@inproceedings{kartik-etal-2024-synthetic,
title = "Synthetic Data Generation and Joint Learning for Robust Code-Mixed Translation",
author = "Kartik, Kartik and
Soni, Sanjana and
Kunchukuttan, Anoop and
Chakraborty, Tanmoy and
Akhtar, Md. Shad",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1345",
pages = "15480--15492",
abstract = "The widespread online communication in a modern multilingual world has provided opportunities to blend more than one language (aka code-mixed language) in a single utterance. This has resulted a formidable challenge for the computational models due to the scarcity of annotated data and presence of noise. A potential solution to mitigate the data scarcity problem in low-resource setup is to leverage existing data in resource-rich language through translation. In this paper, we tackle the problem of code-mixed (Hinglish and Bengalish) to English machine translation. First, we synthetically develop HINMIX, a parallel corpus of Hinglish to English, with {\textasciitilde}4.2M sentence pairs. Subsequently, we propose RCMT, a robust perturbation based joint-training model that learns to handle noise in the real-world code-mixed text by parameter sharing across clean and noisy words. Further, we show the adaptability of RCMT in a zero-shot setup for Bengalish to English translation. Our evaluation and comprehensive analyses qualitatively and quantitatively demonstrate the superiority of RCMT over state-of-the-art code-mixed and robust translation methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kartik-etal-2024-synthetic">
<titleInfo>
<title>Synthetic Data Generation and Joint Learning for Robust Code-Mixed Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kartik</namePart>
<namePart type="family">Kartik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanjana</namePart>
<namePart type="family">Soni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anoop</namePart>
<namePart type="family">Kunchukuttan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Shad</namePart>
<namePart type="family">Akhtar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The widespread online communication in a modern multilingual world has provided opportunities to blend more than one language (aka code-mixed language) in a single utterance. This has resulted a formidable challenge for the computational models due to the scarcity of annotated data and presence of noise. A potential solution to mitigate the data scarcity problem in low-resource setup is to leverage existing data in resource-rich language through translation. In this paper, we tackle the problem of code-mixed (Hinglish and Bengalish) to English machine translation. First, we synthetically develop HINMIX, a parallel corpus of Hinglish to English, with ~4.2M sentence pairs. Subsequently, we propose RCMT, a robust perturbation based joint-training model that learns to handle noise in the real-world code-mixed text by parameter sharing across clean and noisy words. Further, we show the adaptability of RCMT in a zero-shot setup for Bengalish to English translation. Our evaluation and comprehensive analyses qualitatively and quantitatively demonstrate the superiority of RCMT over state-of-the-art code-mixed and robust translation methods.</abstract>
<identifier type="citekey">kartik-etal-2024-synthetic</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1345</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>15480</start>
<end>15492</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Synthetic Data Generation and Joint Learning for Robust Code-Mixed Translation
%A Kartik, Kartik
%A Soni, Sanjana
%A Kunchukuttan, Anoop
%A Chakraborty, Tanmoy
%A Akhtar, Md. Shad
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F kartik-etal-2024-synthetic
%X The widespread online communication in a modern multilingual world has provided opportunities to blend more than one language (aka code-mixed language) in a single utterance. This has resulted a formidable challenge for the computational models due to the scarcity of annotated data and presence of noise. A potential solution to mitigate the data scarcity problem in low-resource setup is to leverage existing data in resource-rich language through translation. In this paper, we tackle the problem of code-mixed (Hinglish and Bengalish) to English machine translation. First, we synthetically develop HINMIX, a parallel corpus of Hinglish to English, with ~4.2M sentence pairs. Subsequently, we propose RCMT, a robust perturbation based joint-training model that learns to handle noise in the real-world code-mixed text by parameter sharing across clean and noisy words. Further, we show the adaptability of RCMT in a zero-shot setup for Bengalish to English translation. Our evaluation and comprehensive analyses qualitatively and quantitatively demonstrate the superiority of RCMT over state-of-the-art code-mixed and robust translation methods.
%U https://aclanthology.org/2024.lrec-main.1345
%P 15480-15492
Markdown (Informal)
[Synthetic Data Generation and Joint Learning for Robust Code-Mixed Translation](https://aclanthology.org/2024.lrec-main.1345) (Kartik et al., LREC-COLING 2024)
ACL