LGIROct 15, 2020

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes