@inproceedings{geetha-etal-2018-tackling,
title = "Tackling Code-Switched {NER}: Participation of {CMU}",
author = "Geetha, Parvathy and
Chandu, Khyathi and
Black, Alan W",
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/W18-3217",
doi = "10.18653/v1/W18-3217",
pages = "126--131",
abstract = "Named Entity Recognition plays a major role in several downstream applications in NLP. Though this task has been heavily studied in formal monolingual texts and also noisy texts like Twitter data, it is still an emerging task in code-switched (CS) content on social media. This paper describes our participation in the shared task of NER on code-switched data for Spanglish (Spanish + English) and Arabish (Arabic + English). In this paper we describe models that intuitively developed from the data for the shared task Named Entity Recognition on Code-switched Data. Owing to the sparse and non-linear relationships between words in Twitter data, we explored neural architectures that are capable of non-linearities fairly well. In specific, we trained character level models and word level models based on Bidirectional LSTMs (Bi-LSTMs) to perform sequential tagging. We train multiple models to identify nominal mentions and subsequently use this information to predict the labels of named entity in a sequence. Our best model is a character level model along with word level pre-trained multilingual embeddings that gave an F-score of 56.72 in Spanglish and a word level model that gave an F-score of 65.02 in Arabish on the test data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="geetha-etal-2018-tackling">
<titleInfo>
<title>Tackling Code-Switched NER: Participation of CMU</title>
</titleInfo>
<name type="personal">
<namePart type="given">Parvathy</namePart>
<namePart type="family">Geetha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khyathi</namePart>
<namePart type="family">Chandu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</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">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>Named Entity Recognition plays a major role in several downstream applications in NLP. Though this task has been heavily studied in formal monolingual texts and also noisy texts like Twitter data, it is still an emerging task in code-switched (CS) content on social media. This paper describes our participation in the shared task of NER on code-switched data for Spanglish (Spanish + English) and Arabish (Arabic + English). In this paper we describe models that intuitively developed from the data for the shared task Named Entity Recognition on Code-switched Data. Owing to the sparse and non-linear relationships between words in Twitter data, we explored neural architectures that are capable of non-linearities fairly well. In specific, we trained character level models and word level models based on Bidirectional LSTMs (Bi-LSTMs) to perform sequential tagging. We train multiple models to identify nominal mentions and subsequently use this information to predict the labels of named entity in a sequence. Our best model is a character level model along with word level pre-trained multilingual embeddings that gave an F-score of 56.72 in Spanglish and a word level model that gave an F-score of 65.02 in Arabish on the test data.</abstract>
<identifier type="citekey">geetha-etal-2018-tackling</identifier>
<identifier type="doi">10.18653/v1/W18-3217</identifier>
<location>
<url>https://aclanthology.org/W18-3217</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>126</start>
<end>131</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Tackling Code-Switched NER: Participation of CMU
%A Geetha, Parvathy
%A Chandu, Khyathi
%A Black, Alan W.
%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 geetha-etal-2018-tackling
%X Named Entity Recognition plays a major role in several downstream applications in NLP. Though this task has been heavily studied in formal monolingual texts and also noisy texts like Twitter data, it is still an emerging task in code-switched (CS) content on social media. This paper describes our participation in the shared task of NER on code-switched data for Spanglish (Spanish + English) and Arabish (Arabic + English). In this paper we describe models that intuitively developed from the data for the shared task Named Entity Recognition on Code-switched Data. Owing to the sparse and non-linear relationships between words in Twitter data, we explored neural architectures that are capable of non-linearities fairly well. In specific, we trained character level models and word level models based on Bidirectional LSTMs (Bi-LSTMs) to perform sequential tagging. We train multiple models to identify nominal mentions and subsequently use this information to predict the labels of named entity in a sequence. Our best model is a character level model along with word level pre-trained multilingual embeddings that gave an F-score of 56.72 in Spanglish and a word level model that gave an F-score of 65.02 in Arabish on the test data.
%R 10.18653/v1/W18-3217
%U https://aclanthology.org/W18-3217
%U https://doi.org/10.18653/v1/W18-3217
%P 126-131
Markdown (Informal)
[Tackling Code-Switched NER: Participation of CMU](https://aclanthology.org/W18-3217) (Geetha et al., ACL 2018)
ACL
- Parvathy Geetha, Khyathi Chandu, and Alan W Black. 2018. Tackling Code-Switched NER: Participation of CMU. In Proceedings of the Third Workshop on Computational Approaches to Linguistic Code-Switching, pages 126–131, Melbourne, Australia. Association for Computational Linguistics.