@inproceedings{pranida-etal-2026-indodialect,
title = "{I}ndo{D}ialect: A Multi-Dialect Conversational Dataset for {I}ndonesian Local Languages",
author = "Pranida, Salsabila Zahirah and
Solorio, Thamar and
Koto, Fajri",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.978/",
pages = "22570--22591",
ISBN = "979-8-89176-459-0",
abstract = "Dialectal variation is a defining characteristic of many low-resource languages, yet most NLP approaches overlook this complexity{---}often assuming uniformity or arbitrarily selecting a single variant without reporting which dialect is used. This assumption severely limits the applicability of language technologies in real-world communication, especially for languages without unified orthography where dialects could differ in vocabulary and morphology. In this paper, we present the first comprehensive study of dialect processing for Indonesian local languages, a linguistically rich and underrepresented setting. We introduce IndoDialect, a high-quality conversational dataset comprising 14.2K conversations across four major local languages and eleven dialects, including five Javanese, two Minangkabau, two Sundanese, and two Dayak dialects. Building on this resource, we define three core tasks: (i) dialect-level language identification, (ii) machine translation across dialects, and (iii) dialect-controlled generation. Our experiments reveal that state-of-the-art multilingual models perform poorly in few-shot scenarios, excel at dialect identification after fine-tuning, but struggle with machine translation and dialect-controlled generation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pranida-etal-2026-indodialect">
<titleInfo>
<title>IndoDialect: A Multi-Dialect Conversational Dataset for Indonesian Local Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Salsabila</namePart>
<namePart type="given">Zahirah</namePart>
<namePart type="family">Pranida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fajri</namePart>
<namePart type="family">Koto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Dialectal variation is a defining characteristic of many low-resource languages, yet most NLP approaches overlook this complexity—often assuming uniformity or arbitrarily selecting a single variant without reporting which dialect is used. This assumption severely limits the applicability of language technologies in real-world communication, especially for languages without unified orthography where dialects could differ in vocabulary and morphology. In this paper, we present the first comprehensive study of dialect processing for Indonesian local languages, a linguistically rich and underrepresented setting. We introduce IndoDialect, a high-quality conversational dataset comprising 14.2K conversations across four major local languages and eleven dialects, including five Javanese, two Minangkabau, two Sundanese, and two Dayak dialects. Building on this resource, we define three core tasks: (i) dialect-level language identification, (ii) machine translation across dialects, and (iii) dialect-controlled generation. Our experiments reveal that state-of-the-art multilingual models perform poorly in few-shot scenarios, excel at dialect identification after fine-tuning, but struggle with machine translation and dialect-controlled generation.</abstract>
<identifier type="citekey">pranida-etal-2026-indodialect</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.978/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>22570</start>
<end>22591</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IndoDialect: A Multi-Dialect Conversational Dataset for Indonesian Local Languages
%A Pranida, Salsabila Zahirah
%A Solorio, Thamar
%A Koto, Fajri
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F pranida-etal-2026-indodialect
%X Dialectal variation is a defining characteristic of many low-resource languages, yet most NLP approaches overlook this complexity—often assuming uniformity or arbitrarily selecting a single variant without reporting which dialect is used. This assumption severely limits the applicability of language technologies in real-world communication, especially for languages without unified orthography where dialects could differ in vocabulary and morphology. In this paper, we present the first comprehensive study of dialect processing for Indonesian local languages, a linguistically rich and underrepresented setting. We introduce IndoDialect, a high-quality conversational dataset comprising 14.2K conversations across four major local languages and eleven dialects, including five Javanese, two Minangkabau, two Sundanese, and two Dayak dialects. Building on this resource, we define three core tasks: (i) dialect-level language identification, (ii) machine translation across dialects, and (iii) dialect-controlled generation. Our experiments reveal that state-of-the-art multilingual models perform poorly in few-shot scenarios, excel at dialect identification after fine-tuning, but struggle with machine translation and dialect-controlled generation.
%U https://aclanthology.org/2026.emnlp-main.978/
%P 22570-22591
Markdown (Informal)
[IndoDialect: A Multi-Dialect Conversational Dataset for Indonesian Local Languages](https://aclanthology.org/2026.emnlp-main.978/) (Pranida et al., EMNLP 2026)
ACL