@inproceedings{ligeti-nagy-etal-2024-hulu,
title = "{H}u{LU}: {H}ungarian Language Understanding Benchmark Kit",
author = "Ligeti-Nagy, No{\'e}mi and
Ferenczi, Gerg{\H{o}} and
H{\'e}ja, Enik{\H{o}} and
Laki, L{\'a}szl{\'o} J{\'a}nos and
Vad{\'a}sz, No{\'e}mi and
Yang, Zijian Gy{\H{o}}z{\H{o}} and
V{\'a}radi, Tam{\'a}s",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.733",
pages = "8360--8371",
abstract = "The paper introduces the Hungarian Language Understanding (HuLU) benchmark, a comprehensive assessment framework designed to evaluate the performance of neural language models on Hungarian language tasks. Inspired by the renowned GLUE and SuperGLUE benchmarks, HuLU aims to address the challenges specific to Hungarian language processing. The benchmark consists of various datasets, each representing different linguistic phenomena and task complexities. Moreover, the paper presents a web service developed for HuLU, offering a user-friendly interface for model evaluation. This platform not only ensures consistent assessment but also fosters transparency by maintaining a leaderboard showcasing model performances. Preliminary evaluations of various LMMs on HuLU datasets indicate that while Hungarian models show promise, there{'}s room for improvement to match the proficiency of English-centric models in their native language.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ligeti-nagy-etal-2024-hulu">
<titleInfo>
<title>HuLU: Hungarian Language Understanding Benchmark Kit</title>
</titleInfo>
<name type="personal">
<namePart type="given">Noémi</namePart>
<namePart type="family">Ligeti-Nagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gergő</namePart>
<namePart type="family">Ferenczi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enikő</namePart>
<namePart type="family">Héja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">László</namePart>
<namePart type="given">János</namePart>
<namePart type="family">Laki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noémi</namePart>
<namePart type="family">Vadász</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zijian</namePart>
<namePart type="given">Győző</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamás</namePart>
<namePart type="family">Váradi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The paper introduces the Hungarian Language Understanding (HuLU) benchmark, a comprehensive assessment framework designed to evaluate the performance of neural language models on Hungarian language tasks. Inspired by the renowned GLUE and SuperGLUE benchmarks, HuLU aims to address the challenges specific to Hungarian language processing. The benchmark consists of various datasets, each representing different linguistic phenomena and task complexities. Moreover, the paper presents a web service developed for HuLU, offering a user-friendly interface for model evaluation. This platform not only ensures consistent assessment but also fosters transparency by maintaining a leaderboard showcasing model performances. Preliminary evaluations of various LMMs on HuLU datasets indicate that while Hungarian models show promise, there’s room for improvement to match the proficiency of English-centric models in their native language.</abstract>
<identifier type="citekey">ligeti-nagy-etal-2024-hulu</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.733</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>8360</start>
<end>8371</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HuLU: Hungarian Language Understanding Benchmark Kit
%A Ligeti-Nagy, Noémi
%A Ferenczi, Gergő
%A Héja, Enikő
%A Laki, László János
%A Vadász, Noémi
%A Yang, Zijian Győző
%A Váradi, Tamás
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F ligeti-nagy-etal-2024-hulu
%X The paper introduces the Hungarian Language Understanding (HuLU) benchmark, a comprehensive assessment framework designed to evaluate the performance of neural language models on Hungarian language tasks. Inspired by the renowned GLUE and SuperGLUE benchmarks, HuLU aims to address the challenges specific to Hungarian language processing. The benchmark consists of various datasets, each representing different linguistic phenomena and task complexities. Moreover, the paper presents a web service developed for HuLU, offering a user-friendly interface for model evaluation. This platform not only ensures consistent assessment but also fosters transparency by maintaining a leaderboard showcasing model performances. Preliminary evaluations of various LMMs on HuLU datasets indicate that while Hungarian models show promise, there’s room for improvement to match the proficiency of English-centric models in their native language.
%U https://aclanthology.org/2024.lrec-main.733
%P 8360-8371
Markdown (Informal)
[HuLU: Hungarian Language Understanding Benchmark Kit](https://aclanthology.org/2024.lrec-main.733) (Ligeti-Nagy et al., LREC-COLING 2024)
ACL
- Noémi Ligeti-Nagy, Gergő Ferenczi, Enikő Héja, László János Laki, Noémi Vadász, Zijian Győző Yang, and Tamás Váradi. 2024. HuLU: Hungarian Language Understanding Benchmark Kit. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 8360–8371, Torino, Italia. ELRA and ICCL.