<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kohita-etal-2017-multilingual">
    <titleInfo>
        <title>Multilingual Back-and-Forth Conversion between Content and Function Head for Easy Dependency Parsing</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ryosuke</namePart>
        <namePart type="family">Kohita</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hiroshi</namePart>
        <namePart type="family">Noji</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuji</namePart>
        <namePart type="family">Matsumoto</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-apr</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Valencia, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Universal Dependencies (UD) is becoming a standard annotation scheme cross-linguistically, but it is argued that this scheme centering on content words is harder to parse than the conventional one centering on function words. To improve the parsability of UD, we propose a back-and-forth conversion algorithm, in which we preprocess the training treebank to increase parsability, and reconvert the parser outputs to follow the UD scheme as a postprocess. We show that this technique consistently improves LAS across languages even with a state-of-the-art parser, in particular on core dependency arcs such as nominal modifier. We also provide an in-depth analysis to understand why our method increases parsability.</abstract>
    <identifier type="citekey">kohita-etal-2017-multilingual</identifier>
    <location>
        <url>https://aclanthology.org/E17-2001</url>
    </location>
    <part>
        <date>2017-apr</date>
        <extent unit="page">
            <start>1</start>
            <end>7</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Multilingual Back-and-Forth Conversion between Content and Function Head for Easy Dependency Parsing
%A Kohita, Ryosuke
%A Noji, Hiroshi
%A Matsumoto, Yuji
%S Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
%D 2017
%8 apr
%I Association for Computational Linguistics
%C Valencia, Spain
%F kohita-etal-2017-multilingual
%X Universal Dependencies (UD) is becoming a standard annotation scheme cross-linguistically, but it is argued that this scheme centering on content words is harder to parse than the conventional one centering on function words. To improve the parsability of UD, we propose a back-and-forth conversion algorithm, in which we preprocess the training treebank to increase parsability, and reconvert the parser outputs to follow the UD scheme as a postprocess. We show that this technique consistently improves LAS across languages even with a state-of-the-art parser, in particular on core dependency arcs such as nominal modifier. We also provide an in-depth analysis to understand why our method increases parsability.
%U https://aclanthology.org/E17-2001
%P 1-7

Markdown (Informal)

[Multilingual Back-and-Forth Conversion between Content and Function Head for Easy Dependency Parsing](https://aclanthology.org/E17-2001) (Kohita et al., EACL 2017)

• Multilingual Back-and-Forth Conversion between Content and Function Head for Easy Dependency Parsing (Kohita et al., EACL 2017)

ACL

• Ryosuke Kohita, Hiroshi Noji, and Yuji Matsumoto. 2017. Multilingual Back-and-Forth Conversion between Content and Function Head for Easy Dependency Parsing. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 1–7, Valencia, Spain. Association for Computational Linguistics.