<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dusek-etal-2019-semantic">
    <titleInfo>
        <title>Semantic Noise Matters for Neural Natural Language Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ondřej</namePart>
        <namePart type="family">Dušek</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">David</namePart>
        <namePart type="given">M</namePart>
        <namePart type="family">Howcroft</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Verena</namePart>
        <namePart type="family">Rieser</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-oct–nov</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 12th International Conference on Natural Language Generation</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Kees</namePart>
            <namePart type="family">van Deemter</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Chenghua</namePart>
            <namePart type="family">Lin</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hiroya</namePart>
            <namePart type="family">Takamura</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Tokyo, Japan</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Neural natural language generation (NNLG) systems are known for their pathological outputs, i.e. generating text which is unrelated to the input specification. In this paper, we show the impact of semantic noise on state-of-the-art NNLG models which implement different semantic control mechanisms. We find that cleaned data can improve semantic correctness by up to 97%, while maintaining fluency. We also find that the most common error is omitting information, rather than hallucination.</abstract>
    <identifier type="citekey">dusek-etal-2019-semantic</identifier>
    <identifier type="doi">10.18653/v1/W19-8652</identifier>
    <location>
        <url>https://aclanthology.org/W19-8652</url>
    </location>
    <part>
        <date>2019-oct–nov</date>
        <extent unit="page">
            <start>421</start>
            <end>426</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Semantic Noise Matters for Neural Natural Language Generation
%A Dušek, Ondřej
%A Howcroft, David M.
%A Rieser, Verena
%Y van Deemter, Kees
%Y Lin, Chenghua
%Y Takamura, Hiroya
%S Proceedings of the 12th International Conference on Natural Language Generation
%D 2019
%8 oct–nov
%I Association for Computational Linguistics
%C Tokyo, Japan
%F dusek-etal-2019-semantic
%X Neural natural language generation (NNLG) systems are known for their pathological outputs, i.e. generating text which is unrelated to the input specification. In this paper, we show the impact of semantic noise on state-of-the-art NNLG models which implement different semantic control mechanisms. We find that cleaned data can improve semantic correctness by up to 97%, while maintaining fluency. We also find that the most common error is omitting information, rather than hallucination.
%R 10.18653/v1/W19-8652
%U https://aclanthology.org/W19-8652
%U https://doi.org/10.18653/v1/W19-8652
%P 421-426

Markdown (Informal)

[Semantic Noise Matters for Neural Natural Language Generation](https://aclanthology.org/W19-8652) (Dušek et al., INLG 2019)

• Semantic Noise Matters for Neural Natural Language Generation (Dušek et al., INLG 2019)

ACL

• Ondřej Dušek, David M. Howcroft, and Verena Rieser. 2019. Semantic Noise Matters for Neural Natural Language Generation. In Proceedings of the 12th International Conference on Natural Language Generation, pages 421–426, Tokyo, Japan. Association for Computational Linguistics.