@inproceedings{bernier-colborne-etal-2019-improving,
title = "Improving Cuneiform Language Identification with {BERT}",
author = "Bernier-Colborne, Gabriel and
Goutte, Cyril and
L{\'e}ger, Serge",
editor = {Zampieri, Marcos and
Nakov, Preslav and
Malmasi, Shervin and
Ljube{\v{s}}i{\'c}, Nikola and
Tiedemann, J{\"o}rg and
Ali, Ahmed},
booktitle = "Proceedings of the Sixth Workshop on {NLP} for Similar Languages, Varieties and Dialects",
month = jun,
year = "2019",
address = "Ann Arbor, Michigan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-1402",
doi = "10.18653/v1/W19-1402",
pages = "17--25",
abstract = "We describe the systems developed by the National Research Council Canada for the Cuneiform Language Identification (CLI) shared task at the 2019 VarDial evaluation campaign. We compare a state-of-the-art baseline relying on character n-grams and a traditional statistical classifier, a voting ensemble of classifiers, and a deep learning approach using a Transformer network. We describe how these systems were trained, and analyze the impact of some preprocessing and model estimation decisions. The deep neural network achieved 77{\%} accuracy on the test data, which turned out to be the best performance at the CLI evaluation, establishing a new state-of-the-art for cuneiform language identification.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bernier-colborne-etal-2019-improving">
<titleInfo>
<title>Improving Cuneiform Language Identification with BERT</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">Cyril</namePart>
<namePart type="family">Goutte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Serge</namePart>
<namePart type="family">Léger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth 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">Shervin</namePart>
<namePart type="family">Malmasi</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">Ahmed</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Ann Arbor, Michigan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe the systems developed by the National Research Council Canada for the Cuneiform Language Identification (CLI) shared task at the 2019 VarDial evaluation campaign. We compare a state-of-the-art baseline relying on character n-grams and a traditional statistical classifier, a voting ensemble of classifiers, and a deep learning approach using a Transformer network. We describe how these systems were trained, and analyze the impact of some preprocessing and model estimation decisions. The deep neural network achieved 77% accuracy on the test data, which turned out to be the best performance at the CLI evaluation, establishing a new state-of-the-art for cuneiform language identification.</abstract>
<identifier type="citekey">bernier-colborne-etal-2019-improving</identifier>
<identifier type="doi">10.18653/v1/W19-1402</identifier>
<location>
<url>https://aclanthology.org/W19-1402</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>17</start>
<end>25</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Cuneiform Language Identification with BERT
%A Bernier-Colborne, Gabriel
%A Goutte, Cyril
%A Léger, Serge
%Y Zampieri, Marcos
%Y Nakov, Preslav
%Y Malmasi, Shervin
%Y Ljubešić, Nikola
%Y Tiedemann, Jörg
%Y Ali, Ahmed
%S Proceedings of the Sixth Workshop on NLP for Similar Languages, Varieties and Dialects
%D 2019
%8 June
%I Association for Computational Linguistics
%C Ann Arbor, Michigan
%F bernier-colborne-etal-2019-improving
%X We describe the systems developed by the National Research Council Canada for the Cuneiform Language Identification (CLI) shared task at the 2019 VarDial evaluation campaign. We compare a state-of-the-art baseline relying on character n-grams and a traditional statistical classifier, a voting ensemble of classifiers, and a deep learning approach using a Transformer network. We describe how these systems were trained, and analyze the impact of some preprocessing and model estimation decisions. The deep neural network achieved 77% accuracy on the test data, which turned out to be the best performance at the CLI evaluation, establishing a new state-of-the-art for cuneiform language identification.
%R 10.18653/v1/W19-1402
%U https://aclanthology.org/W19-1402
%U https://doi.org/10.18653/v1/W19-1402
%P 17-25
Markdown (Informal)
[Improving Cuneiform Language Identification with BERT](https://aclanthology.org/W19-1402) (Bernier-Colborne et al., VarDial 2019)
ACL
- Gabriel Bernier-Colborne, Cyril Goutte, and Serge Léger. 2019. Improving Cuneiform Language Identification with BERT. In Proceedings of the Sixth Workshop on NLP for Similar Languages, Varieties and Dialects, pages 17–25, Ann Arbor, Michigan. Association for Computational Linguistics.