<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="freitag-roy-2018-unsupervised">
    <titleInfo>
        <title>Unsupervised Natural Language Generation with Denoising Autoencoders</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Markus</namePart>
        <namePart type="family">Freitag</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Scott</namePart>
        <namePart type="family">Roy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-oct-nov</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ellen</namePart>
            <namePart type="family">Riloff</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Chiang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Julia</namePart>
            <namePart type="family">Hockenmaier</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jun’ichi</namePart>
            <namePart type="family">Tsujii</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Brussels, Belgium</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Generating text from structured data is important for various tasks such as question answering and dialog systems. We show that in at least one domain, without any supervision and only based on unlabeled text, we are able to build a Natural Language Generation (NLG) system with higher performance than supervised approaches. In our approach, we interpret the structured data as a corrupt representation of the desired output and use a denoising auto-encoder to reconstruct the sentence. We show how to introduce noise into training examples that do not contain structured data, and that the resulting denoising auto-encoder generalizes to generate correct sentences when given structured data.</abstract>
    <identifier type="citekey">freitag-roy-2018-unsupervised</identifier>
    <identifier type="doi">10.18653/v1/D18-1426</identifier>
    <location>
        <url>https://aclanthology.org/D18-1426</url>
    </location>
    <part>
        <date>2018-oct-nov</date>
        <extent unit="page">
            <start>3922</start>
            <end>3929</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Unsupervised Natural Language Generation with Denoising Autoencoders
%A Freitag, Markus
%A Roy, Scott
%Y Riloff, Ellen
%Y Chiang, David
%Y Hockenmaier, Julia
%Y Tsujii, Jun’ichi
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F freitag-roy-2018-unsupervised
%X Generating text from structured data is important for various tasks such as question answering and dialog systems. We show that in at least one domain, without any supervision and only based on unlabeled text, we are able to build a Natural Language Generation (NLG) system with higher performance than supervised approaches. In our approach, we interpret the structured data as a corrupt representation of the desired output and use a denoising auto-encoder to reconstruct the sentence. We show how to introduce noise into training examples that do not contain structured data, and that the resulting denoising auto-encoder generalizes to generate correct sentences when given structured data.
%R 10.18653/v1/D18-1426
%U https://aclanthology.org/D18-1426
%U https://doi.org/10.18653/v1/D18-1426
%P 3922-3929

Markdown (Informal)

[Unsupervised Natural Language Generation with Denoising Autoencoders](https://aclanthology.org/D18-1426) (Freitag & Roy, EMNLP 2018)

• Unsupervised Natural Language Generation with Denoising Autoencoders (Freitag & Roy, EMNLP 2018)

ACL

• Markus Freitag and Scott Roy. 2018. Unsupervised Natural Language Generation with Denoising Autoencoders. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3922–3929, Brussels, Belgium. Association for Computational Linguistics.