<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="grave-etal-2019-training">
    <titleInfo>
        <title>Training Hybrid Language Models by Marginalizing over Segmentations</title>
    </titleInfo>
    <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">Sainbayar</namePart>
        <namePart type="family">Sukhbaatar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <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">Armand</namePart>
        <namePart type="family">Joulin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Korhonen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Traum</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Màrquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Florence, Italy</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In this paper, we study the problem of hybrid language modeling, that is using models which can predict both characters and larger units such as character ngrams or words. Using such models, multiple potential segmentations usually exist for a given string, for example one using words and one using characters only. Thus, the probability of a string is the sum of the probabilities of all the possible segmentations. Here, we show how it is possible to marginalize over the segmentations efficiently, in order to compute the true probability of a sequence. We apply our technique on three datasets, comprising seven languages, showing improvements over a strong character level language model.</abstract>
    <identifier type="citekey">grave-etal-2019-training</identifier>
    <identifier type="doi">10.18653/v1/P19-1143</identifier>
    <location>
        <url>https://aclanthology.org/P19-1143</url>
    </location>
    <part>
        <date>2019-07</date>
        <extent unit="page">
            <start>1477</start>
            <end>1482</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Training Hybrid Language Models by Marginalizing over Segmentations
%A Grave, Edouard
%A Sukhbaatar, Sainbayar
%A Bojanowski, Piotr
%A Joulin, Armand
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F grave-etal-2019-training
%X In this paper, we study the problem of hybrid language modeling, that is using models which can predict both characters and larger units such as character ngrams or words. Using such models, multiple potential segmentations usually exist for a given string, for example one using words and one using characters only. Thus, the probability of a string is the sum of the probabilities of all the possible segmentations. Here, we show how it is possible to marginalize over the segmentations efficiently, in order to compute the true probability of a sequence. We apply our technique on three datasets, comprising seven languages, showing improvements over a strong character level language model.
%R 10.18653/v1/P19-1143
%U https://aclanthology.org/P19-1143
%U https://doi.org/10.18653/v1/P19-1143
%P 1477-1482

Markdown (Informal)

[Training Hybrid Language Models by Marginalizing over Segmentations](https://aclanthology.org/P19-1143) (Grave et al., ACL 2019)

• Training Hybrid Language Models by Marginalizing over Segmentations (Grave et al., ACL 2019)

ACL

• Edouard Grave, Sainbayar Sukhbaatar, Piotr Bojanowski, and Armand Joulin. 2019. Training Hybrid Language Models by Marginalizing over Segmentations. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1477–1482, Florence, Italy. Association for Computational Linguistics.