<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aufrant-etal-2018-exploiting">
    <titleInfo>
        <title>Exploiting Dynamic Oracles to Train Projective Dependency Parsers on Non-Projective Trees</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Lauriane</namePart>
        <namePart type="family">Aufrant</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Guillaume</namePart>
        <namePart type="family">Wisniewski</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">François</namePart>
        <namePart type="family">Yvon</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>Because the most common transition systems are projective, training a transition-based dependency parser often implies to either ignore or rewrite the non-projective training examples, which has an adverse impact on accuracy. In this work, we propose a simple modification of dynamic oracles, which enables the use of non-projective data when training projective parsers. Evaluation on 73 treebanks shows that our method achieves significant gains (+2 to +7 UAS for the most non-projective languages) and consistently outperforms traditional projectivization and pseudo-projectivization approaches.</abstract>
    <identifier type="citekey">aufrant-etal-2018-exploiting</identifier>
    <identifier type="doi">10.18653/v1/N18-2066</identifier>
    <location>
        <url>https://aclanthology.org/N18-2066</url>
    </location>
    <part>
        <date>2018-06</date>
        <extent unit="page">
            <start>413</start>
            <end>419</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Exploiting Dynamic Oracles to Train Projective Dependency Parsers on Non-Projective Trees
%A Aufrant, Lauriane
%A Wisniewski, Guillaume
%A Yvon, François
%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 aufrant-etal-2018-exploiting
%X Because the most common transition systems are projective, training a transition-based dependency parser often implies to either ignore or rewrite the non-projective training examples, which has an adverse impact on accuracy. In this work, we propose a simple modification of dynamic oracles, which enables the use of non-projective data when training projective parsers. Evaluation on 73 treebanks shows that our method achieves significant gains (+2 to +7 UAS for the most non-projective languages) and consistently outperforms traditional projectivization and pseudo-projectivization approaches.
%R 10.18653/v1/N18-2066
%U https://aclanthology.org/N18-2066
%U https://doi.org/10.18653/v1/N18-2066
%P 413-419

Markdown (Informal)

[Exploiting Dynamic Oracles to Train Projective Dependency Parsers on Non-Projective Trees](https://aclanthology.org/N18-2066) (Aufrant et al., NAACL 2018)

• Exploiting Dynamic Oracles to Train Projective Dependency Parsers on Non-Projective Trees (Aufrant et al., NAACL 2018)

ACL

• Lauriane Aufrant, Guillaume Wisniewski, and François Yvon. 2018. Exploiting Dynamic Oracles to Train Projective Dependency Parsers on Non-Projective 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 413–419, New Orleans, Louisiana. Association for Computational Linguistics.