<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="elder-etal-2019-designing">
    <titleInfo>
        <title>Designing a Symbolic Intermediate Representation for Neural Surface Realization</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Henry</namePart>
        <namePart type="family">Elder</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jennifer</namePart>
        <namePart type="family">Foster</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">James</namePart>
        <namePart type="family">Barry</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alexander</namePart>
        <namePart type="family">O’Connor</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-jun</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Workshop on Methods for Optimizing and Evaluating Neural Language Generation</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Minneapolis, Minnesota</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Generated output from neural NLG systems often contain errors such as hallucination, repetition or contradiction. This work focuses on designing a symbolic intermediate representation to be used in multi-stage neural generation with the intention of reducing the frequency of failed outputs. We show that surface realization from this intermediate representation is of high quality and when the full system is applied to the E2E dataset it outperforms the winner of the E2E challenge. Furthermore, by breaking out the surface realization step from typically end-to-end neural systems, we also provide a framework for non-neural based content selection and planning systems to potentially take advantage of semi-supervised pretraining of neural surface realization models.</abstract>
    <identifier type="citekey">elder-etal-2019-designing</identifier>
    <identifier type="doi">10.18653/v1/W19-2308</identifier>
    <location>
        <url>https://aclanthology.org/W19-2308</url>
    </location>
    <part>
        <date>2019-jun</date>
        <extent unit="page">
            <start>65</start>
            <end>73</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Designing a Symbolic Intermediate Representation for Neural Surface Realization
%A Elder, Henry
%A Foster, Jennifer
%A Barry, James
%A O’Connor, Alexander
%S Proceedings of the Workshop on Methods for Optimizing and Evaluating Neural Language Generation
%D 2019
%8 jun
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F elder-etal-2019-designing
%X Generated output from neural NLG systems often contain errors such as hallucination, repetition or contradiction. This work focuses on designing a symbolic intermediate representation to be used in multi-stage neural generation with the intention of reducing the frequency of failed outputs. We show that surface realization from this intermediate representation is of high quality and when the full system is applied to the E2E dataset it outperforms the winner of the E2E challenge. Furthermore, by breaking out the surface realization step from typically end-to-end neural systems, we also provide a framework for non-neural based content selection and planning systems to potentially take advantage of semi-supervised pretraining of neural surface realization models.
%R 10.18653/v1/W19-2308
%U https://aclanthology.org/W19-2308
%U https://doi.org/10.18653/v1/W19-2308
%P 65-73

Markdown (Informal)

[Designing a Symbolic Intermediate Representation for Neural Surface Realization](https://aclanthology.org/W19-2308) (Elder et al., 2019)

• Designing a Symbolic Intermediate Representation for Neural Surface Realization (Elder et al., 2019)

ACL

• Henry Elder, Jennifer Foster, James Barry, and Alexander O’Connor. 2019. Designing a Symbolic Intermediate Representation for Neural Surface Realization. In Proceedings of the Workshop on Methods for Optimizing and Evaluating Neural Language Generation, pages 65–73, Minneapolis, Minnesota. Association for Computational Linguistics.