<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shi-etal-2016-real">
    <titleInfo>
        <title>Real Multi-Sense or Pseudo Multi-Sense: An Approach to Improve Word Representation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Haoyue</namePart>
        <namePart type="family">Shi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Caihua</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Junfeng</namePart>
        <namePart type="family">Hu</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 the Workshop on Computational Linguistics for Linguistic Complexity (CL4LC)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Dominique</namePart>
            <namePart type="family">Brunato</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Felice</namePart>
            <namePart type="family">Dell’Orletta</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Giulia</namePart>
            <namePart type="family">Venturi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Thomas</namePart>
            <namePart type="family">François</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Philippe</namePart>
            <namePart type="family">Blache</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>Previous researches have shown that learning multiple representations for polysemous words can improve the performance of word embeddings on many tasks. However, this leads to another problem. Several vectors of a word may actually point to the same meaning, namely pseudo multi-sense. In this paper, we introduce the concept of pseudo multi-sense, and then propose an algorithm to detect such cases. With the consideration of the detected pseudo multi-sense cases, we try to refine the existing word embeddings to eliminate the influence of pseudo multi-sense. Moreover, we apply our algorithm on previous released multi-sense word embeddings and tested it on artificial word similarity tasks and the analogy task. The result of the experiments shows that diminishing pseudo multi-sense can improve the quality of word representations. Thus, our method is actually an efficient way to reduce linguistic complexity.</abstract>
    <identifier type="citekey">shi-etal-2016-real</identifier>
    <location>
        <url>https://aclanthology.org/W16-4109</url>
    </location>
    <part>
        <date>2016-12</date>
        <extent unit="page">
            <start>79</start>
            <end>88</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Real Multi-Sense or Pseudo Multi-Sense: An Approach to Improve Word Representation
%A Shi, Haoyue
%A Li, Caihua
%A Hu, Junfeng
%Y Brunato, Dominique
%Y Dell’Orletta, Felice
%Y Venturi, Giulia
%Y François, Thomas
%Y Blache, Philippe
%S Proceedings of the Workshop on Computational Linguistics for Linguistic Complexity (CL4LC)
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F shi-etal-2016-real
%X Previous researches have shown that learning multiple representations for polysemous words can improve the performance of word embeddings on many tasks. However, this leads to another problem. Several vectors of a word may actually point to the same meaning, namely pseudo multi-sense. In this paper, we introduce the concept of pseudo multi-sense, and then propose an algorithm to detect such cases. With the consideration of the detected pseudo multi-sense cases, we try to refine the existing word embeddings to eliminate the influence of pseudo multi-sense. Moreover, we apply our algorithm on previous released multi-sense word embeddings and tested it on artificial word similarity tasks and the analogy task. The result of the experiments shows that diminishing pseudo multi-sense can improve the quality of word representations. Thus, our method is actually an efficient way to reduce linguistic complexity.
%U https://aclanthology.org/W16-4109
%P 79-88

Markdown (Informal)

[Real Multi-Sense or Pseudo Multi-Sense: An Approach to Improve Word Representation](https://aclanthology.org/W16-4109) (Shi et al., CL4LC 2016)

• Real Multi-Sense or Pseudo Multi-Sense: An Approach to Improve Word Representation (Shi et al., CL4LC 2016)

ACL

• Haoyue Shi, Caihua Li, and Junfeng Hu. 2016. Real Multi-Sense or Pseudo Multi-Sense: An Approach to Improve Word Representation. In Proceedings of the Workshop on Computational Linguistics for Linguistic Complexity (CL4LC), pages 79–88, Osaka, Japan. The COLING 2016 Organizing Committee.