<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kawakami-etal-2017-learning">
    <titleInfo>
        <title>Learning to Create and Reuse Words in Open-Vocabulary Neural Language Modeling</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Kazuya</namePart>
        <namePart type="family">Kawakami</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chris</namePart>
        <namePart type="family">Dyer</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Phil</namePart>
        <namePart type="family">Blunsom</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Regina</namePart>
            <namePart type="family">Barzilay</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Min-Yen</namePart>
            <namePart type="family">Kan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vancouver, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Fixed-vocabulary language models fail to account for one of the most characteristic statistical facts of natural language: the frequent creation and reuse of new word types. Although character-level language models offer a partial solution in that they can create word types not attested in the training corpus, they do not capture the “bursty” distribution of such words. In this paper, we augment a hierarchical LSTM language model that generates sequences of word tokens character by character with a caching mechanism that learns to reuse previously generated words. To validate our model we construct a new open-vocabulary language modeling corpus (the Multilingual Wikipedia Corpus; MWC) from comparable Wikipedia articles in 7 typologically diverse languages and demonstrate the effectiveness of our model across this range of languages.</abstract>
    <identifier type="citekey">kawakami-etal-2017-learning</identifier>
    <identifier type="doi">10.18653/v1/P17-1137</identifier>
    <location>
        <url>https://aclanthology.org/P17-1137</url>
    </location>
    <part>
        <date>2017-07</date>
        <extent unit="page">
            <start>1492</start>
            <end>1502</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Learning to Create and Reuse Words in Open-Vocabulary Neural Language Modeling
%A Kawakami, Kazuya
%A Dyer, Chris
%A Blunsom, Phil
%Y Barzilay, Regina
%Y Kan, Min-Yen
%S Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2017
%8 July
%I Association for Computational Linguistics
%C Vancouver, Canada
%F kawakami-etal-2017-learning
%X Fixed-vocabulary language models fail to account for one of the most characteristic statistical facts of natural language: the frequent creation and reuse of new word types. Although character-level language models offer a partial solution in that they can create word types not attested in the training corpus, they do not capture the “bursty” distribution of such words. In this paper, we augment a hierarchical LSTM language model that generates sequences of word tokens character by character with a caching mechanism that learns to reuse previously generated words. To validate our model we construct a new open-vocabulary language modeling corpus (the Multilingual Wikipedia Corpus; MWC) from comparable Wikipedia articles in 7 typologically diverse languages and demonstrate the effectiveness of our model across this range of languages.
%R 10.18653/v1/P17-1137
%U https://aclanthology.org/P17-1137
%U https://doi.org/10.18653/v1/P17-1137
%P 1492-1502

Markdown (Informal)

[Learning to Create and Reuse Words in Open-Vocabulary Neural Language Modeling](https://aclanthology.org/P17-1137) (Kawakami et al., ACL 2017)

• Learning to Create and Reuse Words in Open-Vocabulary Neural Language Modeling (Kawakami et al., ACL 2017)

ACL

• Kazuya Kawakami, Chris Dyer, and Phil Blunsom. 2017. Learning to Create and Reuse Words in Open-Vocabulary Neural Language Modeling. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1492–1502, Vancouver, Canada. Association for Computational Linguistics.