@inproceedings{rizal-stymne-2020-evaluating,
title = "Evaluating Word Embeddings for {I}ndonesian{--}{E}nglish Code-Mixed Text Based on Synthetic Data",
author = "Rizal, Arra{'}Di Nur and
Stymne, Sara",
editor = "Solorio, Thamar and
Choudhury, Monojit and
Bali, Kalika and
Sitaram, Sunayana and
Das, Amitava and
Diab, Mona",
booktitle = "Proceedings of the 4th Workshop on Computational Approaches to Code Switching",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.calcs-1.4",
pages = "26--35",
abstract = "Code-mixed texts are abundant, especially in social media, and poses a problem for NLP tools, which are typically trained on monolingual corpora. In this paper, we explore and evaluate different types of word embeddings for Indonesian{--}English code-mixed text. We propose the use of code-mixed embeddings, i.e. embeddings trained on code-mixed text. Because large corpora of code-mixed text are required to train embeddings, we describe a method for synthesizing a code-mixed corpus, grounded in literature and a survey. Using sentiment analysis as a case study, we show that code-mixed embeddings trained on synthesized data are at least as good as cross-lingual embeddings and better than monolingual embeddings.",
language = "English",
ISBN = "979-10-95546-66-5",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rizal-stymne-2020-evaluating">
<titleInfo>
<title>Evaluating Word Embeddings for Indonesian–English Code-Mixed Text Based on Synthetic Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arra’Di</namePart>
<namePart type="given">Nur</namePart>
<namePart type="family">Rizal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Stymne</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 4th Workshop on Computational Approaches to 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">Monojit</namePart>
<namePart type="family">Choudhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</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">Amitava</namePart>
<namePart type="family">Das</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>
<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">979-10-95546-66-5</identifier>
</relatedItem>
<abstract>Code-mixed texts are abundant, especially in social media, and poses a problem for NLP tools, which are typically trained on monolingual corpora. In this paper, we explore and evaluate different types of word embeddings for Indonesian–English code-mixed text. We propose the use of code-mixed embeddings, i.e. embeddings trained on code-mixed text. Because large corpora of code-mixed text are required to train embeddings, we describe a method for synthesizing a code-mixed corpus, grounded in literature and a survey. Using sentiment analysis as a case study, we show that code-mixed embeddings trained on synthesized data are at least as good as cross-lingual embeddings and better than monolingual embeddings.</abstract>
<identifier type="citekey">rizal-stymne-2020-evaluating</identifier>
<location>
<url>https://aclanthology.org/2020.calcs-1.4</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>26</start>
<end>35</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Word Embeddings for Indonesian–English Code-Mixed Text Based on Synthetic Data
%A Rizal, Arra’Di Nur
%A Stymne, Sara
%Y Solorio, Thamar
%Y Choudhury, Monojit
%Y Bali, Kalika
%Y Sitaram, Sunayana
%Y Das, Amitava
%Y Diab, Mona
%S Proceedings of the 4th Workshop on Computational Approaches to Code Switching
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-66-5
%G English
%F rizal-stymne-2020-evaluating
%X Code-mixed texts are abundant, especially in social media, and poses a problem for NLP tools, which are typically trained on monolingual corpora. In this paper, we explore and evaluate different types of word embeddings for Indonesian–English code-mixed text. We propose the use of code-mixed embeddings, i.e. embeddings trained on code-mixed text. Because large corpora of code-mixed text are required to train embeddings, we describe a method for synthesizing a code-mixed corpus, grounded in literature and a survey. Using sentiment analysis as a case study, we show that code-mixed embeddings trained on synthesized data are at least as good as cross-lingual embeddings and better than monolingual embeddings.
%U https://aclanthology.org/2020.calcs-1.4
%P 26-35
Markdown (Informal)
[Evaluating Word Embeddings for Indonesian–English Code-Mixed Text Based on Synthetic Data](https://aclanthology.org/2020.calcs-1.4) (Rizal & Stymne, CALCS 2020)
ACL