@inproceedings{yu-etal-2025-injongo,
title = "{INJONGO}: A Multicultural Intent Detection and Slot-filling Dataset for 16 {A}frican Languages",
author = "Yu, Hao and
Alabi, Jesujoba Oluwadara and
Bukula, Andiswa and
Zhuang, Jian Yun and
Lee, En-Shiun Annie and
Guge, Tadesse Kebede and
Azime, Israel Abebe and
Buzaaba, Happy and
Sibanda, Blessing Kudzaishe and
Kalipe, Godson Koffi and
Mukiibi, Jonathan and
Kabongo Kabenamualu, Salomon and
Setaka, Mmasibidi and
Ndolela, Lolwethu and
Odu, Nkiruka and
Mabuya, Rooweither and
Muhammad, Shamsuddeen Hassan and
Osei, Salomey and
Samb, Sokhar and
Klakow, Dietrich and
Adelani, David Ifeoluwa",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.464/",
doi = "10.18653/v1/2025.acl-long.464",
pages = "9429--9452",
ISBN = "979-8-89176-251-0",
abstract = "Slot-filling and intent detection are well-established tasks in Conversational AI. However, current large-scale benchmarks for these tasks often exclude evaluations of low-resource languages and rely on translations from English benchmarks, thereby predominantly reflecting Western-centric concepts. In this paper, we introduce ``INJONGO'' - a multicultural, open-source benchmark dataset for 16 African languages with utterances generated by native speakers across diverse domains, including banking, travel, home, and dining. Through extensive experiments, we benchmark fine-tuning multilingual transformer models and prompting large language models (LLMs), and show the advantage of leveraging African-cultural utterances over Western-centric utterances for improving cross-lingual transfer from the English language. Experimental results reveal that current LLMs struggle with the slot-filling task, with GPT-4o achieving an average performance of 26 F1. In contrast, intent detection performance is notably better, with an average accuracy of 70.6{\%}, though it still falls short of fine-tuning baselines. When compared to the English language, GPT-4o and fine-tuning baselines perform similarly on intent detection, achieving an accuracy of approximately 81{\%}. Our findings suggest that LLMs performance is still behind for many low-resource African languages, and more work is needed to further improve their downstream performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2025-injongo">
<titleInfo>
<title>INJONGO: A Multicultural Intent Detection and Slot-filling Dataset for 16 African Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesujoba</namePart>
<namePart type="given">Oluwadara</namePart>
<namePart type="family">Alabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andiswa</namePart>
<namePart type="family">Bukula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="given">Yun</namePart>
<namePart type="family">Zhuang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">En-Shiun</namePart>
<namePart type="given">Annie</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tadesse</namePart>
<namePart type="given">Kebede</namePart>
<namePart type="family">Guge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Israel</namePart>
<namePart type="given">Abebe</namePart>
<namePart type="family">Azime</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Happy</namePart>
<namePart type="family">Buzaaba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Blessing</namePart>
<namePart type="given">Kudzaishe</namePart>
<namePart type="family">Sibanda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Godson</namePart>
<namePart type="given">Koffi</namePart>
<namePart type="family">Kalipe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Mukiibi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salomon</namePart>
<namePart type="family">Kabongo Kabenamualu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mmasibidi</namePart>
<namePart type="family">Setaka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lolwethu</namePart>
<namePart type="family">Ndolela</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nkiruka</namePart>
<namePart type="family">Odu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rooweither</namePart>
<namePart type="family">Mabuya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shamsuddeen</namePart>
<namePart type="given">Hassan</namePart>
<namePart type="family">Muhammad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salomey</namePart>
<namePart type="family">Osei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sokhar</namePart>
<namePart type="family">Samb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dietrich</namePart>
<namePart type="family">Klakow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Ifeoluwa</namePart>
<namePart type="family">Adelani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Slot-filling and intent detection are well-established tasks in Conversational AI. However, current large-scale benchmarks for these tasks often exclude evaluations of low-resource languages and rely on translations from English benchmarks, thereby predominantly reflecting Western-centric concepts. In this paper, we introduce “INJONGO” - a multicultural, open-source benchmark dataset for 16 African languages with utterances generated by native speakers across diverse domains, including banking, travel, home, and dining. Through extensive experiments, we benchmark fine-tuning multilingual transformer models and prompting large language models (LLMs), and show the advantage of leveraging African-cultural utterances over Western-centric utterances for improving cross-lingual transfer from the English language. Experimental results reveal that current LLMs struggle with the slot-filling task, with GPT-4o achieving an average performance of 26 F1. In contrast, intent detection performance is notably better, with an average accuracy of 70.6%, though it still falls short of fine-tuning baselines. When compared to the English language, GPT-4o and fine-tuning baselines perform similarly on intent detection, achieving an accuracy of approximately 81%. Our findings suggest that LLMs performance is still behind for many low-resource African languages, and more work is needed to further improve their downstream performance.</abstract>
<identifier type="citekey">yu-etal-2025-injongo</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.464</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.464/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>9429</start>
<end>9452</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T INJONGO: A Multicultural Intent Detection and Slot-filling Dataset for 16 African Languages
%A Yu, Hao
%A Alabi, Jesujoba Oluwadara
%A Bukula, Andiswa
%A Zhuang, Jian Yun
%A Lee, En-Shiun Annie
%A Guge, Tadesse Kebede
%A Azime, Israel Abebe
%A Buzaaba, Happy
%A Sibanda, Blessing Kudzaishe
%A Kalipe, Godson Koffi
%A Mukiibi, Jonathan
%A Kabongo Kabenamualu, Salomon
%A Setaka, Mmasibidi
%A Ndolela, Lolwethu
%A Odu, Nkiruka
%A Mabuya, Rooweither
%A Muhammad, Shamsuddeen Hassan
%A Osei, Salomey
%A Samb, Sokhar
%A Klakow, Dietrich
%A Adelani, David Ifeoluwa
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F yu-etal-2025-injongo
%X Slot-filling and intent detection are well-established tasks in Conversational AI. However, current large-scale benchmarks for these tasks often exclude evaluations of low-resource languages and rely on translations from English benchmarks, thereby predominantly reflecting Western-centric concepts. In this paper, we introduce “INJONGO” - a multicultural, open-source benchmark dataset for 16 African languages with utterances generated by native speakers across diverse domains, including banking, travel, home, and dining. Through extensive experiments, we benchmark fine-tuning multilingual transformer models and prompting large language models (LLMs), and show the advantage of leveraging African-cultural utterances over Western-centric utterances for improving cross-lingual transfer from the English language. Experimental results reveal that current LLMs struggle with the slot-filling task, with GPT-4o achieving an average performance of 26 F1. In contrast, intent detection performance is notably better, with an average accuracy of 70.6%, though it still falls short of fine-tuning baselines. When compared to the English language, GPT-4o and fine-tuning baselines perform similarly on intent detection, achieving an accuracy of approximately 81%. Our findings suggest that LLMs performance is still behind for many low-resource African languages, and more work is needed to further improve their downstream performance.
%R 10.18653/v1/2025.acl-long.464
%U https://aclanthology.org/2025.acl-long.464/
%U https://doi.org/10.18653/v1/2025.acl-long.464
%P 9429-9452
Markdown (Informal)
[INJONGO: A Multicultural Intent Detection and Slot-filling Dataset for 16 African Languages](https://aclanthology.org/2025.acl-long.464/) (Yu et al., ACL 2025)
ACL
- Hao Yu, Jesujoba Oluwadara Alabi, Andiswa Bukula, Jian Yun Zhuang, En-Shiun Annie Lee, Tadesse Kebede Guge, Israel Abebe Azime, Happy Buzaaba, Blessing Kudzaishe Sibanda, Godson Koffi Kalipe, Jonathan Mukiibi, Salomon Kabongo Kabenamualu, Mmasibidi Setaka, Lolwethu Ndolela, Nkiruka Odu, Rooweither Mabuya, Shamsuddeen Hassan Muhammad, Salomey Osei, Sokhar Samb, Dietrich Klakow, and David Ifeoluwa Adelani. 2025. INJONGO: A Multicultural Intent Detection and Slot-filling Dataset for 16 African Languages. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 9429–9452, Vienna, Austria. Association for Computational Linguistics.