Learning Open Domain Multi-hop Search Using Reinforcement Learning

Enrique Noriega-Atala, Mihai Surdeanu, Clayton T Morrison

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.

Original languageEnglish (US)
Title of host publicationSUKI 2022 - Workshop on Structured and Unstructured Knowledge Integration, Proceedings of the Workshop
EditorsWenhu Chen, Xinyun Chen, Zhiyu Chen, Ziyu Yao, Michihiro Yasunaga, Tao Yu, Tao Yu, Rui Zhang
PublisherAssociation for Computational Linguistics (ACL)
Pages26-35
Number of pages10
ISBN (Electronic)9781955917865
StatePublished - 2022
Event2022 Workshop on Structured and Unstructured Knowledge Integration, SUKI 2022 - Seattle, United States
Duration: Jul 14 2022 → …

Publication series

NameSUKI 2022 - Workshop on Structured and Unstructured Knowledge Integration, Proceedings of the Workshop

Conference

Conference2022 Workshop on Structured and Unstructured Knowledge Integration, SUKI 2022
Country/TerritoryUnited States
CitySeattle
Period7/14/22 → …

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Information Systems
  • Information Systems and Management

Fingerprint

Dive into the research topics of 'Learning Open Domain Multi-hop Search Using Reinforcement Learning'. Together they form a unique fingerprint.

Cite this