@inproceedings{rizvi-etal-2021-gcm,
title = "{GCM}: A Toolkit for Generating Synthetic Code-mixed Text",
author = "Rizvi, Mohd Sanad Zaki and
Srinivasan, Anirudh and
Ganu, Tanuja and
Choudhury, Monojit and
Sitaram, Sunayana",
editor = "Gkatzia, Dimitra and
Seddah, Djam{\'e}",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-demos.24",
doi = "10.18653/v1/2021.eacl-demos.24",
pages = "205--211",
abstract = "Code-mixing is common in multilingual communities around the world, and processing it is challenging due to the lack of labeled and unlabeled data. We describe a tool that can automatically generate code-mixed data given parallel data in two languages. We implement two linguistic theories of code-mixing, the Equivalence Constraint theory and the Matrix Language theory to generate all possible code-mixed sentences in the language-pair, followed by sampling of the generated data to generate natural code-mixed sentences. The toolkit provides three modes: a batch mode, an interactive library mode and a web-interface to address the needs of researchers, linguists and language experts. The toolkit can be used to generate unlabeled text data for pre-trained models, as well as visualize linguistic theories of code-mixing. We plan to release the toolkit as open source and extend it by adding more implementations of linguistic theories, visualization techniques and better sampling techniques. We expect that the release of this toolkit will help facilitate more research in code-mixing in diverse language pairs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rizvi-etal-2021-gcm">
<titleInfo>
<title>GCM: A Toolkit for Generating Synthetic Code-mixed Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohd</namePart>
<namePart type="given">Sanad</namePart>
<namePart type="given">Zaki</namePart>
<namePart type="family">Rizvi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anirudh</namePart>
<namePart type="family">Srinivasan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanuja</namePart>
<namePart type="family">Ganu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Monojit</namePart>
<namePart type="family">Choudhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunayana</namePart>
<namePart type="family">Sitaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dimitra</namePart>
<namePart type="family">Gkatzia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Djamé</namePart>
<namePart type="family">Seddah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Code-mixing is common in multilingual communities around the world, and processing it is challenging due to the lack of labeled and unlabeled data. We describe a tool that can automatically generate code-mixed data given parallel data in two languages. We implement two linguistic theories of code-mixing, the Equivalence Constraint theory and the Matrix Language theory to generate all possible code-mixed sentences in the language-pair, followed by sampling of the generated data to generate natural code-mixed sentences. The toolkit provides three modes: a batch mode, an interactive library mode and a web-interface to address the needs of researchers, linguists and language experts. The toolkit can be used to generate unlabeled text data for pre-trained models, as well as visualize linguistic theories of code-mixing. We plan to release the toolkit as open source and extend it by adding more implementations of linguistic theories, visualization techniques and better sampling techniques. We expect that the release of this toolkit will help facilitate more research in code-mixing in diverse language pairs.</abstract>
<identifier type="citekey">rizvi-etal-2021-gcm</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-demos.24</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-demos.24</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>205</start>
<end>211</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GCM: A Toolkit for Generating Synthetic Code-mixed Text
%A Rizvi, Mohd Sanad Zaki
%A Srinivasan, Anirudh
%A Ganu, Tanuja
%A Choudhury, Monojit
%A Sitaram, Sunayana
%Y Gkatzia, Dimitra
%Y Seddah, Djamé
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F rizvi-etal-2021-gcm
%X Code-mixing is common in multilingual communities around the world, and processing it is challenging due to the lack of labeled and unlabeled data. We describe a tool that can automatically generate code-mixed data given parallel data in two languages. We implement two linguistic theories of code-mixing, the Equivalence Constraint theory and the Matrix Language theory to generate all possible code-mixed sentences in the language-pair, followed by sampling of the generated data to generate natural code-mixed sentences. The toolkit provides three modes: a batch mode, an interactive library mode and a web-interface to address the needs of researchers, linguists and language experts. The toolkit can be used to generate unlabeled text data for pre-trained models, as well as visualize linguistic theories of code-mixing. We plan to release the toolkit as open source and extend it by adding more implementations of linguistic theories, visualization techniques and better sampling techniques. We expect that the release of this toolkit will help facilitate more research in code-mixing in diverse language pairs.
%R 10.18653/v1/2021.eacl-demos.24
%U https://aclanthology.org/2021.eacl-demos.24
%U https://doi.org/10.18653/v1/2021.eacl-demos.24
%P 205-211
Markdown (Informal)
[GCM: A Toolkit for Generating Synthetic Code-mixed Text](https://aclanthology.org/2021.eacl-demos.24) (Rizvi et al., EACL 2021)
ACL
- Mohd Sanad Zaki Rizvi, Anirudh Srinivasan, Tanuja Ganu, Monojit Choudhury, and Sunayana Sitaram. 2021. GCM: A Toolkit for Generating Synthetic Code-mixed Text. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, pages 205–211, Online. Association for Computational Linguistics.