@inproceedings{akil-etal-2022-banglaparaphrase,
title = "{B}angla{P}araphrase: A High-Quality {B}angla Paraphrase Dataset",
author = "Akil, Ajwad and
Sultana, Najrin and
Bhattacharjee, Abhik and
Shahriyar, Rifat",
booktitle = "Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = nov,
year = "2022",
address = "Online only",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.aacl-short.33",
pages = "261--272",
abstract = "In this work, we present BanglaParaphrase, a high-quality synthetic Bangla Paraphrase dataset curated by a novel filtering pipeline. We aim to take a step towards alleviating the low resource status of the Bangla language in the NLP domain through the introduction of BanglaParaphrase, which ensures quality by preserving both semantics and diversity, making it particularly useful to enhance other Bangla datasets. We show a detailed comparative analysis between our dataset and models trained on it with other existing works to establish the viability of our synthetic paraphrase data generation pipeline. We are making the dataset and models publicly available at https://github.com/csebuetnlp/banglaparaphrase to further the state of Bangla NLP.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="akil-etal-2022-banglaparaphrase">
<titleInfo>
<title>BanglaParaphrase: A High-Quality Bangla Paraphrase Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ajwad</namePart>
<namePart type="family">Akil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Najrin</namePart>
<namePart type="family">Sultana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhik</namePart>
<namePart type="family">Bhattacharjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rifat</namePart>
<namePart type="family">Shahriyar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online only</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work, we present BanglaParaphrase, a high-quality synthetic Bangla Paraphrase dataset curated by a novel filtering pipeline. We aim to take a step towards alleviating the low resource status of the Bangla language in the NLP domain through the introduction of BanglaParaphrase, which ensures quality by preserving both semantics and diversity, making it particularly useful to enhance other Bangla datasets. We show a detailed comparative analysis between our dataset and models trained on it with other existing works to establish the viability of our synthetic paraphrase data generation pipeline. We are making the dataset and models publicly available at https://github.com/csebuetnlp/banglaparaphrase to further the state of Bangla NLP.</abstract>
<identifier type="citekey">akil-etal-2022-banglaparaphrase</identifier>
<location>
<url>https://aclanthology.org/2022.aacl-short.33</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>261</start>
<end>272</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BanglaParaphrase: A High-Quality Bangla Paraphrase Dataset
%A Akil, Ajwad
%A Sultana, Najrin
%A Bhattacharjee, Abhik
%A Shahriyar, Rifat
%S Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online only
%F akil-etal-2022-banglaparaphrase
%X In this work, we present BanglaParaphrase, a high-quality synthetic Bangla Paraphrase dataset curated by a novel filtering pipeline. We aim to take a step towards alleviating the low resource status of the Bangla language in the NLP domain through the introduction of BanglaParaphrase, which ensures quality by preserving both semantics and diversity, making it particularly useful to enhance other Bangla datasets. We show a detailed comparative analysis between our dataset and models trained on it with other existing works to establish the viability of our synthetic paraphrase data generation pipeline. We are making the dataset and models publicly available at https://github.com/csebuetnlp/banglaparaphrase to further the state of Bangla NLP.
%U https://aclanthology.org/2022.aacl-short.33
%P 261-272
Markdown (Informal)
[BanglaParaphrase: A High-Quality Bangla Paraphrase Dataset](https://aclanthology.org/2022.aacl-short.33) (Akil et al., AACL-IJCNLP 2022)
ACL
- Ajwad Akil, Najrin Sultana, Abhik Bhattacharjee, and Rifat Shahriyar. 2022. BanglaParaphrase: A High-Quality Bangla Paraphrase Dataset. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 261–272, Online only. Association for Computational Linguistics.