<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ronning-etal-2018-sluice">
    <titleInfo>
        <title>Sluice Resolution without Hand-Crafted Features over Brittle Syntax Trees</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ola</namePart>
        <namePart type="family">Rønning</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Daniel</namePart>
        <namePart type="family">Hardt</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Anders</namePart>
        <namePart type="family">Søgaard</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)</title>
        </titleInfo>
        <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">Heng</namePart>
            <namePart type="family">Ji</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Amanda</namePart>
            <namePart type="family">Stent</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">New Orleans, Louisiana</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Sluice resolution in English is the problem of finding antecedents of wh-fronted ellipses. Previous work has relied on hand-crafted features over syntax trees that scale poorly to other languages and domains; in particular, to dialogue, which is one of the most interesting applications of sluice resolution. Syntactic information is arguably important for sluice resolution, but we show that multi-task learning with partial parsing as auxiliary tasks effectively closes the gap and buys us an additional 9% error reduction over previous work. Since we are not directly relying on features from partial parsers, our system is more robust to domain shifts, giving a 26% error reduction on embedded sluices in dialogue.</abstract>
    <identifier type="citekey">ronning-etal-2018-sluice</identifier>
    <identifier type="doi">10.18653/v1/N18-2038</identifier>
    <location>
        <url>https://aclanthology.org/N18-2038</url>
    </location>
    <part>
        <date>2018-06</date>
        <extent unit="page">
            <start>236</start>
            <end>241</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Sluice Resolution without Hand-Crafted Features over Brittle Syntax Trees
%A Rønning, Ola
%A Hardt, Daniel
%A Søgaard, Anders
%Y Walker, Marilyn
%Y Ji, Heng
%Y Stent, Amanda
%S Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans, Louisiana
%F ronning-etal-2018-sluice
%X Sluice resolution in English is the problem of finding antecedents of wh-fronted ellipses. Previous work has relied on hand-crafted features over syntax trees that scale poorly to other languages and domains; in particular, to dialogue, which is one of the most interesting applications of sluice resolution. Syntactic information is arguably important for sluice resolution, but we show that multi-task learning with partial parsing as auxiliary tasks effectively closes the gap and buys us an additional 9% error reduction over previous work. Since we are not directly relying on features from partial parsers, our system is more robust to domain shifts, giving a 26% error reduction on embedded sluices in dialogue.
%R 10.18653/v1/N18-2038
%U https://aclanthology.org/N18-2038
%U https://doi.org/10.18653/v1/N18-2038
%P 236-241

Markdown (Informal)

[Sluice Resolution without Hand-Crafted Features over Brittle Syntax Trees](https://aclanthology.org/N18-2038) (Rønning et al., NAACL 2018)

• Sluice Resolution without Hand-Crafted Features over Brittle Syntax Trees (Rønning et al., NAACL 2018)

ACL

• Ola Rønning, Daniel Hardt, and Anders Søgaard. 2018. Sluice Resolution without Hand-Crafted Features over Brittle Syntax Trees. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 236–241, New Orleans, Louisiana. Association for Computational Linguistics.