@inproceedings{jain-etal-2018-simple,
title = "Simple Features for Strong Performance on Named Entity Recognition in Code-Switched {T}witter Data",
author = "Jain, Devanshu and
Kustikova, Maria and
Darbari, Mayank and
Gupta, Rishabh and
Mayhew, Stephen",
editor = "Aguilar, Gustavo and
AlGhamdi, Fahad and
Soto, Victor and
Solorio, Thamar and
Diab, Mona and
Hirschberg, Julia",
booktitle = "Proceedings of the Third Workshop on Computational Approaches to Linguistic Code-Switching",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-3213",
doi = "10.18653/v1/W18-3213",
pages = "103--109",
abstract = "In this work, we address the problem of Named Entity Recognition (NER) in code-switched tweets as a part of the Workshop on Computational Approaches to Linguistic Code-switching (CALCS) at ACL{'}18. Code-switching is the phenomenon where a speaker switches between two languages or variants of the same language within or across utterances, known as intra-sentential or inter-sentential code-switching, respectively. Processing such data is challenging using state of the art methods since such technology is generally geared towards processing monolingual text. In this paper we explored ways to use language identification and translation to recognize named entities in such data, however, utilizing simple features (sans multi-lingual features) with Conditional Random Field (CRF) classifier achieved the best results. Our experiments were mainly aimed at the (ENG-SPA) English-Spanish dataset but we submitted a language-independent version of our system to the (MSA-EGY) Arabic-Egyptian dataset as well and achieved good results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jain-etal-2018-simple">
<titleInfo>
<title>Simple Features for Strong Performance on Named Entity Recognition in Code-Switched Twitter Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Devanshu</namePart>
<namePart type="family">Jain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Kustikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mayank</namePart>
<namePart type="family">Darbari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rishabh</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Mayhew</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Computational Approaches to Linguistic Code-Switching</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gustavo</namePart>
<namePart type="family">Aguilar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fahad</namePart>
<namePart type="family">AlGhamdi</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">Thamar</namePart>
<namePart type="family">Solorio</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">Julia</namePart>
<namePart type="family">Hirschberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work, we address the problem of Named Entity Recognition (NER) in code-switched tweets as a part of the Workshop on Computational Approaches to Linguistic Code-switching (CALCS) at ACL’18. Code-switching is the phenomenon where a speaker switches between two languages or variants of the same language within or across utterances, known as intra-sentential or inter-sentential code-switching, respectively. Processing such data is challenging using state of the art methods since such technology is generally geared towards processing monolingual text. In this paper we explored ways to use language identification and translation to recognize named entities in such data, however, utilizing simple features (sans multi-lingual features) with Conditional Random Field (CRF) classifier achieved the best results. Our experiments were mainly aimed at the (ENG-SPA) English-Spanish dataset but we submitted a language-independent version of our system to the (MSA-EGY) Arabic-Egyptian dataset as well and achieved good results.</abstract>
<identifier type="citekey">jain-etal-2018-simple</identifier>
<identifier type="doi">10.18653/v1/W18-3213</identifier>
<location>
<url>https://aclanthology.org/W18-3213</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>103</start>
<end>109</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Simple Features for Strong Performance on Named Entity Recognition in Code-Switched Twitter Data
%A Jain, Devanshu
%A Kustikova, Maria
%A Darbari, Mayank
%A Gupta, Rishabh
%A Mayhew, Stephen
%Y Aguilar, Gustavo
%Y AlGhamdi, Fahad
%Y Soto, Victor
%Y Solorio, Thamar
%Y Diab, Mona
%Y Hirschberg, Julia
%S Proceedings of the Third Workshop on Computational Approaches to Linguistic Code-Switching
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F jain-etal-2018-simple
%X In this work, we address the problem of Named Entity Recognition (NER) in code-switched tweets as a part of the Workshop on Computational Approaches to Linguistic Code-switching (CALCS) at ACL’18. Code-switching is the phenomenon where a speaker switches between two languages or variants of the same language within or across utterances, known as intra-sentential or inter-sentential code-switching, respectively. Processing such data is challenging using state of the art methods since such technology is generally geared towards processing monolingual text. In this paper we explored ways to use language identification and translation to recognize named entities in such data, however, utilizing simple features (sans multi-lingual features) with Conditional Random Field (CRF) classifier achieved the best results. Our experiments were mainly aimed at the (ENG-SPA) English-Spanish dataset but we submitted a language-independent version of our system to the (MSA-EGY) Arabic-Egyptian dataset as well and achieved good results.
%R 10.18653/v1/W18-3213
%U https://aclanthology.org/W18-3213
%U https://doi.org/10.18653/v1/W18-3213
%P 103-109
Markdown (Informal)
[Simple Features for Strong Performance on Named Entity Recognition in Code-Switched Twitter Data](https://aclanthology.org/W18-3213) (Jain et al., ACL 2018)
ACL
