@inproceedings{alghamdi-diab-2019-leveraging,
title = "Leveraging Pretrained Word Embeddings for Part-of-Speech Tagging of Code Switching Data",
author = "AlGhamdi, Fahad and
Diab, Mona",
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/W19-1410",
doi = "10.18653/v1/W19-1410",
pages = "99--109",
abstract = "Linguistic Code Switching (CS) is a phenomenon that occurs when multilingual speakers alternate between two or more languages/dialects within a single conversation. Processing CS data is especially challenging in intra-sentential data given state-of-the-art monolingual NLP technologies since such technologies are geared toward the processing of one language at a time. In this paper, we address the problem of Part-of-Speech tagging (POS) in the context of linguistic code switching (CS). We explore leveraging multiple neural network architectures to measure the impact of different pre-trained embeddings methods on POS tagging CS data. We investigate the landscape in four CS language pairs, Spanish-English, Hindi-English, Modern Standard Arabic- Egyptian Arabic dialect (MSA-EGY), and Modern Standard Arabic- Levantine Arabic dialect (MSA-LEV). Our results show that multilingual embedding (e.g., MSA-EGY and MSA-LEV) helps closely related languages (EGY/LEV) but adds noise to the languages that are distant (SPA/HIN). Finally, we show that our proposed models outperform state-of-the-art CS taggers for MSA-EGY language pair.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alghamdi-diab-2019-leveraging">
<titleInfo>
<title>Leveraging Pretrained Word Embeddings for Part-of-Speech Tagging of Code Switching Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fahad</namePart>
<namePart type="family">AlGhamdi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mona</namePart>
<namePart type="family">Diab</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>Linguistic Code Switching (CS) is a phenomenon that occurs when multilingual speakers alternate between two or more languages/dialects within a single conversation. Processing CS data is especially challenging in intra-sentential data given state-of-the-art monolingual NLP technologies since such technologies are geared toward the processing of one language at a time. In this paper, we address the problem of Part-of-Speech tagging (POS) in the context of linguistic code switching (CS). We explore leveraging multiple neural network architectures to measure the impact of different pre-trained embeddings methods on POS tagging CS data. We investigate the landscape in four CS language pairs, Spanish-English, Hindi-English, Modern Standard Arabic- Egyptian Arabic dialect (MSA-EGY), and Modern Standard Arabic- Levantine Arabic dialect (MSA-LEV). Our results show that multilingual embedding (e.g., MSA-EGY and MSA-LEV) helps closely related languages (EGY/LEV) but adds noise to the languages that are distant (SPA/HIN). Finally, we show that our proposed models outperform state-of-the-art CS taggers for MSA-EGY language pair.</abstract>
<identifier type="citekey">alghamdi-diab-2019-leveraging</identifier>
<identifier type="doi">10.18653/v1/W19-1410</identifier>
<location>
<url>https://aclanthology.org/W19-1410</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>99</start>
<end>109</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging Pretrained Word Embeddings for Part-of-Speech Tagging of Code Switching Data
%A AlGhamdi, Fahad
%A Diab, Mona
%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 alghamdi-diab-2019-leveraging
%X Linguistic Code Switching (CS) is a phenomenon that occurs when multilingual speakers alternate between two or more languages/dialects within a single conversation. Processing CS data is especially challenging in intra-sentential data given state-of-the-art monolingual NLP technologies since such technologies are geared toward the processing of one language at a time. In this paper, we address the problem of Part-of-Speech tagging (POS) in the context of linguistic code switching (CS). We explore leveraging multiple neural network architectures to measure the impact of different pre-trained embeddings methods on POS tagging CS data. We investigate the landscape in four CS language pairs, Spanish-English, Hindi-English, Modern Standard Arabic- Egyptian Arabic dialect (MSA-EGY), and Modern Standard Arabic- Levantine Arabic dialect (MSA-LEV). Our results show that multilingual embedding (e.g., MSA-EGY and MSA-LEV) helps closely related languages (EGY/LEV) but adds noise to the languages that are distant (SPA/HIN). Finally, we show that our proposed models outperform state-of-the-art CS taggers for MSA-EGY language pair.
%R 10.18653/v1/W19-1410
%U https://aclanthology.org/W19-1410
%U https://doi.org/10.18653/v1/W19-1410
%P 99-109
Markdown (Informal)
[Leveraging Pretrained Word Embeddings for Part-of-Speech Tagging of Code Switching Data](https://aclanthology.org/W19-1410) (AlGhamdi & Diab, VarDial 2019)
ACL