@inproceedings{jang-etal-2024-kodialogbench-evaluating,
title = "{K}o{D}ialog{B}ench: Evaluating Conversational Understanding of Language Models with {K}orean Dialogue Benchmark",
author = "Jang, Seongbo and
Lee, Seonghyeon and
Yu, Hwanjo",
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.865",
pages = "9905--9925",
abstract = "As language models are often deployed as chatbot assistants, it becomes a virtue for models to engage in conversations in a user{'}s first language. While these models are trained on a wide range of languages, a comprehensive evaluation of their proficiency in low-resource languages such as Korean has been lacking. In this work, we introduce KoDialogBench, a benchmark designed to assess language models{'} conversational capabilities in Korean. To this end, we collect native Korean dialogues on daily topics from public sources, or translate dialogues from other languages. We then structure these conversations into diverse test datasets, spanning from dialogue comprehension to response selection tasks. Leveraging the proposed benchmark, we conduct extensive evaluations and analyses of various language models to measure a foundational understanding of Korean dialogues. Experimental results indicate that there exists significant room for improvement in models{'} conversation skills. Furthermore, our in-depth comparisons across different language models highlight the effectiveness of recent training techniques in enhancing conversational proficiency. We anticipate that KoDialogBench will promote the progress towards conversation-aware Korean language models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jang-etal-2024-kodialogbench-evaluating">
<titleInfo>
<title>KoDialogBench: Evaluating Conversational Understanding of Language Models with Korean Dialogue Benchmark</title>
</titleInfo>
<name type="personal">
<namePart type="given">Seongbo</namePart>
<namePart type="family">Jang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seonghyeon</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hwanjo</namePart>
<namePart type="family">Yu</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>As language models are often deployed as chatbot assistants, it becomes a virtue for models to engage in conversations in a user’s first language. While these models are trained on a wide range of languages, a comprehensive evaluation of their proficiency in low-resource languages such as Korean has been lacking. In this work, we introduce KoDialogBench, a benchmark designed to assess language models’ conversational capabilities in Korean. To this end, we collect native Korean dialogues on daily topics from public sources, or translate dialogues from other languages. We then structure these conversations into diverse test datasets, spanning from dialogue comprehension to response selection tasks. Leveraging the proposed benchmark, we conduct extensive evaluations and analyses of various language models to measure a foundational understanding of Korean dialogues. Experimental results indicate that there exists significant room for improvement in models’ conversation skills. Furthermore, our in-depth comparisons across different language models highlight the effectiveness of recent training techniques in enhancing conversational proficiency. We anticipate that KoDialogBench will promote the progress towards conversation-aware Korean language models.</abstract>
<identifier type="citekey">jang-etal-2024-kodialogbench-evaluating</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.865</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>9905</start>
<end>9925</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KoDialogBench: Evaluating Conversational Understanding of Language Models with Korean Dialogue Benchmark
%A Jang, Seongbo
%A Lee, Seonghyeon
%A Yu, Hwanjo
%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 jang-etal-2024-kodialogbench-evaluating
%X As language models are often deployed as chatbot assistants, it becomes a virtue for models to engage in conversations in a user’s first language. While these models are trained on a wide range of languages, a comprehensive evaluation of their proficiency in low-resource languages such as Korean has been lacking. In this work, we introduce KoDialogBench, a benchmark designed to assess language models’ conversational capabilities in Korean. To this end, we collect native Korean dialogues on daily topics from public sources, or translate dialogues from other languages. We then structure these conversations into diverse test datasets, spanning from dialogue comprehension to response selection tasks. Leveraging the proposed benchmark, we conduct extensive evaluations and analyses of various language models to measure a foundational understanding of Korean dialogues. Experimental results indicate that there exists significant room for improvement in models’ conversation skills. Furthermore, our in-depth comparisons across different language models highlight the effectiveness of recent training techniques in enhancing conversational proficiency. We anticipate that KoDialogBench will promote the progress towards conversation-aware Korean language models.
%U https://aclanthology.org/2024.lrec-main.865
%P 9905-9925
Markdown (Informal)
[KoDialogBench: Evaluating Conversational Understanding of Language Models with Korean Dialogue Benchmark](https://aclanthology.org/2024.lrec-main.865) (Jang et al., LREC-COLING 2024)
ACL