@inproceedings{purwarianti-etal-2025-nusadialogue,
title = "{N}usa{D}ialogue: Dialogue Summarization and Generation for Underrepresented and Extremely Low-Resource Languages",
author = "Purwarianti, Ayu and
Adhista, Dea and
Baptiso, Agung and
Mahfuzh, Miftahul and
Sabila, Yusrina and
Adila, Aulia and
Cahyawijaya, Samuel and
Aji, Alham Fikri",
editor = "Wijaya, Derry and
Aji, Alham Fikri and
Vania, Clara and
Winata, Genta Indra and
Purwarianti, Ayu",
booktitle = "Proceedings of the Second Workshop in South East Asian Language Processing",
month = jan,
year = "2025",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.sealp-1.8/",
pages = "82--100",
abstract = "Developing dialogue summarization for extremely low-resource languages is a challenging task. We introduce NusaDialogue, a dialogue summarization dataset for three underrepresented languages in the Malayo-Polynesian language family: Minangkabau, Balinese, and Buginese. NusaDialogue covers 17 topics and 185 subtopics, with annotations provided by 73 native speakers. Additionally, we conducted experiments using fine-tuning on a specifically designed medium-sized language model for Indonesian, as well as zero- and few-shot learning on various multilingual large language models (LLMs). The results indicate that, for extremely low-resource languages such as Minangkabau, Balinese, and Buginese, the fine-tuning approach yields significantly higher performance compared to zero- and few-shot prompting, even when applied to LLMs with considerably larger parameter sizes."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="purwarianti-etal-2025-nusadialogue">
<titleInfo>
<title>NusaDialogue: Dialogue Summarization and Generation for Underrepresented and Extremely Low-Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dea</namePart>
<namePart type="family">Adhista</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agung</namePart>
<namePart type="family">Baptiso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miftahul</namePart>
<namePart type="family">Mahfuzh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusrina</namePart>
<namePart type="family">Sabila</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aulia</namePart>
<namePart type="family">Adila</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Cahyawijaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alham</namePart>
<namePart type="given">Fikri</namePart>
<namePart type="family">Aji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop in South East Asian Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Derry</namePart>
<namePart type="family">Wijaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alham</namePart>
<namePart type="given">Fikri</namePart>
<namePart type="family">Aji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Clara</namePart>
<namePart type="family">Vania</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Genta</namePart>
<namePart type="given">Indra</namePart>
<namePart type="family">Winata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Developing dialogue summarization for extremely low-resource languages is a challenging task. We introduce NusaDialogue, a dialogue summarization dataset for three underrepresented languages in the Malayo-Polynesian language family: Minangkabau, Balinese, and Buginese. NusaDialogue covers 17 topics and 185 subtopics, with annotations provided by 73 native speakers. Additionally, we conducted experiments using fine-tuning on a specifically designed medium-sized language model for Indonesian, as well as zero- and few-shot learning on various multilingual large language models (LLMs). The results indicate that, for extremely low-resource languages such as Minangkabau, Balinese, and Buginese, the fine-tuning approach yields significantly higher performance compared to zero- and few-shot prompting, even when applied to LLMs with considerably larger parameter sizes.</abstract>
<identifier type="citekey">purwarianti-etal-2025-nusadialogue</identifier>
<location>
<url>https://aclanthology.org/2025.sealp-1.8/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>82</start>
<end>100</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NusaDialogue: Dialogue Summarization and Generation for Underrepresented and Extremely Low-Resource Languages
%A Purwarianti, Ayu
%A Adhista, Dea
%A Baptiso, Agung
%A Mahfuzh, Miftahul
%A Sabila, Yusrina
%A Adila, Aulia
%A Cahyawijaya, Samuel
%A Aji, Alham Fikri
%Y Wijaya, Derry
%Y Aji, Alham Fikri
%Y Vania, Clara
%Y Winata, Genta Indra
%Y Purwarianti, Ayu
%S Proceedings of the Second Workshop in South East Asian Language Processing
%D 2025
%8 January
%I Association for Computational Linguistics
%C Online
%F purwarianti-etal-2025-nusadialogue
%X Developing dialogue summarization for extremely low-resource languages is a challenging task. We introduce NusaDialogue, a dialogue summarization dataset for three underrepresented languages in the Malayo-Polynesian language family: Minangkabau, Balinese, and Buginese. NusaDialogue covers 17 topics and 185 subtopics, with annotations provided by 73 native speakers. Additionally, we conducted experiments using fine-tuning on a specifically designed medium-sized language model for Indonesian, as well as zero- and few-shot learning on various multilingual large language models (LLMs). The results indicate that, for extremely low-resource languages such as Minangkabau, Balinese, and Buginese, the fine-tuning approach yields significantly higher performance compared to zero- and few-shot prompting, even when applied to LLMs with considerably larger parameter sizes.
%U https://aclanthology.org/2025.sealp-1.8/
%P 82-100
Markdown (Informal)
[NusaDialogue: Dialogue Summarization and Generation for Underrepresented and Extremely Low-Resource Languages](https://aclanthology.org/2025.sealp-1.8/) (Purwarianti et al., sealp 2025)
ACL