@inproceedings{zhang-etal-2018-fast-compact,
title = "A Fast, Compact, Accurate Model for Language Identification of Codemixed Text",
author = "Zhang, Yuan and
Riesa, Jason and
Gillick, Daniel and
Bakalov, Anton and
Baldridge, Jason and
Weiss, David",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
month = oct # "-" # nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D18-1030",
doi = "10.18653/v1/D18-1030",
pages = "328--337",
abstract = "We address fine-grained multilingual language identification: providing a language code for every token in a sentence, including codemixed text containing multiple languages. Such text is prevalent online, in documents, social media, and message boards. We show that a feed-forward network with a simple globally constrained decoder can accurately and rapidly label both codemixed and monolingual text in 100 languages and 100 language pairs. This model outperforms previously published multilingual approaches in terms of both accuracy and speed, yielding an 800x speed-up and a 19.5{\%} averaged absolute gain on three codemixed datasets. It furthermore outperforms several benchmark systems on monolingual language identification.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2018-fast-compact">
<titleInfo>
<title>A Fast, Compact, Accurate Model for Language Identification of Codemixed Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="family">Riesa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Gillick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anton</namePart>
<namePart type="family">Bakalov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="family">Baldridge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Weiss</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct"-"nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We address fine-grained multilingual language identification: providing a language code for every token in a sentence, including codemixed text containing multiple languages. Such text is prevalent online, in documents, social media, and message boards. We show that a feed-forward network with a simple globally constrained decoder can accurately and rapidly label both codemixed and monolingual text in 100 languages and 100 language pairs. This model outperforms previously published multilingual approaches in terms of both accuracy and speed, yielding an 800x speed-up and a 19.5% averaged absolute gain on three codemixed datasets. It furthermore outperforms several benchmark systems on monolingual language identification.</abstract>
<identifier type="citekey">zhang-etal-2018-fast-compact</identifier>
<identifier type="doi">10.18653/v1/D18-1030</identifier>
<location>
<url>https://aclanthology.org/D18-1030</url>
</location>
<part>
<date>2018-oct"-"nov</date>
<extent unit="page">
<start>328</start>
<end>337</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Fast, Compact, Accurate Model for Language Identification of Codemixed Text
%A Zhang, Yuan
%A Riesa, Jason
%A Gillick, Daniel
%A Bakalov, Anton
%A Baldridge, Jason
%A Weiss, David
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct" "nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F zhang-etal-2018-fast-compact
%X We address fine-grained multilingual language identification: providing a language code for every token in a sentence, including codemixed text containing multiple languages. Such text is prevalent online, in documents, social media, and message boards. We show that a feed-forward network with a simple globally constrained decoder can accurately and rapidly label both codemixed and monolingual text in 100 languages and 100 language pairs. This model outperforms previously published multilingual approaches in terms of both accuracy and speed, yielding an 800x speed-up and a 19.5% averaged absolute gain on three codemixed datasets. It furthermore outperforms several benchmark systems on monolingual language identification.
%R 10.18653/v1/D18-1030
%U https://aclanthology.org/D18-1030
%U https://doi.org/10.18653/v1/D18-1030
%P 328-337
Markdown (Informal)
[A Fast, Compact, Accurate Model for Language Identification of Codemixed Text](https://aclanthology.org/D18-1030) (Zhang et al., EMNLP 2018)
ACL
- Yuan Zhang, Jason Riesa, Daniel Gillick, Anton Bakalov, Jason Baldridge, and David Weiss. 2018. A Fast, Compact, Accurate Model for Language Identification of Codemixed Text. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 328–337, Brussels, Belgium. Association for Computational Linguistics.