Specific Expertise AU - Klementiev, Alexandre AU - Roth, Dan AU - Small, Kevin AU - Titov, Ivan T2 - Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence, IJCAI-09 PB - International Joint Conferences on Artificial Intelligence PY - 2009 SP - 1101 EP - 1105 UR - https://ijcai.org/proceedings/2009/186 ER -Copied
Machine-readable versions of this paper, for tools and AI agents: