Optimizing Query Evaluations using Reinforcement Learning for Web Search
Information Retrieval
2018-08-21 v2
Abstract
In web search, typically a candidate generation step selects a small set of documents---from collections containing as many as billions of web pages---that are subsequently ranked and pruned before being presented to the user. In Bing, the candidate generation involves scanning the index using statically designed match plans that prescribe sequences of different match criteria and stopping conditions. In this work, we pose match planning as a reinforcement learning task and observe up to 20% reduction in index blocks accessed, with small or no degradation in the quality of the candidate sets.
Cite
@article{arxiv.1804.04410,
title = {Optimizing Query Evaluations using Reinforcement Learning for Web Search},
author = {Corby Rosset and Damien Jose and Gargi Ghosh and Bhaskar Mitra and Saurabh Tiwary},
journal= {arXiv preprint arXiv:1804.04410},
year = {2018}
}
Comments
ACM SIGIR 2018 short paper (pre-print)