@inproceedings{bernier-colborne-etal-2021-n,
title = "N-gram and Neural Models for {U}ralic Language Identification: {NRC} at {V}ar{D}ial 2021",
author = "Bernier-Colborne, Gabriel and
Leger, Serge and
Goutte, Cyril",
editor = {Zampieri, Marcos and
Nakov, Preslav and
Ljube{\v{s}}i{\'c}, Nikola and
Tiedemann, J{\"o}rg and
Scherrer, Yves and
Jauhiainen, Tommi},
booktitle = "Proceedings of the Eighth Workshop on NLP for Similar Languages, Varieties and Dialects",
month = apr,
year = "2021",
address = "Kiyv, Ukraine",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.vardial-1.15/",
pages = "128--134",
abstract = "We describe the systems developed by the National Research Council Canada for the Uralic language identification shared task at the 2021 VarDial evaluation campaign. We evaluated two different approaches to this task: a probabilistic classifier exploiting only character 5-grams as features, and a character-based neural network pre-trained through self-supervision, then fine-tuned on the language identification task. The former method turned out to perform better, which casts doubt on the usefulness of deep learning methods for language identification, where they have yet to convincingly and consistently outperform simpler and less costly classification algorithms exploiting n-gram features."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bernier-colborne-etal-2021-n">
<titleInfo>
<title>N-gram and Neural Models for Uralic Language Identification: NRC at VarDial 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Bernier-Colborne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Serge</namePart>
<namePart type="family">Leger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cyril</namePart>
<namePart type="family">Goutte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth Workshop on NLP for Similar Languages, Varieties and Dialects</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Scherrer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tommi</namePart>
<namePart type="family">Jauhiainen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kiyv, Ukraine</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe the systems developed by the National Research Council Canada for the Uralic language identification shared task at the 2021 VarDial evaluation campaign. We evaluated two different approaches to this task: a probabilistic classifier exploiting only character 5-grams as features, and a character-based neural network pre-trained through self-supervision, then fine-tuned on the language identification task. The former method turned out to perform better, which casts doubt on the usefulness of deep learning methods for language identification, where they have yet to convincingly and consistently outperform simpler and less costly classification algorithms exploiting n-gram features.</abstract>
<identifier type="citekey">bernier-colborne-etal-2021-n</identifier>
<location>
<url>https://aclanthology.org/2021.vardial-1.15/</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>128</start>
<end>134</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T N-gram and Neural Models for Uralic Language Identification: NRC at VarDial 2021
%A Bernier-Colborne, Gabriel
%A Leger, Serge
%A Goutte, Cyril
%Y Zampieri, Marcos
%Y Nakov, Preslav
%Y Ljubešić, Nikola
%Y Tiedemann, Jörg
%Y Scherrer, Yves
%Y Jauhiainen, Tommi
%S Proceedings of the Eighth Workshop on NLP for Similar Languages, Varieties and Dialects
%D 2021
%8 April
%I Association for Computational Linguistics
%C Kiyv, Ukraine
%F bernier-colborne-etal-2021-n
%X We describe the systems developed by the National Research Council Canada for the Uralic language identification shared task at the 2021 VarDial evaluation campaign. We evaluated two different approaches to this task: a probabilistic classifier exploiting only character 5-grams as features, and a character-based neural network pre-trained through self-supervision, then fine-tuned on the language identification task. The former method turned out to perform better, which casts doubt on the usefulness of deep learning methods for language identification, where they have yet to convincingly and consistently outperform simpler and less costly classification algorithms exploiting n-gram features.
%U https://aclanthology.org/2021.vardial-1.15/
%P 128-134
Markdown (Informal)
[N-gram and Neural Models for Uralic Language Identification: NRC at VarDial 2021](https://aclanthology.org/2021.vardial-1.15/) (Bernier-Colborne et al., VarDial 2021)
ACL