@inproceedings{tran-etal-2024-viglue,
title = "{V}i{GLUE}: A {V}ietnamese General Language Understanding Benchmark and Analysis of {V}ietnamese Language Models",
author = "Tran, Minh-Nam and
Nguyen, Phu-Vinh and
Nguyen, Long and
Dinh, Dien",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-naacl.261",
pages = "4174--4189",
abstract = "As the number of language models has increased, various benchmarks have been suggested to assess the proficiency of the models in natural language understanding. However, there is a lack of such a benchmark in Vietnamese due to the difficulty in accessing natural language processing datasets or the scarcity of task-specific datasets. **ViGLUE**, the proposed dataset collection, is a **Vi**etnamese **G**eneral **L**anguage **U**nderstanding **E**valuation benchmark developed using three methods: translating an existing benchmark, generating new corpora, and collecting available datasets. ViGLUE contains twelve tasks and encompasses over ten areas and subjects, enabling it to evaluate models comprehensively over a broad spectrum of aspects. Baseline models utilizing multilingual language models are also provided for all tasks in the proposed benchmarks. In addition, the study of the available Vietnamese large language models is conducted to explore the language models{'} ability in the few-shot learning framework, leading to the exploration of the relationship between specific tasks and the number of shots.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tran-etal-2024-viglue">
<titleInfo>
<title>ViGLUE: A Vietnamese General Language Understanding Benchmark and Analysis of Vietnamese Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Minh-Nam</namePart>
<namePart type="family">Tran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phu-Vinh</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Long</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dien</namePart>
<namePart type="family">Dinh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As the number of language models has increased, various benchmarks have been suggested to assess the proficiency of the models in natural language understanding. However, there is a lack of such a benchmark in Vietnamese due to the difficulty in accessing natural language processing datasets or the scarcity of task-specific datasets. **ViGLUE**, the proposed dataset collection, is a **Vi**etnamese **G**eneral **L**anguage **U**nderstanding **E**valuation benchmark developed using three methods: translating an existing benchmark, generating new corpora, and collecting available datasets. ViGLUE contains twelve tasks and encompasses over ten areas and subjects, enabling it to evaluate models comprehensively over a broad spectrum of aspects. Baseline models utilizing multilingual language models are also provided for all tasks in the proposed benchmarks. In addition, the study of the available Vietnamese large language models is conducted to explore the language models’ ability in the few-shot learning framework, leading to the exploration of the relationship between specific tasks and the number of shots.</abstract>
<identifier type="citekey">tran-etal-2024-viglue</identifier>
<location>
<url>https://aclanthology.org/2024.findings-naacl.261</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>4174</start>
<end>4189</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ViGLUE: A Vietnamese General Language Understanding Benchmark and Analysis of Vietnamese Language Models
%A Tran, Minh-Nam
%A Nguyen, Phu-Vinh
%A Nguyen, Long
%A Dinh, Dien
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Findings of the Association for Computational Linguistics: NAACL 2024
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F tran-etal-2024-viglue
%X As the number of language models has increased, various benchmarks have been suggested to assess the proficiency of the models in natural language understanding. However, there is a lack of such a benchmark in Vietnamese due to the difficulty in accessing natural language processing datasets or the scarcity of task-specific datasets. **ViGLUE**, the proposed dataset collection, is a **Vi**etnamese **G**eneral **L**anguage **U**nderstanding **E**valuation benchmark developed using three methods: translating an existing benchmark, generating new corpora, and collecting available datasets. ViGLUE contains twelve tasks and encompasses over ten areas and subjects, enabling it to evaluate models comprehensively over a broad spectrum of aspects. Baseline models utilizing multilingual language models are also provided for all tasks in the proposed benchmarks. In addition, the study of the available Vietnamese large language models is conducted to explore the language models’ ability in the few-shot learning framework, leading to the exploration of the relationship between specific tasks and the number of shots.
%U https://aclanthology.org/2024.findings-naacl.261
%P 4174-4189
Markdown (Informal)
[ViGLUE: A Vietnamese General Language Understanding Benchmark and Analysis of Vietnamese Language Models](https://aclanthology.org/2024.findings-naacl.261) (Tran et al., Findings 2024)
ACL