<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mehta-etal-2019-fine">
    <titleInfo>
        <title>Fine-Grained Control of Sentence Segmentation and Entity Positioning in Neural NLG</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Kritika</namePart>
        <namePart type="family">Mehta</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Raheel</namePart>
        <namePart type="family">Qader</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Cyril</namePart>
        <namePart type="family">Labbe</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">François</namePart>
        <namePart type="family">Portet</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 1st Workshop on Discourse Structure in Neural NLG</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anusha</namePart>
            <namePart type="family">Balakrishnan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Vera</namePart>
            <namePart type="family">Demberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Chandra</namePart>
            <namePart type="family">Khatri</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Abhinav</namePart>
            <namePart type="family">Rastogi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Donia</namePart>
            <namePart type="family">Scott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marilyn</namePart>
            <namePart type="family">Walker</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Michael</namePart>
            <namePart type="family">White</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>The move from pipeline Natural Language Generation (NLG) approaches to neural end-to-end approaches led to a loss of control in sentence planning operations owing to the conflation of intermediary micro-planning stages into a single model. Such control is highly necessary when the text should be tailored to respect some constraints such as which entity to be mentioned first, the entity position, the complexity of sentences, etc. In this paper, we introduce fine-grained control of sentence planning in neural data-to-text generation models at two levels - realization of input entities in desired sentences and realization of the input entities in the desired position among individual sentences. We show that by augmenting the input with explicit position identifiers, the neural model can achieve a great control over the output structure while keeping the naturalness of the generated text intact. Since sentence level metrics are not entirely suitable to evaluate this task, we used a metric specific to our task that accounts for the model’s ability to achieve control. The results demonstrate that the position identifiers do constraint the neural model to respect the intended output structure which can be useful in a variety of domains that require the generated text to be in a certain structure.</abstract>
    <identifier type="citekey">mehta-etal-2019-fine</identifier>
    <identifier type="doi">10.18653/v1/W19-8103</identifier>
    <location>
        <url>https://aclanthology.org/W19-8103</url>
    </location>
    <part>
        <date>2019-11</date>
        <extent unit="page">
            <start>18</start>
            <end>23</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Fine-Grained Control of Sentence Segmentation and Entity Positioning in Neural NLG
%A Mehta, Kritika
%A Qader, Raheel
%A Labbe, Cyril
%A Portet, François
%Y Balakrishnan, Anusha
%Y Demberg, Vera
%Y Khatri, Chandra
%Y Rastogi, Abhinav
%Y Scott, Donia
%Y Walker, Marilyn
%Y White, Michael
%S Proceedings of the 1st Workshop on Discourse Structure in Neural NLG
%D 2019
%8 November
%I Association for Computational Linguistics
%C Tokyo, Japan
%F mehta-etal-2019-fine
%X The move from pipeline Natural Language Generation (NLG) approaches to neural end-to-end approaches led to a loss of control in sentence planning operations owing to the conflation of intermediary micro-planning stages into a single model. Such control is highly necessary when the text should be tailored to respect some constraints such as which entity to be mentioned first, the entity position, the complexity of sentences, etc. In this paper, we introduce fine-grained control of sentence planning in neural data-to-text generation models at two levels - realization of input entities in desired sentences and realization of the input entities in the desired position among individual sentences. We show that by augmenting the input with explicit position identifiers, the neural model can achieve a great control over the output structure while keeping the naturalness of the generated text intact. Since sentence level metrics are not entirely suitable to evaluate this task, we used a metric specific to our task that accounts for the model’s ability to achieve control. The results demonstrate that the position identifiers do constraint the neural model to respect the intended output structure which can be useful in a variety of domains that require the generated text to be in a certain structure.
%R 10.18653/v1/W19-8103
%U https://aclanthology.org/W19-8103
%U https://doi.org/10.18653/v1/W19-8103
%P 18-23

Markdown (Informal)

[Fine-Grained Control of Sentence Segmentation and Entity Positioning in Neural NLG](https://aclanthology.org/W19-8103) (Mehta et al., INLG 2019)

• Fine-Grained Control of Sentence Segmentation and Entity Positioning in Neural NLG (Mehta et al., INLG 2019)

ACL

• Kritika Mehta, Raheel Qader, Cyril Labbe, and François Portet. 2019. Fine-Grained Control of Sentence Segmentation and Entity Positioning in Neural NLG. In Proceedings of the 1st Workshop on Discourse Structure in Neural NLG, pages 18–23, Tokyo, Japan. Association for Computational Linguistics.