@inproceedings{khan-etal-2023-banglachq,
title = "{B}angla{CHQ}-Summ: An Abstractive Summarization Dataset for Medical Queries in {B}angla Conversational Speech",
author = "Khan, Alvi and
Kamal, Fida and
Chowdhury, Mohammad Abrar and
Ahmed, Tasnim and
Laskar, Md Tahmid Rahman and
Ahmed, Sabbir",
editor = "Alam, Firoj and
Kar, Sudipta and
Chowdhury, Shammur Absar and
Sadeque, Farig and
Amin, Ruhul",
booktitle = "Proceedings of the First Workshop on Bangla Language Processing (BLP-2023)",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.banglalp-1.10",
doi = "10.18653/v1/2023.banglalp-1.10",
pages = "85--93",
abstract = "Online health consultation is steadily gaining popularity as a platform for patients to discuss their medical health inquiries, known as Consumer Health Questions (CHQs). The emergence of the COVID-19 pandemic has also led to a surge in the use of such platforms, creating a significant burden for the limited number of healthcare professionals attempting to respond to the influx of questions. Abstractive text summarization is a promising solution to this challenge, since shortening CHQs to only the information essential to answering them reduces the amount of time spent parsing unnecessary information. The summarization process can also serve as an intermediate step towards the eventual development of an automated medical question-answering system. This paper presents {`}BanglaCHQ-Summ{'}, the first CHQ summarization dataset for the Bangla language, consisting of 2,350 question-summary pairs. It is benchmarked on state-of-the-art Bangla and multilingual text generation models, with the best-performing model, BanglaT5, achieving a ROUGE-L score of 48.35{\%}. In addition, we address the limitations of existing automatic metrics for summarization by conducting a human evaluation. The dataset and all relevant code used in this work have been made publicly available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khan-etal-2023-banglachq">
<titleInfo>
<title>BanglaCHQ-Summ: An Abstractive Summarization Dataset for Medical Queries in Bangla Conversational Speech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alvi</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fida</namePart>
<namePart type="family">Kamal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Abrar</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tasnim</namePart>
<namePart type="family">Ahmed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Tahmid</namePart>
<namePart type="given">Rahman</namePart>
<namePart type="family">Laskar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabbir</namePart>
<namePart type="family">Ahmed</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 First Workshop on Bangla Language Processing (BLP-2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Firoj</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudipta</namePart>
<namePart type="family">Kar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shammur</namePart>
<namePart type="given">Absar</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Farig</namePart>
<namePart type="family">Sadeque</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruhul</namePart>
<namePart type="family">Amin</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>Online health consultation is steadily gaining popularity as a platform for patients to discuss their medical health inquiries, known as Consumer Health Questions (CHQs). The emergence of the COVID-19 pandemic has also led to a surge in the use of such platforms, creating a significant burden for the limited number of healthcare professionals attempting to respond to the influx of questions. Abstractive text summarization is a promising solution to this challenge, since shortening CHQs to only the information essential to answering them reduces the amount of time spent parsing unnecessary information. The summarization process can also serve as an intermediate step towards the eventual development of an automated medical question-answering system. This paper presents ‘BanglaCHQ-Summ’, the first CHQ summarization dataset for the Bangla language, consisting of 2,350 question-summary pairs. It is benchmarked on state-of-the-art Bangla and multilingual text generation models, with the best-performing model, BanglaT5, achieving a ROUGE-L score of 48.35%. In addition, we address the limitations of existing automatic metrics for summarization by conducting a human evaluation. The dataset and all relevant code used in this work have been made publicly available.</abstract>
<identifier type="citekey">khan-etal-2023-banglachq</identifier>
<identifier type="doi">10.18653/v1/2023.banglalp-1.10</identifier>
<location>
<url>https://aclanthology.org/2023.banglalp-1.10</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>85</start>
<end>93</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BanglaCHQ-Summ: An Abstractive Summarization Dataset for Medical Queries in Bangla Conversational Speech
%A Khan, Alvi
%A Kamal, Fida
%A Chowdhury, Mohammad Abrar
%A Ahmed, Tasnim
%A Laskar, Md Tahmid Rahman
%A Ahmed, Sabbir
%Y Alam, Firoj
%Y Kar, Sudipta
%Y Chowdhury, Shammur Absar
%Y Sadeque, Farig
%Y Amin, Ruhul
%S Proceedings of the First Workshop on Bangla Language Processing (BLP-2023)
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F khan-etal-2023-banglachq
%X Online health consultation is steadily gaining popularity as a platform for patients to discuss their medical health inquiries, known as Consumer Health Questions (CHQs). The emergence of the COVID-19 pandemic has also led to a surge in the use of such platforms, creating a significant burden for the limited number of healthcare professionals attempting to respond to the influx of questions. Abstractive text summarization is a promising solution to this challenge, since shortening CHQs to only the information essential to answering them reduces the amount of time spent parsing unnecessary information. The summarization process can also serve as an intermediate step towards the eventual development of an automated medical question-answering system. This paper presents ‘BanglaCHQ-Summ’, the first CHQ summarization dataset for the Bangla language, consisting of 2,350 question-summary pairs. It is benchmarked on state-of-the-art Bangla and multilingual text generation models, with the best-performing model, BanglaT5, achieving a ROUGE-L score of 48.35%. In addition, we address the limitations of existing automatic metrics for summarization by conducting a human evaluation. The dataset and all relevant code used in this work have been made publicly available.
%R 10.18653/v1/2023.banglalp-1.10
%U https://aclanthology.org/2023.banglalp-1.10
%U https://doi.org/10.18653/v1/2023.banglalp-1.10
%P 85-93
Markdown (Informal)
[BanglaCHQ-Summ: An Abstractive Summarization Dataset for Medical Queries in Bangla Conversational Speech](https://aclanthology.org/2023.banglalp-1.10) (Khan et al., BanglaLP 2023)
ACL