<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="du-black-2019-top">
    <titleInfo>
        <title>Top-Down Structurally-Constrained Neural Response Generation with Lexicalized Probabilistic Context-Free Grammar</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Wenchao</namePart>
        <namePart type="family">Du</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alan</namePart>
        <namePart type="given">W</namePart>
        <namePart type="family">Black</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Jill</namePart>
            <namePart type="family">Burstein</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Christy</namePart>
            <namePart type="family">Doran</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Thamar</namePart>
            <namePart type="family">Solorio</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Minneapolis, Minnesota</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We consider neural language generation under a novel problem setting: generating the words of a sentence according to the order of their first appearance in its lexicalized PCFG parse tree, in a depth-first, left-to-right manner. Unlike previous tree-based language generation methods, our approach is both (i) top-down and (ii) explicitly generating syntactic structure at the same time. In addition, our method combines neural model with symbolic approach: word choice at each step is constrained by its predicted syntactic function. We applied our model to the task of dialog response generation, and found it significantly improves over sequence-to-sequence baseline, in terms of diversity and relevance. We also investigated the effect of lexicalization on language generation, and found that lexicalization schemes that give priority to content words have certain advantages over those focusing on dependency relations.</abstract>
    <identifier type="citekey">du-black-2019-top</identifier>
    <identifier type="doi">10.18653/v1/N19-1377</identifier>
    <location>
        <url>https://aclanthology.org/N19-1377</url>
    </location>
    <part>
        <date>2019-06</date>
        <extent unit="page">
            <start>3762</start>
            <end>3771</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Top-Down Structurally-Constrained Neural Response Generation with Lexicalized Probabilistic Context-Free Grammar
%A Du, Wenchao
%A Black, Alan W.
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F du-black-2019-top
%X We consider neural language generation under a novel problem setting: generating the words of a sentence according to the order of their first appearance in its lexicalized PCFG parse tree, in a depth-first, left-to-right manner. Unlike previous tree-based language generation methods, our approach is both (i) top-down and (ii) explicitly generating syntactic structure at the same time. In addition, our method combines neural model with symbolic approach: word choice at each step is constrained by its predicted syntactic function. We applied our model to the task of dialog response generation, and found it significantly improves over sequence-to-sequence baseline, in terms of diversity and relevance. We also investigated the effect of lexicalization on language generation, and found that lexicalization schemes that give priority to content words have certain advantages over those focusing on dependency relations.
%R 10.18653/v1/N19-1377
%U https://aclanthology.org/N19-1377
%U https://doi.org/10.18653/v1/N19-1377
%P 3762-3771

Markdown (Informal)

[Top-Down Structurally-Constrained Neural Response Generation with Lexicalized Probabilistic Context-Free Grammar](https://aclanthology.org/N19-1377) (Du & Black, NAACL 2019)

• Top-Down Structurally-Constrained Neural Response Generation with Lexicalized Probabilistic Context-Free Grammar (Du & Black, NAACL 2019)

ACL

• Wenchao Du and Alan W Black. 2019. Top-Down Structurally-Constrained Neural Response Generation with Lexicalized Probabilistic Context-Free Grammar. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 3762–3771, Minneapolis, Minnesota. Association for Computational Linguistics.