<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sharma-etal-2017-speeding">
    <titleInfo>
        <title>Speeding up Reinforcement Learning-based Information Extraction Training using Asynchronous Methods</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Aditya</namePart>
        <namePart type="family">Sharma</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zarana</namePart>
        <namePart type="family">Parekh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Partha</namePart>
        <namePart type="family">Talukdar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Martha</namePart>
            <namePart type="family">Palmer</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rebecca</namePart>
            <namePart type="family">Hwa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sebastian</namePart>
            <namePart type="family">Riedel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Copenhagen, Denmark</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>RLIE-DQN is a recently proposed Reinforcement Learning-based Information Extraction (IE) technique which is able to incorporate external evidence during the extraction process. RLIE-DQN trains a single agent sequentially, training on one instance at a time. This results in significant training slowdown which is undesirable. We leverage recent advances in parallel RL training using asynchronous methods and propose RLIE-A3C. RLIE-A3C trains multiple agents in parallel and is able to achieve upto 6x training speedup over RLIE-DQN, while suffering no loss in average accuracy.</abstract>
    <identifier type="citekey">sharma-etal-2017-speeding</identifier>
    <identifier type="doi">10.18653/v1/D17-1281</identifier>
    <location>
        <url>https://aclanthology.org/D17-1281</url>
    </location>
    <part>
        <date>2017-09</date>
        <extent unit="page">
            <start>2658</start>
            <end>2663</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Speeding up Reinforcement Learning-based Information Extraction Training using Asynchronous Methods
%A Sharma, Aditya
%A Parekh, Zarana
%A Talukdar, Partha
%Y Palmer, Martha
%Y Hwa, Rebecca
%Y Riedel, Sebastian
%S Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F sharma-etal-2017-speeding
%X RLIE-DQN is a recently proposed Reinforcement Learning-based Information Extraction (IE) technique which is able to incorporate external evidence during the extraction process. RLIE-DQN trains a single agent sequentially, training on one instance at a time. This results in significant training slowdown which is undesirable. We leverage recent advances in parallel RL training using asynchronous methods and propose RLIE-A3C. RLIE-A3C trains multiple agents in parallel and is able to achieve upto 6x training speedup over RLIE-DQN, while suffering no loss in average accuracy.
%R 10.18653/v1/D17-1281
%U https://aclanthology.org/D17-1281
%U https://doi.org/10.18653/v1/D17-1281
%P 2658-2663

Markdown (Informal)

[Speeding up Reinforcement Learning-based Information Extraction Training using Asynchronous Methods](https://aclanthology.org/D17-1281) (Sharma et al., EMNLP 2017)

• Speeding up Reinforcement Learning-based Information Extraction Training using Asynchronous Methods (Sharma et al., EMNLP 2017)

ACL

• Aditya Sharma, Zarana Parekh, and Partha Talukdar. 2017. Speeding up Reinforcement Learning-based Information Extraction Training using Asynchronous Methods. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2658–2663, Copenhagen, Denmark. Association for Computational Linguistics.