@inproceedings{sravani-mamidi-2023-enhancing,
title = "Enhancing Code-mixed Text Generation Using Synthetic Data Filtering in Neural Machine Translation",
author = "Sravani, Dama and
Mamidi, Radhika",
editor = "Jiang, Jing and
Reitter, David and
Deng, Shumin",
booktitle = "Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.conll-1.15",
doi = "10.18653/v1/2023.conll-1.15",
pages = "211--220",
abstract = "Code-Mixing, the act of mixing two or more languages, is a common communicative phenomenon in multi-lingual societies. The lack of quality in code-mixed data is a bottleneck for NLP systems. On the other hand, Monolingual systems perform well due to ample high-quality data. To bridge the gap, creating coherent translations of monolingual sentences to their code-mixed counterparts can improve accuracy in code-mixed settings for NLP downstream tasks. In this paper, we propose a neural machine translation approach to generate high-quality code-mixed sentences by leveraging human judgements. We train filters based on human judgements to identify natural code-mixed sentences from a larger synthetically generated code-mixed corpus, resulting in a three-way silver parallel corpus between monolingual English, monolingual Indian language and code-mixed English with an Indian language. Using these corpora, we fine-tune multi-lingual encoder-decoder models viz, mT5 and mBART, for the translation task. Our results indicate that our approach of using filtered data for training outperforms the current systems for code-mixed generation in Hindi-English. Apart from Hindi-English, the approach performs well when applied to Telugu, a low-resource language, to generate Telugu-English code-mixed sentences.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sravani-mamidi-2023-enhancing">
<titleInfo>
<title>Enhancing Code-mixed Text Generation Using Synthetic Data Filtering in Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dama</namePart>
<namePart type="family">Sravani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Radhika</namePart>
<namePart type="family">Mamidi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Reitter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shumin</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Code-Mixing, the act of mixing two or more languages, is a common communicative phenomenon in multi-lingual societies. The lack of quality in code-mixed data is a bottleneck for NLP systems. On the other hand, Monolingual systems perform well due to ample high-quality data. To bridge the gap, creating coherent translations of monolingual sentences to their code-mixed counterparts can improve accuracy in code-mixed settings for NLP downstream tasks. In this paper, we propose a neural machine translation approach to generate high-quality code-mixed sentences by leveraging human judgements. We train filters based on human judgements to identify natural code-mixed sentences from a larger synthetically generated code-mixed corpus, resulting in a three-way silver parallel corpus between monolingual English, monolingual Indian language and code-mixed English with an Indian language. Using these corpora, we fine-tune multi-lingual encoder-decoder models viz, mT5 and mBART, for the translation task. Our results indicate that our approach of using filtered data for training outperforms the current systems for code-mixed generation in Hindi-English. Apart from Hindi-English, the approach performs well when applied to Telugu, a low-resource language, to generate Telugu-English code-mixed sentences.</abstract>
<identifier type="citekey">sravani-mamidi-2023-enhancing</identifier>
<identifier type="doi">10.18653/v1/2023.conll-1.15</identifier>
<location>
<url>https://aclanthology.org/2023.conll-1.15</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>211</start>
<end>220</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Code-mixed Text Generation Using Synthetic Data Filtering in Neural Machine Translation
%A Sravani, Dama
%A Mamidi, Radhika
%Y Jiang, Jing
%Y Reitter, David
%Y Deng, Shumin
%S Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F sravani-mamidi-2023-enhancing
%X Code-Mixing, the act of mixing two or more languages, is a common communicative phenomenon in multi-lingual societies. The lack of quality in code-mixed data is a bottleneck for NLP systems. On the other hand, Monolingual systems perform well due to ample high-quality data. To bridge the gap, creating coherent translations of monolingual sentences to their code-mixed counterparts can improve accuracy in code-mixed settings for NLP downstream tasks. In this paper, we propose a neural machine translation approach to generate high-quality code-mixed sentences by leveraging human judgements. We train filters based on human judgements to identify natural code-mixed sentences from a larger synthetically generated code-mixed corpus, resulting in a three-way silver parallel corpus between monolingual English, monolingual Indian language and code-mixed English with an Indian language. Using these corpora, we fine-tune multi-lingual encoder-decoder models viz, mT5 and mBART, for the translation task. Our results indicate that our approach of using filtered data for training outperforms the current systems for code-mixed generation in Hindi-English. Apart from Hindi-English, the approach performs well when applied to Telugu, a low-resource language, to generate Telugu-English code-mixed sentences.
%R 10.18653/v1/2023.conll-1.15
%U https://aclanthology.org/2023.conll-1.15
%U https://doi.org/10.18653/v1/2023.conll-1.15
%P 211-220
Markdown (Informal)
[Enhancing Code-mixed Text Generation Using Synthetic Data Filtering in Neural Machine Translation](https://aclanthology.org/2023.conll-1.15) (Sravani & Mamidi, CoNLL 2023)
ACL