<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="osborne-etal-2016-encoding">
    <titleInfo>
        <title>Encoding Prior Knowledge with Eigenword Embeddings</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Dominique</namePart>
        <namePart type="family">Osborne</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shashi</namePart>
        <namePart type="family">Narayan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shay</namePart>
        <namePart type="given">B</namePart>
        <namePart type="family">Cohen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2016</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Canonical correlation analysis (CCA) is a method for reducing the dimension of data represented using two views. It has been previously used to derive word embeddings, where one view indicates a word, and the other view indicates its context. We describe a way to incorporate prior knowledge into CCA, give a theoretical justification for it, and test it by deriving word embeddings and evaluating them on a myriad of datasets.</abstract>
    <identifier type="citekey">osborne-etal-2016-encoding</identifier>
    <identifier type="doi">10.1162/tacl_a_00108</identifier>
    <location>
        <url>https://aclanthology.org/Q16-1030</url>
    </location>
    <part>
        <date>2016</date>
        <detail type="volume"><number>4</number></detail>
        <extent unit="page">
            <start>417</start>
            <end>430</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Encoding Prior Knowledge with Eigenword Embeddings
%A Osborne, Dominique
%A Narayan, Shashi
%A Cohen, Shay B.
%J Transactions of the Association for Computational Linguistics
%D 2016
%V 4
%I MIT Press
%C Cambridge, MA
%F osborne-etal-2016-encoding
%X Canonical correlation analysis (CCA) is a method for reducing the dimension of data represented using two views. It has been previously used to derive word embeddings, where one view indicates a word, and the other view indicates its context. We describe a way to incorporate prior knowledge into CCA, give a theoretical justification for it, and test it by deriving word embeddings and evaluating them on a myriad of datasets.
%R 10.1162/tacl_a_00108
%U https://aclanthology.org/Q16-1030
%U https://doi.org/10.1162/tacl_a_00108
%P 417-430

Markdown (Informal)

[Encoding Prior Knowledge with Eigenword Embeddings](https://aclanthology.org/Q16-1030) (Osborne et al., TACL 2016)

• Encoding Prior Knowledge with Eigenword Embeddings (Osborne et al., TACL 2016)

ACL

• Dominique Osborne, Shashi Narayan, and Shay B. Cohen. 2016. Encoding Prior Knowledge with Eigenword Embeddings. Transactions of the Association for Computational Linguistics, 4:417–430.