<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kober-etal-2017-one">
    <titleInfo>
        <title>One Representation per Word - Does it make Sense for Composition?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Thomas</namePart>
        <namePart type="family">Kober</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Julie</namePart>
        <namePart type="family">Weeds</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">John</namePart>
        <namePart type="family">Wilkie</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jeremy</namePart>
        <namePart type="family">Reffin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">David</namePart>
        <namePart type="family">Weir</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-04</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 1st Workshop on Sense, Concept and Entity Representations and their Applications</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Jose</namePart>
            <namePart type="family">Camacho-Collados</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohammad</namePart>
            <namePart type="given">Taher</namePart>
            <namePart type="family">Pilehvar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Valencia, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In this paper, we investigate whether an a priori disambiguation of word senses is strictly necessary or whether the meaning of a word in context can be disambiguated through composition alone. We evaluate the performance of off-the-shelf single-vector and multi-sense vector models on a benchmark phrase similarity task and a novel task for word-sense discrimination. We find that single-sense vector models perform as well or better than multi-sense vector models despite arguably less clean elementary representations. Our findings furthermore show that simple composition functions such as pointwise addition are able to recover sense specific information from a single-sense vector model remarkably well.</abstract>
    <identifier type="citekey">kober-etal-2017-one</identifier>
    <identifier type="doi">10.18653/v1/W17-1910</identifier>
    <location>
        <url>https://aclanthology.org/W17-1910</url>
    </location>
    <part>
        <date>2017-04</date>
        <extent unit="page">
            <start>79</start>
            <end>90</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T One Representation per Word - Does it make Sense for Composition?
%A Kober, Thomas
%A Weeds, Julie
%A Wilkie, John
%A Reffin, Jeremy
%A Weir, David
%Y Camacho-Collados, Jose
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 1st Workshop on Sense, Concept and Entity Representations and their Applications
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F kober-etal-2017-one
%X In this paper, we investigate whether an a priori disambiguation of word senses is strictly necessary or whether the meaning of a word in context can be disambiguated through composition alone. We evaluate the performance of off-the-shelf single-vector and multi-sense vector models on a benchmark phrase similarity task and a novel task for word-sense discrimination. We find that single-sense vector models perform as well or better than multi-sense vector models despite arguably less clean elementary representations. Our findings furthermore show that simple composition functions such as pointwise addition are able to recover sense specific information from a single-sense vector model remarkably well.
%R 10.18653/v1/W17-1910
%U https://aclanthology.org/W17-1910
%U https://doi.org/10.18653/v1/W17-1910
%P 79-90

Markdown (Informal)

[One Representation per Word - Does it make Sense for Composition?](https://aclanthology.org/W17-1910) (Kober et al., SENSE 2017)

• One Representation per Word - Does it make Sense for Composition? (Kober et al., SENSE 2017)

ACL

• Thomas Kober, Julie Weeds, John Wilkie, Jeremy Reffin, and David Weir. 2017. One Representation per Word - Does it make Sense for Composition?. In Proceedings of the 1st Workshop on Sense, Concept and Entity Representations and their Applications, pages 79–90, Valencia, Spain. Association for Computational Linguistics.