@inproceedings{gautam-etal-2021-comet,
title = "{C}o{M}e{T}: Towards Code-Mixed Translation Using Parallel Monolingual Sentences",
author = "Gautam, Devansh and
Kodali, Prashant and
Gupta, Kshitij and
Goel, Anmol and
Shrivastava, Manish and
Kumaraguru, Ponnurangam",
editor = "Solorio, Thamar and
Chen, Shuguang and
Black, Alan W. and
Diab, Mona and
Sitaram, Sunayana and
Soto, Victor and
Yilmaz, Emre and
Srinivasan, Anirudh",
booktitle = "Proceedings of the Fifth Workshop on Computational Approaches to Linguistic Code-Switching",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.calcs-1.7/",
doi = "10.18653/v1/2021.calcs-1.7",
pages = "47--55",
abstract = "Code-mixed languages are very popular in multilingual societies around the world, yet the resources lag behind to enable robust systems on such languages. A major contributing factor is the informal nature of these languages which makes it difficult to collect code-mixed data. In this paper, we propose our system for Task 1 of CACLS 2021 to generate a machine translation system for English to Hinglish in a supervised setting. Translating in the given direction can help expand the set of resources for several tasks by translating valuable datasets from high resource languages. We propose to use mBART, a pre-trained multilingual sequence-to-sequence model, and fully utilize the pre-training of the model by transliterating the roman Hindi words in the code-mixed sentences to Devanagri script. We evaluate how expanding the input by concatenating Hindi translations of the English sentences improves mBART`s performance. Our system gives a BLEU score of 12.22 on test set. Further, we perform a detailed error analysis of our proposed systems and explore the limitations of the provided dataset and metrics."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gautam-etal-2021-comet">
<titleInfo>
<title>CoMeT: Towards Code-Mixed Translation Using Parallel Monolingual Sentences</title>
</titleInfo>
<name type="personal">
<namePart type="given">Devansh</namePart>
<namePart type="family">Gautam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prashant</namePart>
<namePart type="family">Kodali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kshitij</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anmol</namePart>
<namePart type="family">Goel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manish</namePart>
<namePart type="family">Shrivastava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ponnurangam</namePart>
<namePart type="family">Kumaraguru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Computational Approaches to Linguistic Code-Switching</title>
</titleInfo>
<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">Shuguang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</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">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">Sunayana</namePart>
<namePart type="family">Sitaram</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">Emre</namePart>
<namePart type="family">Yilmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anirudh</namePart>
<namePart type="family">Srinivasan</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-mixed languages are very popular in multilingual societies around the world, yet the resources lag behind to enable robust systems on such languages. A major contributing factor is the informal nature of these languages which makes it difficult to collect code-mixed data. In this paper, we propose our system for Task 1 of CACLS 2021 to generate a machine translation system for English to Hinglish in a supervised setting. Translating in the given direction can help expand the set of resources for several tasks by translating valuable datasets from high resource languages. We propose to use mBART, a pre-trained multilingual sequence-to-sequence model, and fully utilize the pre-training of the model by transliterating the roman Hindi words in the code-mixed sentences to Devanagri script. We evaluate how expanding the input by concatenating Hindi translations of the English sentences improves mBART‘s performance. Our system gives a BLEU score of 12.22 on test set. Further, we perform a detailed error analysis of our proposed systems and explore the limitations of the provided dataset and metrics.</abstract>
<identifier type="citekey">gautam-etal-2021-comet</identifier>
<identifier type="doi">10.18653/v1/2021.calcs-1.7</identifier>
<location>
<url>https://aclanthology.org/2021.calcs-1.7/</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>47</start>
<end>55</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CoMeT: Towards Code-Mixed Translation Using Parallel Monolingual Sentences
%A Gautam, Devansh
%A Kodali, Prashant
%A Gupta, Kshitij
%A Goel, Anmol
%A Shrivastava, Manish
%A Kumaraguru, Ponnurangam
%Y Solorio, Thamar
%Y Chen, Shuguang
%Y Black, Alan W.
%Y Diab, Mona
%Y Sitaram, Sunayana
%Y Soto, Victor
%Y Yilmaz, Emre
%Y Srinivasan, Anirudh
%S Proceedings of the Fifth Workshop on Computational Approaches to Linguistic Code-Switching
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F gautam-etal-2021-comet
%X Code-mixed languages are very popular in multilingual societies around the world, yet the resources lag behind to enable robust systems on such languages. A major contributing factor is the informal nature of these languages which makes it difficult to collect code-mixed data. In this paper, we propose our system for Task 1 of CACLS 2021 to generate a machine translation system for English to Hinglish in a supervised setting. Translating in the given direction can help expand the set of resources for several tasks by translating valuable datasets from high resource languages. We propose to use mBART, a pre-trained multilingual sequence-to-sequence model, and fully utilize the pre-training of the model by transliterating the roman Hindi words in the code-mixed sentences to Devanagri script. We evaluate how expanding the input by concatenating Hindi translations of the English sentences improves mBART‘s performance. Our system gives a BLEU score of 12.22 on test set. Further, we perform a detailed error analysis of our proposed systems and explore the limitations of the provided dataset and metrics.
%R 10.18653/v1/2021.calcs-1.7
%U https://aclanthology.org/2021.calcs-1.7/
%U https://doi.org/10.18653/v1/2021.calcs-1.7
%P 47-55
Markdown (Informal)
[CoMeT: Towards Code-Mixed Translation Using Parallel Monolingual Sentences](https://aclanthology.org/2021.calcs-1.7/) (Gautam et al., CALCS 2021)
ACL