@inproceedings{king-cook-2020-evaluating,
title = "Evaluating Approaches to Personalizing Language Models",
author = "King, Milton and
Cook, Paul",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.299",
pages = "2461--2469",
abstract = "In this work, we consider the problem of personalizing language models, that is, building language models that are tailored to the writing style of an individual. Because training language models requires a large amount of text, and individuals do not necessarily possess a large corpus of their writing that could be used for training, approaches to personalizing language models must be able to rely on only a small amount of text from any one user. In this work, we compare three approaches to personalizing a language model that was trained on a large background corpus using a relatively small amount of text from an individual user. We evaluate these approaches using perplexity, as well as two measures based on next word prediction for smartphone soft keyboards. Our results show that when only a small amount of user-specific text is available, an approach based on priming gives the most improvement, while when larger amounts of user-specific text are available, an approach based on language model interpolation performs best. We carry out further experiments to show that these approaches to personalization outperform language model adaptation based on demographic factors.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="king-cook-2020-evaluating">
<titleInfo>
<title>Evaluating Approaches to Personalizing Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Milton</namePart>
<namePart type="family">King</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Cook</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>In this work, we consider the problem of personalizing language models, that is, building language models that are tailored to the writing style of an individual. Because training language models requires a large amount of text, and individuals do not necessarily possess a large corpus of their writing that could be used for training, approaches to personalizing language models must be able to rely on only a small amount of text from any one user. In this work, we compare three approaches to personalizing a language model that was trained on a large background corpus using a relatively small amount of text from an individual user. We evaluate these approaches using perplexity, as well as two measures based on next word prediction for smartphone soft keyboards. Our results show that when only a small amount of user-specific text is available, an approach based on priming gives the most improvement, while when larger amounts of user-specific text are available, an approach based on language model interpolation performs best. We carry out further experiments to show that these approaches to personalization outperform language model adaptation based on demographic factors.</abstract>
<identifier type="citekey">king-cook-2020-evaluating</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.299</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>2461</start>
<end>2469</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Approaches to Personalizing Language Models
%A King, Milton
%A Cook, Paul
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F king-cook-2020-evaluating
%X In this work, we consider the problem of personalizing language models, that is, building language models that are tailored to the writing style of an individual. Because training language models requires a large amount of text, and individuals do not necessarily possess a large corpus of their writing that could be used for training, approaches to personalizing language models must be able to rely on only a small amount of text from any one user. In this work, we compare three approaches to personalizing a language model that was trained on a large background corpus using a relatively small amount of text from an individual user. We evaluate these approaches using perplexity, as well as two measures based on next word prediction for smartphone soft keyboards. Our results show that when only a small amount of user-specific text is available, an approach based on priming gives the most improvement, while when larger amounts of user-specific text are available, an approach based on language model interpolation performs best. We carry out further experiments to show that these approaches to personalization outperform language model adaptation based on demographic factors.
%U https://aclanthology.org/2020.lrec-1.299
%P 2461-2469
Markdown (Informal)
[Evaluating Approaches to Personalizing Language Models](https://aclanthology.org/2020.lrec-1.299) (King & Cook, LREC 2020)
ACL