@inproceedings{aguilar-etal-2020-lince,
title = "{L}in{CE}: A Centralized Benchmark for Linguistic Code-switching Evaluation",
author = "Aguilar, Gustavo and
Kar, Sudipta and
Solorio, Thamar",
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-1.223",
pages = "1803--1813",
abstract = "Recent trends in NLP research have raised an interest in linguistic code-switching (CS); modern approaches have been proposed to solve a wide range of NLP tasks on multiple language pairs. Unfortunately, these proposed methods are hardly generalizable to different code-switched languages. In addition, it is unclear whether a model architecture is applicable for a different task while still being compatible with the code-switching setting. This is mainly because of the lack of a centralized benchmark and the sparse corpora that researchers employ based on their specific needs and interests. To facilitate research in this direction, we propose a centralized benchmark for Linguistic Code-switching Evaluation (LinCE) that combines eleven corpora covering four different code-switched language pairs (i.e., Spanish-English, Nepali-English, Hindi-English, and Modern Standard Arabic-Egyptian Arabic) and four tasks (i.e., language identification, named entity recognition, part-of-speech tagging, and sentiment analysis). As part of the benchmark centralization effort, we provide an online platform where researchers can submit their results while comparing with others in real-time. In addition, we provide the scores of different popular models, including LSTM, ELMo, and multilingual BERT so that the NLP community can compare against state-of-the-art systems. LinCE is a continuous effort, and we will expand it with more low-resource languages and tasks.",
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="aguilar-etal-2020-lince">
<titleInfo>
<title>LinCE: A Centralized Benchmark for Linguistic Code-switching Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gustavo</namePart>
<namePart type="family">Aguilar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudipta</namePart>
<namePart type="family">Kar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</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>Recent trends in NLP research have raised an interest in linguistic code-switching (CS); modern approaches have been proposed to solve a wide range of NLP tasks on multiple language pairs. Unfortunately, these proposed methods are hardly generalizable to different code-switched languages. In addition, it is unclear whether a model architecture is applicable for a different task while still being compatible with the code-switching setting. This is mainly because of the lack of a centralized benchmark and the sparse corpora that researchers employ based on their specific needs and interests. To facilitate research in this direction, we propose a centralized benchmark for Linguistic Code-switching Evaluation (LinCE) that combines eleven corpora covering four different code-switched language pairs (i.e., Spanish-English, Nepali-English, Hindi-English, and Modern Standard Arabic-Egyptian Arabic) and four tasks (i.e., language identification, named entity recognition, part-of-speech tagging, and sentiment analysis). As part of the benchmark centralization effort, we provide an online platform where researchers can submit their results while comparing with others in real-time. In addition, we provide the scores of different popular models, including LSTM, ELMo, and multilingual BERT so that the NLP community can compare against state-of-the-art systems. LinCE is a continuous effort, and we will expand it with more low-resource languages and tasks.</abstract>
<identifier type="citekey">aguilar-etal-2020-lince</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.223</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>1803</start>
<end>1813</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LinCE: A Centralized Benchmark for Linguistic Code-switching Evaluation
%A Aguilar, Gustavo
%A Kar, Sudipta
%A Solorio, Thamar
%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 aguilar-etal-2020-lince
%X Recent trends in NLP research have raised an interest in linguistic code-switching (CS); modern approaches have been proposed to solve a wide range of NLP tasks on multiple language pairs. Unfortunately, these proposed methods are hardly generalizable to different code-switched languages. In addition, it is unclear whether a model architecture is applicable for a different task while still being compatible with the code-switching setting. This is mainly because of the lack of a centralized benchmark and the sparse corpora that researchers employ based on their specific needs and interests. To facilitate research in this direction, we propose a centralized benchmark for Linguistic Code-switching Evaluation (LinCE) that combines eleven corpora covering four different code-switched language pairs (i.e., Spanish-English, Nepali-English, Hindi-English, and Modern Standard Arabic-Egyptian Arabic) and four tasks (i.e., language identification, named entity recognition, part-of-speech tagging, and sentiment analysis). As part of the benchmark centralization effort, we provide an online platform where researchers can submit their results while comparing with others in real-time. In addition, we provide the scores of different popular models, including LSTM, ELMo, and multilingual BERT so that the NLP community can compare against state-of-the-art systems. LinCE is a continuous effort, and we will expand it with more low-resource languages and tasks.
%U https://aclanthology.org/2020.lrec-1.223
%P 1803-1813
Markdown (Informal)
[LinCE: A Centralized Benchmark for Linguistic Code-switching Evaluation](https://aclanthology.org/2020.lrec-1.223) (Aguilar et al., LREC 2020)
ACL