@inproceedings{e-etal-2023-copara,
title = "{C}o{P}ara: The First {D}ravidian Paragraph-level n-way Aligned Corpus",
author = "E, Nikhil and
Choudhary, Mukund and
Mamidi, Radhika",
editor = "Chakravarthi, Bharathi R. and
Priyadharshini, Ruba and
M, Anand Kumar and
Thavareesan, Sajeetha and
Sherly, Elizabeth",
booktitle = "Proceedings of the Third Workshop on Speech and Language Technologies for Dravidian Languages",
month = sep,
year = "2023",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2023.dravidianlangtech-1.12",
pages = "88--96",
abstract = "We present CoPara, the first publicly available paragraph-level (n-way aligned) multilingual parallel corpora for Dravidian languages. The collection contains 2856 paragraph/passage pairs between English and four Dravidian languages. We source the parallel paragraphs from the New India Samachar magazine and align them with English as a pivot language. We do human and artificial evaluations to validate the high-quality alignment and richness of the parallel paragraphs of a range of lengths. To show one of the many ways this dataset can be wielded, we finetuned IndicBART, a seq2seq NMT model on all XX-En pairs of languages in CoPara which perform better than existing sentence-level models on standard benchmarks (like BLEU) on sentence level translations and longer text too. We show how this dataset can enrich a model trained for a task like this, with more contextual cues and beyond sentence understanding even in low-resource settings like that of Dravidian languages. Finally, the dataset and models are made available publicly at CoPara to help advance research in Dravidian NLP, parallel multilingual, and beyond sentence-level tasks like NMT, etc.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="e-etal-2023-copara">
<titleInfo>
<title>CoPara: The First Dravidian Paragraph-level n-way Aligned Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikhil</namePart>
<namePart type="family">E</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mukund</namePart>
<namePart type="family">Choudhary</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>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Speech and Language Technologies for Dravidian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruba</namePart>
<namePart type="family">Priyadharshini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anand</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">M</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sajeetha</namePart>
<namePart type="family">Thavareesan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Sherly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present CoPara, the first publicly available paragraph-level (n-way aligned) multilingual parallel corpora for Dravidian languages. The collection contains 2856 paragraph/passage pairs between English and four Dravidian languages. We source the parallel paragraphs from the New India Samachar magazine and align them with English as a pivot language. We do human and artificial evaluations to validate the high-quality alignment and richness of the parallel paragraphs of a range of lengths. To show one of the many ways this dataset can be wielded, we finetuned IndicBART, a seq2seq NMT model on all XX-En pairs of languages in CoPara which perform better than existing sentence-level models on standard benchmarks (like BLEU) on sentence level translations and longer text too. We show how this dataset can enrich a model trained for a task like this, with more contextual cues and beyond sentence understanding even in low-resource settings like that of Dravidian languages. Finally, the dataset and models are made available publicly at CoPara to help advance research in Dravidian NLP, parallel multilingual, and beyond sentence-level tasks like NMT, etc.</abstract>
<identifier type="citekey">e-etal-2023-copara</identifier>
<location>
<url>https://aclanthology.org/2023.dravidianlangtech-1.12</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>88</start>
<end>96</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CoPara: The First Dravidian Paragraph-level n-way Aligned Corpus
%A E, Nikhil
%A Choudhary, Mukund
%A Mamidi, Radhika
%Y Chakravarthi, Bharathi R.
%Y Priyadharshini, Ruba
%Y M, Anand Kumar
%Y Thavareesan, Sajeetha
%Y Sherly, Elizabeth
%S Proceedings of the Third Workshop on Speech and Language Technologies for Dravidian Languages
%D 2023
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F e-etal-2023-copara
%X We present CoPara, the first publicly available paragraph-level (n-way aligned) multilingual parallel corpora for Dravidian languages. The collection contains 2856 paragraph/passage pairs between English and four Dravidian languages. We source the parallel paragraphs from the New India Samachar magazine and align them with English as a pivot language. We do human and artificial evaluations to validate the high-quality alignment and richness of the parallel paragraphs of a range of lengths. To show one of the many ways this dataset can be wielded, we finetuned IndicBART, a seq2seq NMT model on all XX-En pairs of languages in CoPara which perform better than existing sentence-level models on standard benchmarks (like BLEU) on sentence level translations and longer text too. We show how this dataset can enrich a model trained for a task like this, with more contextual cues and beyond sentence understanding even in low-resource settings like that of Dravidian languages. Finally, the dataset and models are made available publicly at CoPara to help advance research in Dravidian NLP, parallel multilingual, and beyond sentence-level tasks like NMT, etc.
%U https://aclanthology.org/2023.dravidianlangtech-1.12
%P 88-96
Markdown (Informal)
[CoPara: The First Dravidian Paragraph-level n-way Aligned Corpus](https://aclanthology.org/2023.dravidianlangtech-1.12) (E et al., DravidianLangTech-WS 2023)
ACL