Blending Search and Discovery: Tag-Based Query Refinement with Contextual Reinforcement Learning
arXiv:2010.09495v12 citations
Originality Synthesis-oriented
AI Analysis
This work addresses query refinement for mobile users, but appears incremental as it adapts existing methods to a specific application.
The paper tackled the problem of tag-based query refinement for mobile-friendly search by using reinforcement learning, proposing a deep contextual bandit that scales efficiently in multi-tenant SaaS scenarios.
We tackle tag-based query refinement as a mobile-friendly alternative to standard facet search. We approach the inference challenge with reinforcement learning, and propose a deep contextual bandit that can be efficiently scaled in a multi-tenant SaaS scenario.