<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vilares-gomez-rodriguez-2018-transition-based">
    <titleInfo>
        <title>Transition-based Parsing with Lighter Feed-Forward Networks</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">David</namePart>
        <namePart type="family">Vilares</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Carlos</namePart>
        <namePart type="family">Gómez-Rodríguez</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Second Workshop on Universal Dependencies (UDW 2018)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marie-Catherine</namePart>
            <namePart type="family">de Marneffe</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Teresa</namePart>
            <namePart type="family">Lynn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sebastian</namePart>
            <namePart type="family">Schuster</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Brussels, Belgium</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We explore whether it is possible to build lighter parsers, that are statistically equivalent to their corresponding standard version, for a wide set of languages showing different structures and morphologies. As testbed, we use the Universal Dependencies and transition-based dependency parsers trained on feed-forward networks. For these, most existing research assumes de facto standard embedded features and relies on pre-computation tricks to obtain speed-ups. We explore how these features and their size can be reduced and whether this translates into speed-ups with a negligible impact on accuracy. The experiments show that grand-daughter features can be removed for the majority of treebanks without a significant (negative or positive) LAS difference. They also show how the size of the embeddings can be notably reduced.</abstract>
    <identifier type="citekey">vilares-gomez-rodriguez-2018-transition-based</identifier>
    <identifier type="doi">10.18653/v1/W18-6019</identifier>
    <location>
        <url>https://aclanthology.org/W18-6019</url>
    </location>
    <part>
        <date>2018-11</date>
        <extent unit="page">
            <start>162</start>
            <end>172</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Transition-based Parsing with Lighter Feed-Forward Networks
%A Vilares, David
%A Gómez-Rodríguez, Carlos
%Y de Marneffe, Marie-Catherine
%Y Lynn, Teresa
%Y Schuster, Sebastian
%S Proceedings of the Second Workshop on Universal Dependencies (UDW 2018)
%D 2018
%8 November
%I Association for Computational Linguistics
%C Brussels, Belgium
%F vilares-gomez-rodriguez-2018-transition-based
%X We explore whether it is possible to build lighter parsers, that are statistically equivalent to their corresponding standard version, for a wide set of languages showing different structures and morphologies. As testbed, we use the Universal Dependencies and transition-based dependency parsers trained on feed-forward networks. For these, most existing research assumes de facto standard embedded features and relies on pre-computation tricks to obtain speed-ups. We explore how these features and their size can be reduced and whether this translates into speed-ups with a negligible impact on accuracy. The experiments show that grand-daughter features can be removed for the majority of treebanks without a significant (negative or positive) LAS difference. They also show how the size of the embeddings can be notably reduced.
%R 10.18653/v1/W18-6019
%U https://aclanthology.org/W18-6019
%U https://doi.org/10.18653/v1/W18-6019
%P 162-172

Markdown (Informal)

[Transition-based Parsing with Lighter Feed-Forward Networks](https://aclanthology.org/W18-6019) (Vilares & Gómez-Rodríguez, UDW 2018)

• Transition-based Parsing with Lighter Feed-Forward Networks (Vilares & Gómez-Rodríguez, UDW 2018)

ACL

• David Vilares and Carlos Gómez-Rodríguez. 2018. Transition-based Parsing with Lighter Feed-Forward Networks. In Proceedings of the Second Workshop on Universal Dependencies (UDW 2018), pages 162–172, Brussels, Belgium. Association for Computational Linguistics.