@inproceedings{ngo-etal-2024-vlogqa,
title = "{V}log{QA}: Task, Dataset, and Baseline Models for {V}ietnamese Spoken-Based Machine Reading Comprehension",
author = "Ngo, Thinh and
Dang, Khoa and
Luu, Son and
Nguyen, Kiet and
Nguyen, Ngan",
editor = "Graham, Yvette and
Purver, Matthew",
booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.eacl-long.79",
pages = "1310--1324",
abstract = "This paper presents the development process of a Vietnamese spoken language corpus for machine reading comprehension (MRC) tasks and provides insights into the challenges and opportunities associated with using real-world data for machine reading comprehension tasks. The existing MRC corpora in Vietnamese mainly focus on formal written documents such as Wikipedia articles, online newspapers, or textbooks. In contrast, the VlogQA consists of 10,076 question-answer pairs based on 1,230 transcript documents sourced from YouTube {--} an extensive source of user-uploaded content, covering the topics of food and travel. By capturing the spoken language of native Vietnamese speakers in natural settings, an obscure corner overlooked in Vietnamese research, the corpus provides a valuable resource for future research in reading comprehension tasks for the Vietnamese language. Regarding performance evaluation, our deep-learning models achieved the highest F1 score of 75.34{\%} on the test set, indicating significant progress in machine reading comprehension for Vietnamese spoken language data. In terms of EM, the highest score we accomplished is 53.97{\%}, which reflects the challenge in processing spoken-based content and highlights the need for further improvement.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ngo-etal-2024-vlogqa">
<titleInfo>
<title>VlogQA: Task, Dataset, and Baseline Models for Vietnamese Spoken-Based Machine Reading Comprehension</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thinh</namePart>
<namePart type="family">Ngo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khoa</namePart>
<namePart type="family">Dang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Son</namePart>
<namePart type="family">Luu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kiet</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ngan</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents the development process of a Vietnamese spoken language corpus for machine reading comprehension (MRC) tasks and provides insights into the challenges and opportunities associated with using real-world data for machine reading comprehension tasks. The existing MRC corpora in Vietnamese mainly focus on formal written documents such as Wikipedia articles, online newspapers, or textbooks. In contrast, the VlogQA consists of 10,076 question-answer pairs based on 1,230 transcript documents sourced from YouTube – an extensive source of user-uploaded content, covering the topics of food and travel. By capturing the spoken language of native Vietnamese speakers in natural settings, an obscure corner overlooked in Vietnamese research, the corpus provides a valuable resource for future research in reading comprehension tasks for the Vietnamese language. Regarding performance evaluation, our deep-learning models achieved the highest F1 score of 75.34% on the test set, indicating significant progress in machine reading comprehension for Vietnamese spoken language data. In terms of EM, the highest score we accomplished is 53.97%, which reflects the challenge in processing spoken-based content and highlights the need for further improvement.</abstract>
<identifier type="citekey">ngo-etal-2024-vlogqa</identifier>
<location>
<url>https://aclanthology.org/2024.eacl-long.79</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>1310</start>
<end>1324</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VlogQA: Task, Dataset, and Baseline Models for Vietnamese Spoken-Based Machine Reading Comprehension
%A Ngo, Thinh
%A Dang, Khoa
%A Luu, Son
%A Nguyen, Kiet
%A Nguyen, Ngan
%Y Graham, Yvette
%Y Purver, Matthew
%S Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F ngo-etal-2024-vlogqa
%X This paper presents the development process of a Vietnamese spoken language corpus for machine reading comprehension (MRC) tasks and provides insights into the challenges and opportunities associated with using real-world data for machine reading comprehension tasks. The existing MRC corpora in Vietnamese mainly focus on formal written documents such as Wikipedia articles, online newspapers, or textbooks. In contrast, the VlogQA consists of 10,076 question-answer pairs based on 1,230 transcript documents sourced from YouTube – an extensive source of user-uploaded content, covering the topics of food and travel. By capturing the spoken language of native Vietnamese speakers in natural settings, an obscure corner overlooked in Vietnamese research, the corpus provides a valuable resource for future research in reading comprehension tasks for the Vietnamese language. Regarding performance evaluation, our deep-learning models achieved the highest F1 score of 75.34% on the test set, indicating significant progress in machine reading comprehension for Vietnamese spoken language data. In terms of EM, the highest score we accomplished is 53.97%, which reflects the challenge in processing spoken-based content and highlights the need for further improvement.
%U https://aclanthology.org/2024.eacl-long.79
%P 1310-1324
Markdown (Informal)
[VlogQA: Task, Dataset, and Baseline Models for Vietnamese Spoken-Based Machine Reading Comprehension](https://aclanthology.org/2024.eacl-long.79) (Ngo et al., EACL 2024)
ACL