Dr. Teresa Lynn from Dublin City University (DCU) discussed the challenges in developing NLP tools for Irish, a low-resource language facing digital extinction. She highlighted the lack of speech and language applications and fundamental language resources for Irish. Lynn also mentioned her work at DCU on the GaelTech project and her involvement in the European Language Equality project. Why it matters: The development of NLP tools for low-resource languages like Irish is crucial for preserving linguistic diversity and preventing digital marginalization in the AI era.
Thamar Solorio from the University of Houston will discuss machine learning approaches for spontaneous human language processing. The talk will cover adapting multilingual transformers to code-switching data and using data augmentation for domain adaptation in sequence labeling tasks. Solorio will also provide an overview of other research projects at the RiTUAL lab, focusing on the scarcity of labeled data. Why it matters: This presentation addresses key challenges in Arabic NLP related to data scarcity, which is a persistent obstacle in developing effective AI applications for the region.
MBZUAI's Hanan Al Darmaki is working to improve automated speech recognition (ASR) for low-resource languages, where labeled data is scarce. She notes that Arabic presents unique challenges due to dialectal variations and a lack of written resources corresponding to spoken dialects. Al Darmaki's research focuses on unsupervised speech recognition to address this gap. Why it matters: Overcoming these challenges can improve virtual assistant effectiveness across diverse languages and enable more inclusive AI applications in the Arabic-speaking world.
The first Workshop on Language Models for Low-Resource Languages (LoResLM 2025) was held in Abu Dhabi as part of COLING 2025. It provided a forum for researchers to share work on language models for low-resource languages. The workshop accepted 35 papers from 52 submissions, covering diverse languages and research areas.
This survey paper reviews the landscape of Natural Language Processing (NLP) research and applications in the Arab world. It discusses the unique challenges posed by the Arabic language, such as its morphological complexity and dialectal diversity. The paper also presents a historical overview of Arabic NLP and surveys various research areas, including machine translation, sentiment analysis, and speech recognition. Why it matters: The survey provides a comprehensive resource for researchers and practitioners interested in the current state and future directions of Arabic NLP, a field critical for enabling AI technologies to serve Arabic-speaking communities.
Researchers developed Atlas-Chat, a collection of LLMs for dialectal Arabic, focusing on Moroccan Arabic (Darija). They constructed an instruction dataset by consolidating existing Darija language resources and translating English instructions. Atlas-Chat models (2B, 9B, 27B) outperform state-of-the-art and Arabic-specialized LLMs like LLaMa, Jais, and AceGPT on Darija NLP tasks. Why it matters: This work addresses the gap in LLM support for low-resource Arabic dialects, providing a methodology for instruction-tuning and benchmarks for future research.
This paper benchmarks multilingual and monolingual LLM performance across Arabic, English, and Indic languages, examining model compression effects like pruning and quantization. Multilingual models outperform language-specific counterparts, demonstrating cross-lingual transfer. Quantization maintains accuracy while promoting efficiency, but aggressive pruning compromises performance, particularly in larger models. Why it matters: The findings highlight strategies for scalable and fair multilingual NLP, addressing hallucination and generalization errors in low-resource languages.
This paper introduces two shared tasks for abusive and threatening language detection in Urdu, a low-resource language with over 170 million speakers. The tasks involve binary classification of Urdu tweets into Abusive/Non-Abusive and Threatening/Non-Threatening categories, respectively. Datasets of 2400/6000 training tweets and 1100/3950 testing tweets were created and manually annotated, along with logistic regression and BERT-based baselines. 21 teams participated and the best systems achieved F1-scores of 0.880 and 0.545 on the abusive and threatening language tasks, respectively, with m-BERT showing the best performance.