@inproceedings{noriega-atala-etal-2022-learning,
title = "Learning Open Domain Multi-hop Search Using Reinforcement Learning",
author = "Noriega-Atala, Enrique and
Surdeanu, Mihai and
Morrison, Clayton",
editor = "Chen, Wenhu and
Chen, Xinyun and
Chen, Zhiyu and
Yao, Ziyu and
Yasunaga, Michihiro and
Yu, Tao and
Zhang, Rui",
booktitle = "Proceedings of the Workshop on Structured and Unstructured Knowledge Integration (SUKI)",
month = jul,
year = "2022",
address = "Seattle, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.suki-1.4",
doi = "10.18653/v1/2022.suki-1.4",
pages = "26--35",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="noriega-atala-etal-2022-learning">
<titleInfo>
<title>Learning Open Domain Multi-hop Search Using Reinforcement Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Enrique</namePart>
<namePart type="family">Noriega-Atala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihai</namePart>
<namePart type="family">Surdeanu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Clayton</namePart>
<namePart type="family">Morrison</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Structured and Unstructured Knowledge Integration (SUKI)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenhu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyun</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziyu</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michihiro</namePart>
<namePart type="family">Yasunaga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">noriega-atala-etal-2022-learning</identifier>
<identifier type="doi">10.18653/v1/2022.suki-1.4</identifier>
<location>
<url>https://aclanthology.org/2022.suki-1.4</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>26</start>
<end>35</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning Open Domain Multi-hop Search Using Reinforcement Learning
%A Noriega-Atala, Enrique
%A Surdeanu, Mihai
%A Morrison, Clayton
%Y Chen, Wenhu
%Y Chen, Xinyun
%Y Chen, Zhiyu
%Y Yao, Ziyu
%Y Yasunaga, Michihiro
%Y Yu, Tao
%Y Zhang, Rui
%S Proceedings of the Workshop on Structured and Unstructured Knowledge Integration (SUKI)
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, USA
%F noriega-atala-etal-2022-learning
%X 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.
%R 10.18653/v1/2022.suki-1.4
%U https://aclanthology.org/2022.suki-1.4
%U https://doi.org/10.18653/v1/2022.suki-1.4
%P 26-35
Markdown (Informal)
[Learning Open Domain Multi-hop Search Using Reinforcement Learning](https://aclanthology.org/2022.suki-1.4) (Noriega-Atala et al., SUKI 2022)
ACL