@inproceedings{winata-etal-2018-bilingual,
title = "Bilingual Character Representation for Efficiently Addressing Out-of-Vocabulary Words in Code-Switching Named Entity Recognition",
author = "Winata, Genta Indra and
Wu, Chien-Sheng and
Madotto, Andrea and
Fung, Pascale",
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/W18-3214",
doi = "10.18653/v1/W18-3214",
pages = "110--114",
abstract = "We propose an LSTM-based model with hierarchical architecture on named entity recognition from code-switching Twitter data. Our model uses bilingual character representation and transfer learning to address out-of-vocabulary words. In order to mitigate data noise, we propose to use token replacement and normalization. In the 3rd Workshop on Computational Approaches to Linguistic Code-Switching Shared Task, we achieved second place with 62.76{\%} harmonic mean F1-score for English-Spanish language pair without using any gazetteer and knowledge-based information.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="winata-etal-2018-bilingual">
<titleInfo>
<title>Bilingual Character Representation for Efficiently Addressing Out-of-Vocabulary Words in Code-Switching Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Genta</namePart>
<namePart type="given">Indra</namePart>
<namePart type="family">Winata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chien-Sheng</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Madotto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pascale</namePart>
<namePart type="family">Fung</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>We propose an LSTM-based model with hierarchical architecture on named entity recognition from code-switching Twitter data. Our model uses bilingual character representation and transfer learning to address out-of-vocabulary words. In order to mitigate data noise, we propose to use token replacement and normalization. In the 3rd Workshop on Computational Approaches to Linguistic Code-Switching Shared Task, we achieved second place with 62.76% harmonic mean F1-score for English-Spanish language pair without using any gazetteer and knowledge-based information.</abstract>
<identifier type="citekey">winata-etal-2018-bilingual</identifier>
<identifier type="doi">10.18653/v1/W18-3214</identifier>
<location>
<url>https://aclanthology.org/W18-3214</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>110</start>
<end>114</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bilingual Character Representation for Efficiently Addressing Out-of-Vocabulary Words in Code-Switching Named Entity Recognition
%A Winata, Genta Indra
%A Wu, Chien-Sheng
%A Madotto, Andrea
%A Fung, Pascale
%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 winata-etal-2018-bilingual
%X We propose an LSTM-based model with hierarchical architecture on named entity recognition from code-switching Twitter data. Our model uses bilingual character representation and transfer learning to address out-of-vocabulary words. In order to mitigate data noise, we propose to use token replacement and normalization. In the 3rd Workshop on Computational Approaches to Linguistic Code-Switching Shared Task, we achieved second place with 62.76% harmonic mean F1-score for English-Spanish language pair without using any gazetteer and knowledge-based information.
%R 10.18653/v1/W18-3214
%U https://aclanthology.org/W18-3214
%U https://doi.org/10.18653/v1/W18-3214
%P 110-114
Markdown (Informal)
[Bilingual Character Representation for Efficiently Addressing Out-of-Vocabulary Words in Code-Switching Named Entity Recognition](https://aclanthology.org/W18-3214) (Winata et al., ACL 2018)
ACL