@inproceedings{monsur-etal-2022-shonglap,
title = "{SHONGLAP}: A Large {B}engali Open-Domain Dialogue Corpus",
author = "Monsur, Syed Mostofa and
Chowdhury, Sakib and
Fatemi, Md Shahrar and
Ahmed, Shafayat",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.623",
pages = "5797--5804",
abstract = "We introduce SHONGLAP, a large annotated open-domain dialogue corpus in Bengali language. Due to unavailability of high-quality dialogue datasets for low-resource languages like Bengali, existing neural open-domain dialogue systems suffer from data scarcity. We propose a framework to prepare large-scale open-domain dialogue datasets from publicly available multi-party discussion podcasts, talk-shows and label them based on weak-supervision techniques which is particularly suitable for low-resource settings. Using this framework, we prepared our corpus, the first reported Bengali open-domain dialogue corpus (7.7k+ fully annotated dialogues in total) which can serve as a strong baseline for future works. Experimental results show that our corpus improves performance of large language models (BanglaBERT) in case of downstream classification tasks during fine-tuning.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="monsur-etal-2022-shonglap">
<titleInfo>
<title>SHONGLAP: A Large Bengali Open-Domain Dialogue Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Syed</namePart>
<namePart type="given">Mostofa</namePart>
<namePart type="family">Monsur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakib</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Shahrar</namePart>
<namePart type="family">Fatemi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shafayat</namePart>
<namePart type="family">Ahmed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce SHONGLAP, a large annotated open-domain dialogue corpus in Bengali language. Due to unavailability of high-quality dialogue datasets for low-resource languages like Bengali, existing neural open-domain dialogue systems suffer from data scarcity. We propose a framework to prepare large-scale open-domain dialogue datasets from publicly available multi-party discussion podcasts, talk-shows and label them based on weak-supervision techniques which is particularly suitable for low-resource settings. Using this framework, we prepared our corpus, the first reported Bengali open-domain dialogue corpus (7.7k+ fully annotated dialogues in total) which can serve as a strong baseline for future works. Experimental results show that our corpus improves performance of large language models (BanglaBERT) in case of downstream classification tasks during fine-tuning.</abstract>
<identifier type="citekey">monsur-etal-2022-shonglap</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.623</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>5797</start>
<end>5804</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SHONGLAP: A Large Bengali Open-Domain Dialogue Corpus
%A Monsur, Syed Mostofa
%A Chowdhury, Sakib
%A Fatemi, Md Shahrar
%A Ahmed, Shafayat
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F monsur-etal-2022-shonglap
%X We introduce SHONGLAP, a large annotated open-domain dialogue corpus in Bengali language. Due to unavailability of high-quality dialogue datasets for low-resource languages like Bengali, existing neural open-domain dialogue systems suffer from data scarcity. We propose a framework to prepare large-scale open-domain dialogue datasets from publicly available multi-party discussion podcasts, talk-shows and label them based on weak-supervision techniques which is particularly suitable for low-resource settings. Using this framework, we prepared our corpus, the first reported Bengali open-domain dialogue corpus (7.7k+ fully annotated dialogues in total) which can serve as a strong baseline for future works. Experimental results show that our corpus improves performance of large language models (BanglaBERT) in case of downstream classification tasks during fine-tuning.
%U https://aclanthology.org/2022.lrec-1.623
%P 5797-5804
Markdown (Informal)
[SHONGLAP: A Large Bengali Open-Domain Dialogue Corpus](https://aclanthology.org/2022.lrec-1.623) (Monsur et al., LREC 2022)
ACL
- Syed Mostofa Monsur, Sakib Chowdhury, Md Shahrar Fatemi, and Shafayat Ahmed. 2022. SHONGLAP: A Large Bengali Open-Domain Dialogue Corpus. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 5797–5804, Marseille, France. European Language Resources Association.