Deep Reinforcement Agent for Efficient Instant Search

Ravneet Arora, Sreejith Menon, Ayush Jain, Nehil Jain

2023

Abstract

Instant Search is a paradigm where a search system retrieves answers on the fly while typing. The naı̈ve 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 toward retrieving relevant documents and utilizing 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 in relation to the search engine. Our proposed method treats the search system as a black box and is more universally applicable to diverse architectures. To further support our work, 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 baselines. Experimental results demonstrate the efficacy of the proposed method in achieving a superior trade-off.

Paper Citation

in Harvard Style

Arora R., Menon S., Jain A. and Jain N. (2023). Deep Reinforcement Agent for Efficient Instant Search. In Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR; ISBN 978-989-758-671-2, SciTePress, pages 281-288. DOI: 10.5220/0012178300003598

in Bibtex Style

@conference{kdir23,
author={Ravneet Arora and Sreejith Menon and Ayush Jain and Nehil Jain},
title={Deep Reinforcement Agent for Efficient Instant Search},
booktitle={Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR},
year={2023},
pages={281-288},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012178300003598},
isbn={978-989-758-671-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR
TI - Deep Reinforcement Agent for Efficient Instant Search
SN - 978-989-758-671-2
AU - Arora R.
AU - Menon S.
AU - Jain A.
AU - Jain N.
PY - 2023
SP - 281
EP - 288
DO - 10.5220/0012178300003598
PB - SciTePress