@inproceedings{1a296e20a78b42548909f49a45a9cf1c,
title = "Learning Open Domain Multi-hop Search Using Reinforcement Learning",
abstract = "We propose a method to teach an automated agent to learn how to search for multi-hop paths of relations between entities in an open domain. The method learns a policy for directing existing information retrieval and machine reading resources to focus on relevant regions of a corpus. The approach formulates the learning problem as a Markov decision process with a state representation that encodes the dynamics of the search process and a reward structure that minimizes the number of documents that must be processed while still finding multi-hop paths. We implement the method in an actor-critic reinforcement learning algorithm and evaluate it on a dataset of search problems derived from a subset of English Wikipedia. The algorithm finds a family of policies that succeeds in extracting the desired information while processing fewer documents compared to several baseline heuristic algorithms.",
author = "Enrique Noriega-Atala and Mihai Surdeanu and Morrison, {Clayton T}",
note = "Publisher Copyright: {\textcopyright} 2022 Association for Computational Linguistics.; 2022 Workshop on Structured and Unstructured Knowledge Integration, SUKI 2022 ; Conference date: 14-07-2022",
year = "2022",
language = "English (US)",
series = "SUKI 2022 - Workshop on Structured and Unstructured Knowledge Integration, Proceedings of the Workshop",
publisher = "Association for Computational Linguistics (ACL)",
pages = "26--35",
editor = "Wenhu Chen and Xinyun Chen and Zhiyu Chen and Ziyu Yao and Michihiro Yasunaga and Tao Yu and Tao Yu and Rui Zhang",
booktitle = "SUKI 2022 - Workshop on Structured and Unstructured Knowledge Integration, Proceedings of the Workshop",
}