<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="utsumi-2018-refining">
    <titleInfo>
        <title>Refining Pretrained Word Embeddings Using Layer-wise Relevance Propagation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Akira</namePart>
        <namePart type="family">Utsumi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-oct-nov</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ellen</namePart>
            <namePart type="family">Riloff</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Chiang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Julia</namePart>
            <namePart type="family">Hockenmaier</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jun’ichi</namePart>
            <namePart type="family">Tsujii</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>In this paper, we propose a simple method for refining pretrained word embeddings using layer-wise relevance propagation. Given a target semantic representation one would like word vectors to reflect, our method first trains the mapping between the original word vectors and the target representation using a neural network. Estimated target values are then propagated backward toward word vectors, and a relevance score is computed for each dimension of word vectors. Finally, the relevance score vectors are used to refine the original word vectors so that they are projected into the subspace that reflects the information relevant to the target representation. The evaluation experiment using binary classification of word pairs demonstrates that the refined vectors by our method achieve the higher performance than the original vectors.</abstract>
    <identifier type="citekey">utsumi-2018-refining</identifier>
    <identifier type="doi">10.18653/v1/D18-1520</identifier>
    <location>
        <url>https://aclanthology.org/D18-1520</url>
    </location>
    <part>
        <date>2018-oct-nov</date>
        <extent unit="page">
            <start>4840</start>
            <end>4846</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Refining Pretrained Word Embeddings Using Layer-wise Relevance Propagation
%A Utsumi, Akira
%Y Riloff, Ellen
%Y Chiang, David
%Y Hockenmaier, Julia
%Y Tsujii, Jun’ichi
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F utsumi-2018-refining
%X In this paper, we propose a simple method for refining pretrained word embeddings using layer-wise relevance propagation. Given a target semantic representation one would like word vectors to reflect, our method first trains the mapping between the original word vectors and the target representation using a neural network. Estimated target values are then propagated backward toward word vectors, and a relevance score is computed for each dimension of word vectors. Finally, the relevance score vectors are used to refine the original word vectors so that they are projected into the subspace that reflects the information relevant to the target representation. The evaluation experiment using binary classification of word pairs demonstrates that the refined vectors by our method achieve the higher performance than the original vectors.
%R 10.18653/v1/D18-1520
%U https://aclanthology.org/D18-1520
%U https://doi.org/10.18653/v1/D18-1520
%P 4840-4846

Markdown (Informal)

[Refining Pretrained Word Embeddings Using Layer-wise Relevance Propagation](https://aclanthology.org/D18-1520) (Utsumi, EMNLP 2018)

• Refining Pretrained Word Embeddings Using Layer-wise Relevance Propagation (Utsumi, EMNLP 2018)

ACL

• Akira Utsumi. 2018. Refining Pretrained Word Embeddings Using Layer-wise Relevance Propagation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4840–4846, Brussels, Belgium. Association for Computational Linguistics.