avatar

Salsabila Zahirah Pranida

M.Sc @ NLP
MBZUAI
irasalsabila (at) gmail (dot) com


Hello, and Ohm Swastiastu!

I am a graduate of the M.Sc. in Natural Language Processing at MBZUAI, where I worked under the supervision of Dr. Fajri Koto as part of the Koto-MOSAIC Lab, and was co-supervised by Prof. Thamar Solorio. My research lies at the intersection of Computational Social Science and NLP, focusing on dialogue systems, multilingual and dialect processing, resource development and evaluation, as well as speech technologies. My Master’s thesis on Indonesian dialects, collecting 11 dialects across 4 languages in Indonesia, was accepted to the EMNLP 2026 Main Conference.

I primarily work on Indonesian and its local languages and dialects, though I’m always eager to explore other linguistic and cultural contexts. I’m particularly interested in understanding how language and dialect variation reflect social and cultural nuances, as well as in modeling code-switching and code-mixing to better capture the dynamics of multilingual communication.

If you’re interested in collaborating or discussing low-resource NLP, feel free to get in touch! You can reach me via email at irasalsabila (at) gmail (dot) com. I am currently actively looking for PhD opportunities!

Latest Updates

Selected Publications

Please refer to my Google Scholar page for the complete publications.

  1. AACL-IJCNLP 2026
    CULTURETALK-ID: A Multi-Task Dialogue Benchmark for Cultural Commonsense in Indonesian Local Languages
    Muhammad Dehan Al Kautsar, Salsabila Zahirah Pranida, Bilal Elbouardi, and Fajri Koto
    Findings of the Association for Computational Linguistics: AACL-IJCNLP 2026. Association for Computational Linguistics.
    PDF

  2. EMNLP 2026
    INDODIALECT: A Multi-Dialect Conversational Dataset for Indonesian Local Languages
    Salsabila Zahirah Pranida, Thamar Solorio, and Fajri Koto
    Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026). Association for Computational Linguistics.

  3. PANDORA 2026
    Whose Toxicity? Persona Conditioning and Model–Annotator Label Agreement by Gender in Indonesian Toxicity Classification
    Salsabila Zahirah Pranida*, Antonia Karamolegkou*, Andrea Morales-Garzón, and Daniel Hershcovich
    First workshop on Pluralistic AI & NLP: Diversity-aware, Sociotechnical, Responsible Alignment (PANDORA 2026), Budapest, Hungary.

  4. ACL 2026
    Multilingual Idioms in Sentences and Conversations Across High-, Medium-, and Low-Resource Languages
    Saeed Almheiri*, Bilal Elbouardi*, Salsabila Zahirah Pranida*, ..., Suma Bhat, Fajri Koto
    Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12363–12389, San Diego, California, United States. Association for Computational Linguistics.
    PDF Code Dataset

  5. WiNLP 2025
    ASR Under Noise: Exploring Robustness for Sundanese and Javanese
    Salsabila Zahirah Pranida*, Muhammad Cendekia Airlangga*, Rifo Ahmad Genadi*, and Shady Shehata
    Proceedings of the 9th Widening NLP Workshop (WiNLP 2025), pages 87–99, Suzhou, China. Association for Computational Linguistics.
    PDF Code Dataset Best Paper @ WiNLP Workshop 2025

  6. MRL 2025
    Culturally-Nuanced Story Generation for Reasoning in Low-Resource Languages: The Case of Javanese and Sundanese
    Salsabila Zahirah Pranida*, Rifo Ahmad Genadi*, Fajri Koto
    Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025), pages 369–384, Suzhou, China. Association for Computational Linguistics.
    PDF Dataset

Education

Work Experiences

References


Powered by Jekyll and Minimal Light theme.