@inproceedings{riyadh-kondrak-2019-joint,
title = "Joint Approach to Deromanization of Code-mixed Texts",
author = "Riyadh, Rashed Rubby and
Kondrak, Grzegorz",
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/W19-1403",
doi = "10.18653/v1/W19-1403",
pages = "26--34",
abstract = "The conversion of romanized texts back to the native scripts is a challenging task because of the inconsistent romanization conventions and non-standard language use. This problem is compounded by code-mixing, i.e., using words from more than one language within the same discourse. In this paper, we propose a novel approach for handling these two problems together in a single system. Our approach combines three components: language identification, back-transliteration, and sequence prediction. The results of our experiments on Bengali and Hindi datasets establish the state of the art for the task of deromanization of code-mixed texts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="riyadh-kondrak-2019-joint">
<titleInfo>
<title>Joint Approach to Deromanization of Code-mixed Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rashed</namePart>
<namePart type="given">Rubby</namePart>
<namePart type="family">Riyadh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Grzegorz</namePart>
<namePart type="family">Kondrak</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>The conversion of romanized texts back to the native scripts is a challenging task because of the inconsistent romanization conventions and non-standard language use. This problem is compounded by code-mixing, i.e., using words from more than one language within the same discourse. In this paper, we propose a novel approach for handling these two problems together in a single system. Our approach combines three components: language identification, back-transliteration, and sequence prediction. The results of our experiments on Bengali and Hindi datasets establish the state of the art for the task of deromanization of code-mixed texts.</abstract>
<identifier type="citekey">riyadh-kondrak-2019-joint</identifier>
<identifier type="doi">10.18653/v1/W19-1403</identifier>
<location>
<url>https://aclanthology.org/W19-1403</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>26</start>
<end>34</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Joint Approach to Deromanization of Code-mixed Texts
%A Riyadh, Rashed Rubby
%A Kondrak, Grzegorz
%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 riyadh-kondrak-2019-joint
%X The conversion of romanized texts back to the native scripts is a challenging task because of the inconsistent romanization conventions and non-standard language use. This problem is compounded by code-mixing, i.e., using words from more than one language within the same discourse. In this paper, we propose a novel approach for handling these two problems together in a single system. Our approach combines three components: language identification, back-transliteration, and sequence prediction. The results of our experiments on Bengali and Hindi datasets establish the state of the art for the task of deromanization of code-mixed texts.
%R 10.18653/v1/W19-1403
%U https://aclanthology.org/W19-1403
%U https://doi.org/10.18653/v1/W19-1403
%P 26-34
Markdown (Informal)
[Joint Approach to Deromanization of Code-mixed Texts](https://aclanthology.org/W19-1403) (Riyadh & Kondrak, VarDial 2019)
ACL
- Rashed Rubby Riyadh and Grzegorz Kondrak. 2019. Joint Approach to Deromanization of Code-mixed Texts. In Proceedings of the Sixth Workshop on NLP for Similar Languages, Varieties and Dialects, pages 26–34, Ann Arbor, Michigan. Association for Computational Linguistics.