Optimizing Query Evaluations using Reinforcement Learning for Web Search

04/12/2018
by   Corby Rosset, et al.
0

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 degradation in the quality of the candidate sets.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset