<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gaddy-klein-2019-pre">
    <titleInfo>
        <title>Pre-Learning Environment Representations for Data-Efficient Neural Instruction Following</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">David</namePart>
        <namePart type="family">Gaddy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dan</namePart>
        <namePart type="family">Klein</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Korhonen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Traum</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Màrquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Florence, Italy</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We consider the problem of learning to map from natural language instructions to state transitions (actions) in a data-efficient manner. Our method takes inspiration from the idea that it should be easier to ground language to concepts that have already been formed through pre-linguistic observation. We augment a baseline instruction-following learner with an initial environment-learning phase that uses observations of language-free state transitions to induce a suitable latent representation of actions before processing the instruction-following training data. We show that mapping to pre-learned representations substantially improves performance over systems whose representations are learned from limited instructional data alone.</abstract>
    <identifier type="citekey">gaddy-klein-2019-pre</identifier>
    <identifier type="doi">10.18653/v1/P19-1188</identifier>
    <location>
        <url>https://aclanthology.org/P19-1188</url>
    </location>
    <part>
        <date>2019-07</date>
        <extent unit="page">
            <start>1946</start>
            <end>1956</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Pre-Learning Environment Representations for Data-Efficient Neural Instruction Following
%A Gaddy, David
%A Klein, Dan
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F gaddy-klein-2019-pre
%X We consider the problem of learning to map from natural language instructions to state transitions (actions) in a data-efficient manner. Our method takes inspiration from the idea that it should be easier to ground language to concepts that have already been formed through pre-linguistic observation. We augment a baseline instruction-following learner with an initial environment-learning phase that uses observations of language-free state transitions to induce a suitable latent representation of actions before processing the instruction-following training data. We show that mapping to pre-learned representations substantially improves performance over systems whose representations are learned from limited instructional data alone.
%R 10.18653/v1/P19-1188
%U https://aclanthology.org/P19-1188
%U https://doi.org/10.18653/v1/P19-1188
%P 1946-1956

Markdown (Informal)

[Pre-Learning Environment Representations for Data-Efficient Neural Instruction Following](https://aclanthology.org/P19-1188) (Gaddy & Klein, ACL 2019)

• Pre-Learning Environment Representations for Data-Efficient Neural Instruction Following (Gaddy & Klein, ACL 2019)

ACL

• David Gaddy and Dan Klein. 2019. Pre-Learning Environment Representations for Data-Efficient Neural Instruction Following. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1946–1956, Florence, Italy. Association for Computational Linguistics.