@inproceedings{iliescu-etal-2021-much,
title = "Much Gracias: Semi-supervised Code-switch Detection for {S}panish-{E}nglish: How far can we get?",
author = "Iliescu, Dana-Maria and
Grand, Rasmus and
Qirko, Sara and
van der Goot, Rob",
editor = "Solorio, Thamar and
Chen, Shuguang and
Black, Alan W. and
Diab, Mona and
Sitaram, Sunayana and
Soto, Victor and
Yilmaz, Emre and
Srinivasan, Anirudh",
booktitle = "Proceedings of the Fifth Workshop on Computational Approaches to Linguistic Code-Switching",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.calcs-1.9",
doi = "10.18653/v1/2021.calcs-1.9",
pages = "65--71",
abstract = "Because of globalization, it is becoming more and more common to use multiple languages in a single utterance, also called code-switching. This results in special linguistic structures and, therefore, poses many challenges for Natural Language Processing. Existing models for language identification in code-switched data are all supervised, requiring annotated training data which is only available for a limited number of language pairs. In this paper, we explore semi-supervised approaches, that exploit out-of-domain mono-lingual training data. We experiment with word uni-grams, word n-grams, character n-grams, Viterbi Decoding, Latent Dirichlet Allocation, Support Vector Machine and Logistic Regression. The Viterbi model was the best semi-supervised model, scoring a weighted F1 score of 92.23{\%}, whereas a fully supervised state-of-the-art BERT-based model scored 98.43{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="iliescu-etal-2021-much">
<titleInfo>
<title>Much Gracias: Semi-supervised Code-switch Detection for Spanish-English: How far can we get?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dana-Maria</namePart>
<namePart type="family">Iliescu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rasmus</namePart>
<namePart type="family">Grand</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Qirko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rob</namePart>
<namePart type="family">van der Goot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Computational Approaches to Linguistic Code-Switching</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuguang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="given">W</namePart>
<namePart type="family">Black</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mona</namePart>
<namePart type="family">Diab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunayana</namePart>
<namePart type="family">Sitaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victor</namePart>
<namePart type="family">Soto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emre</namePart>
<namePart type="family">Yilmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anirudh</namePart>
<namePart type="family">Srinivasan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Because of globalization, it is becoming more and more common to use multiple languages in a single utterance, also called code-switching. This results in special linguistic structures and, therefore, poses many challenges for Natural Language Processing. Existing models for language identification in code-switched data are all supervised, requiring annotated training data which is only available for a limited number of language pairs. In this paper, we explore semi-supervised approaches, that exploit out-of-domain mono-lingual training data. We experiment with word uni-grams, word n-grams, character n-grams, Viterbi Decoding, Latent Dirichlet Allocation, Support Vector Machine and Logistic Regression. The Viterbi model was the best semi-supervised model, scoring a weighted F1 score of 92.23%, whereas a fully supervised state-of-the-art BERT-based model scored 98.43%.</abstract>
<identifier type="citekey">iliescu-etal-2021-much</identifier>
<identifier type="doi">10.18653/v1/2021.calcs-1.9</identifier>
<location>
<url>https://aclanthology.org/2021.calcs-1.9</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>65</start>
<end>71</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Much Gracias: Semi-supervised Code-switch Detection for Spanish-English: How far can we get?
%A Iliescu, Dana-Maria
%A Grand, Rasmus
%A Qirko, Sara
%A van der Goot, Rob
%Y Solorio, Thamar
%Y Chen, Shuguang
%Y Black, Alan W.
%Y Diab, Mona
%Y Sitaram, Sunayana
%Y Soto, Victor
%Y Yilmaz, Emre
%Y Srinivasan, Anirudh
%S Proceedings of the Fifth Workshop on Computational Approaches to Linguistic Code-Switching
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F iliescu-etal-2021-much
%X Because of globalization, it is becoming more and more common to use multiple languages in a single utterance, also called code-switching. This results in special linguistic structures and, therefore, poses many challenges for Natural Language Processing. Existing models for language identification in code-switched data are all supervised, requiring annotated training data which is only available for a limited number of language pairs. In this paper, we explore semi-supervised approaches, that exploit out-of-domain mono-lingual training data. We experiment with word uni-grams, word n-grams, character n-grams, Viterbi Decoding, Latent Dirichlet Allocation, Support Vector Machine and Logistic Regression. The Viterbi model was the best semi-supervised model, scoring a weighted F1 score of 92.23%, whereas a fully supervised state-of-the-art BERT-based model scored 98.43%.
%R 10.18653/v1/2021.calcs-1.9
%U https://aclanthology.org/2021.calcs-1.9
%U https://doi.org/10.18653/v1/2021.calcs-1.9
%P 65-71
Markdown (Informal)
[Much Gracias: Semi-supervised Code-switch Detection for Spanish-English: How far can we get?](https://aclanthology.org/2021.calcs-1.9) (Iliescu et al., CALCS 2021)
ACL