<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bojanowski-etal-2017-enriching">
    <titleInfo>
        <title>Enriching Word Vectors with Subword Information</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Piotr</namePart>
        <namePart type="family">Bojanowski</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Edouard</namePart>
        <namePart type="family">Grave</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Armand</namePart>
        <namePart type="family">Joulin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tomas</namePart>
        <namePart type="family">Mikolov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017</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>Continuous word representations, trained on large unlabeled corpora are useful for many natural language processing tasks. Popular models that learn such representations ignore the morphology of words, by assigning a distinct vector to each word. This is a limitation, especially for languages with large vocabularies and many rare words. In this paper, we propose a new approach based on the skipgram model, where each word is represented as a bag of character n-grams. A vector representation is associated to each character n-gram; words being represented as the sum of these representations. Our method is fast, allowing to train models on large corpora quickly and allows us to compute word representations for words that did not appear in the training data. We evaluate our word representations on nine different languages, both on word similarity and analogy tasks. By comparing to recently proposed morphological word representations, we show that our vectors achieve state-of-the-art performance on these tasks.</abstract>
    <identifier type="citekey">bojanowski-etal-2017-enriching</identifier>
    <identifier type="doi">10.1162/tacl_a_00051</identifier>
    <location>
        <url>https://aclanthology.org/Q17-1010</url>
    </location>
    <part>
        <date>2017</date>
        <detail type="volume"><number>5</number></detail>
        <extent unit="page">
            <start>135</start>
            <end>146</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Enriching Word Vectors with Subword Information
%A Bojanowski, Piotr
%A Grave, Edouard
%A Joulin, Armand
%A Mikolov, Tomas
%J Transactions of the Association for Computational Linguistics
%D 2017
%V 5
%I MIT Press
%C Cambridge, MA
%F bojanowski-etal-2017-enriching
%X Continuous word representations, trained on large unlabeled corpora are useful for many natural language processing tasks. Popular models that learn such representations ignore the morphology of words, by assigning a distinct vector to each word. This is a limitation, especially for languages with large vocabularies and many rare words. In this paper, we propose a new approach based on the skipgram model, where each word is represented as a bag of character n-grams. A vector representation is associated to each character n-gram; words being represented as the sum of these representations. Our method is fast, allowing to train models on large corpora quickly and allows us to compute word representations for words that did not appear in the training data. We evaluate our word representations on nine different languages, both on word similarity and analogy tasks. By comparing to recently proposed morphological word representations, we show that our vectors achieve state-of-the-art performance on these tasks.
%R 10.1162/tacl_a_00051
%U https://aclanthology.org/Q17-1010
%U https://doi.org/10.1162/tacl_a_00051
%P 135-146

Markdown (Informal)

[Enriching Word Vectors with Subword Information](https://aclanthology.org/Q17-1010) (Bojanowski et al., TACL 2017)

• Enriching Word Vectors with Subword Information (Bojanowski et al., TACL 2017)

ACL

• Piotr Bojanowski, Edouard Grave, Armand Joulin, and Tomas Mikolov. 2017. Enriching Word Vectors with Subword Information. Transactions of the Association for Computational Linguistics, 5:135–146.