<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="postma-etal-2016-always">
    <titleInfo>
        <title>More is not always better: balancing sense distributions for all-words Word Sense Disambiguation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Marten</namePart>
        <namePart type="family">Postma</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ruben</namePart>
        <namePart type="family">Izquierdo Bevia</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Piek</namePart>
        <namePart type="family">Vossen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2016-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yuji</namePart>
            <namePart type="family">Matsumoto</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rashmi</namePart>
            <namePart type="family">Prasad</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>The COLING 2016 Organizing Committee</publisher>
            <place>
                <placeTerm type="text">Osaka, Japan</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Current Word Sense Disambiguation systems show an extremely poor performance on low frequent senses, which is mainly caused by the difference in sense distributions between training and test data. The main focus in tackling this problem has been on acquiring more data or selecting a single predominant sense and not necessarily on the meta properties of the data itself. We demonstrate that these properties, such as the volume, provenance, and balancing, play an important role with respect to system performance. In this paper, we describe a set of experiments to analyze these meta properties in the framework of a state-of-the-art WSD system when evaluated on the SemEval-2013 English all-words dataset. We show that volume and provenance are indeed important, but that approximating the perfect balancing of the selected training data leads to an improvement of 21 points and exceeds state-of-the-art systems by 14 points while using only simple features. We therefore conclude that unsupervised acquisition of training data should be guided by strategies aimed at matching meta properties.</abstract>
    <identifier type="citekey">postma-etal-2016-always</identifier>
    <location>
        <url>https://aclanthology.org/C16-1330</url>
    </location>
    <part>
        <date>2016-12</date>
        <extent unit="page">
            <start>3496</start>
            <end>3506</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T More is not always better: balancing sense distributions for all-words Word Sense Disambiguation
%A Postma, Marten
%A Izquierdo Bevia, Ruben
%A Vossen, Piek
%Y Matsumoto, Yuji
%Y Prasad, Rashmi
%S Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F postma-etal-2016-always
%X Current Word Sense Disambiguation systems show an extremely poor performance on low frequent senses, which is mainly caused by the difference in sense distributions between training and test data. The main focus in tackling this problem has been on acquiring more data or selecting a single predominant sense and not necessarily on the meta properties of the data itself. We demonstrate that these properties, such as the volume, provenance, and balancing, play an important role with respect to system performance. In this paper, we describe a set of experiments to analyze these meta properties in the framework of a state-of-the-art WSD system when evaluated on the SemEval-2013 English all-words dataset. We show that volume and provenance are indeed important, but that approximating the perfect balancing of the selected training data leads to an improvement of 21 points and exceeds state-of-the-art systems by 14 points while using only simple features. We therefore conclude that unsupervised acquisition of training data should be guided by strategies aimed at matching meta properties.
%U https://aclanthology.org/C16-1330
%P 3496-3506

Markdown (Informal)

[More is not always better: balancing sense distributions for all-words Word Sense Disambiguation](https://aclanthology.org/C16-1330) (Postma et al., COLING 2016)

• More is not always better: balancing sense distributions for all-words Word Sense Disambiguation (Postma et al., COLING 2016)

ACL

• Marten Postma, Ruben Izquierdo Bevia, and Piek Vossen. 2016. More is not always better: balancing sense distributions for all-words Word Sense Disambiguation. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 3496–3506, Osaka, Japan. The COLING 2016 Organizing Committee.