Deep Reinforcement Agent for Efficient Instant Search

TL;DR

This paper introduces a reinforcement learning-based agent that selectively triggers instant searches by identifying salient tokens, reducing system load while maintaining high relevance in search results.

Contribution

It presents a novel reinforcement learning approach to predict token importance for efficient instant search, applicable across diverse search architectures.

Findings

The method reduces search triggers while maintaining relevance.

Reinforcement agent outperforms baseline strategies.

New evaluation framework quantifies trade-offs effectively.

Abstract

Instant Search is a paradigm where a search system retrieves answers on the fly while typing. The na\"ive implementation of an Instant Search system would hit the search back-end for results each time a user types a key, imposing a very high load on the underlying search system. In this paper, we propose to address the load issue by identifying tokens that are semantically more salient towards retrieving relevant documents and utilize this knowledge to trigger an instant search selectively. We train a reinforcement agent that interacts directly with the search engine and learns to predict the word's importance. Our proposed method treats the underlying search system as a black box and is more universally applicable to a diverse set of architectures. Furthermore, a novel evaluation framework is presented to study the trade-off between the number of triggered searches and the system's performance. We utilize the framework to evaluate and compare the proposed reinforcement method with other intuitive baselines. Experimental results demonstrate the efficacy of the proposed method towards achieving a superior trade-off.