Low-Resource Language Processing

Follow this topic Ask about this topic

Momentum

42 papers in the last four weeks, up 62% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 342

All topics

Language-Specific Effects of Tokenizer Choice in Multilingual Language Models
Oct 8, 2026Clara Meister, Gül Sena Altıntaş, Antoine BosselutMultilingual Language Models Multilingual Language Model Evaluation
EPFL · University of Toronto, Vector Institute
Adapting English Quality Classifiers for Multilingual LLM Pretraining Data Selection
Oct 8, 2026Vinko Sabolčec, Bettina Messmer, Yassine Turki +1Language Model Pretraining Cross-Lingual Transfer
EPFL
Document-Level Text Simplification in Estonian Using Large Language Models
Oct 7, 2026Meeri-Ly Muru, Eduard BarbuLow-Resource Language Processing Language Model Generation Evaluation
National Library of Estonia · Institute of Computer Science, University of Tartu Tartu, Estonia
BanglaRhet: Benchmarking Classical and Transformer Models for Rhetorical and Persuasion Detection in Bangla Political Speech
Oct 7, 2026Rohit Kumar Sen, Anik ChowdhuryPolitical Discourse Analysis Low-Resource Language Processing
Department of Computer Science and Engineering North East University Bangladesh Sylhet, Bangladesh
The ÌròyìnSpeech Text Corpus: 24,905 Curated Yorùbá Sentences for Speech and Language Technology
Oct 4, 2026Kola Tubosun, Aanuoluwapo Aremu, Tolulope Ogunremi +2Low-Resource Language Processing
Stanford University · Niger-Volta LTI · Mila / McGill University
Multilingual GSM-Symbolic: What determines capability transfer across languages?
Oct 2, 2026Kenneth Enevoldsen, Riley Herchert, Sofie Mosegaard +22Mathematical Reasoning Benchmarks Multilingual Language Model Evaluation
Aarhus University · Danish Foundation Models · University of Alabama +13
Yo-ByT5: Efficient and High-Fidelity Diacritic Restoration for Yorùbá
Oct 1, 2026Ahmad Samuel Gali, Shamsuddeen Hassan MuhammadLow-Resource Language Processing
University of Lagos · Bayero University Kano · Imperial College London
BanglaDial-Abuse: A Corpus-Grounded Dataset for Regional Dialect Identification in Abusive Bangla Text
Oct 1, 2026Hasin Almas SifatLow-Resource Language Processing
Department of Computer Science American International University-Bangladesh Dhaka, Bangladesh
Assessing the Impact of Language Disparity on Multilingual Linguistic Ability in Large Language Models
Sep 30, 2026Zhanyu Chen, Jaap JumeletMultilingual Language Model Evaluation Language Modeling
University of Groningen
LLM-as-a-Judge for Low-Resource Languages: Adapting Ragas and Comparative Ranking for Romanian
Sep 30, 2026Claudiu Creanga, Liviu P. DinuLLM Evaluation LLM-as-a-Judge
Interdisciplinary School of Doctoral Studies, University of Bucharest, Romania · HLT Research Center, University of Bucharest, Romania · Faculty of Mathematics and Computer Science, University of Bucharest, Romania
TTLab at Daleel 2026: STAR-Ar, Sequence Tagging for Argument Recognition in Arabic
Sep 30, 2026Bhuvanesh Verma, Ali Abusaleh, Alexander MehlerArgument Mining Arabic NLP
Text Technology Lab (TTLab), Goethe University Frankfurt
The Invisible Language Tax: Token Premiums of French and Regional Languages in 2026 LLM Tokenizers, and a French-Optimized Prototype
Sep 30, 2026Thomas ServalMultilingual Language Models Token Efficiency
Baracoda AI Labs & NEOMA Business School
Towards Model as a Library: Offline, Community-Sourced AI for Low-Resource African Languages
Sep 29, 2026Fendji K. E. Jean LouisSpeech Processing Low-Resource Language Processing
Centre of Research, Experimentation and Production SCEMI, University of Ngaoundere, Ngaoundere, Cameroon · Stellenbosch Institute for Advanced Study Wallenberg Research Centre at Stellenbosch University, Stellenbosch, South Africa
Zero-shot Dependency Parsing with Unsupervised Cross-Lingual Bootstrapping
Sep 29, 2026Lalita Lowphansirikul, Attapol Rutherford, Jian Gang Ngui +2Multilingual Language Models Low-Resource Language Processing
VISTEC, Thailand · Chulalongkorn University, Thailand · AI Singapore, Singapore
How Many Labels Does a Language Need? Annotation Budgets and Cross-Lingual Pooling for African-Language Text Classification
Sep 29, 2026Bhanu Prakash Vangala, Sowmya Guda, Navya VangalaZero-Shot Text Classification Text Classification
University of Missouri · Amar Bio Tech Pvt Ltd
One Threshold Does Not Fit All Languages: Language-Conditional Deferral for Reliable and Efficient Low-Resource Text Classification
Sep 29, 2026Bhanu Prakash Vangala, Vangala NavyaSelective Prediction Group-Conditional Conformal Prediction
University of Missouri · Amar Bio Tech Pvt Ltd
RunyaNER: Auxiliary Language Selection for Runyankore NER
Sep 29, 2026Prosper Arineitwe Asiimwe, Francois Meyer, Jan BuysNamed Entity Recognition Multilingual Language Model Evaluation
Department of Computer Science, University of Cape Town
Word Similarity Datasets for Indian Languages: Annotation and Baseline Systems
Sep 28, 2026Syed S. Akhtar, Arihant Gupta, Avijit Vajpayee +2Semantic Textual Similarity Low-Resource Language Processing
International Institute of Information Technology Hyderabad, Telangana, India
Preserving Morphemes: Morphology-Guided Pre-Tokenization for Nepali
Sep 27, 2026Kalash Shrestha, Nikhil PradhanLanguage Model Pretraining Low-Resource Language Processing
Kathmandu University · IOE Thapathali Campus
Multi-Task Learning by using Contextualized Word Representations for Syntactic Parsing of a Morphologically Rich Language
Sep 24, 2026Toqeer Ehsan, Miriam Butt, Sarmad Hussain +2Multi-Task Learning Low-Resource Language Processing
Reliable Intelligence Team, VTT Technical Research Centre of Finland Ltd., 02150 Espoo, Finland. · Department of Linguistics, University of Konstanz, 78464 Konstanz, Germany. · Center for Language Engineering, Al-Khawarizmi Institute of Computer Science, University of Engineering and Technology, 54890 Lahore, Pakistan. +2
BanglaKontho: Closing the Long-Form Gap in Bangla Text-to-Speech
Sep 24, 2026Mizbaul Haque MarufTTS Synthesis Low-Resource TTS Synthesis
Vivasoft Limited, Dhaka, Bangladesh
Language Specificity vs. Domain Diversity: Benchmarking Transformers for Bangla Medical NER
Sep 24, 2026Rakib Abdullah, Md. Maruful Islam MarufNamed Entity Recognition Multilingual Language Model Evaluation
Department of Artificial Intelligence and Data Science Green University of Bangladesh Dhaka, Bangladesh
ThaiTrees: Thai Syntactic Dependency Trees Across Domains
Sep 23, 2026Attapol T. Rutherford, Papatchol ThientongLow-Resource Language Processing Dependency Parsing
Department of Linguistics Chulalongkorn University
AraGenre 2026: A Hierarchical Definition-Guided Arabic Genre Classification Shared Task
Sep 23, 2026Mo El-Haj, Saad Ezzini, Shadi Abudalfa +3Arabic NLP Zero-Shot Text Classification
VinUniversity, Vietnam · Lancaster University, UK · King Fahd University of Petroleum and Minerals, Saudi Arabia +3
TransBERT: A Framework for Synthetic Translation in Domain-Specific Language Modeling
Sep 22, 2026Julien Knafou, Luc Mottin, Anaïs Mottaz +2Synthetic Data Pretraining Language Modeling
HES-SO, Geneva, Switzerland · SIB, Swiss Institute of Bioinformatics, Geneva, Switzerland
ARAFA: An LLM-Generated Arabic Fact-Checking Dataset
Sep 22, 2026Christophe Khalil, Shady Elbassuoni, Rida AssafArabic NLP Automated Fact-Checking
Computer Science, American University of Beirut, Beirut, Lebanon
ToneCL: Contrastive Learning for Few-Shot Syllable-Level Tone Classification
Sep 21, 2026Qisheng Liao, Youngah DoContrastive Learning Few-Shot Audio Classification
Department of Linguistics The University of Hong Kong
URA-NER: A Unified Retrieval-Augmented Framework with Retrieval Alignment and Uncertainty Reduction for Low-Resource NER
Sep 21, 2026Jingyu Wang, Shijie Wu, Fusheng JinNamed Entity Recognition In-Context Learning
School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China
Zero-Shot Cross-Lingual Recognition of Sign Language Handshapes
Sep 16, 2026Marcel Granero-Moya, Carolina del Corral Farrarós, Gloria Haro +2Zero-Shot Learning Sign Language Recognition
Universitat Pompeu Fabra
A Scalable Framework for Automated NER Annotation Correction in Low-Resource Languages
Sep 16, 2026Toqeer Ehsan, Thamar SolorioNamed Entity Recognition Low-Resource Language Processing
Quantitative Science and Technology Studies (QSTS), VTT Technical Research Centre of Finland Ltd., Espoo, Finland · Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), Masdar City, Abu Dhabi, United Arab Emirates

Oct 8, 2026, cs.CLJ/K move · Enter open · S save

Language-Specific Effects of Tokenizer Choice in Multilingual Language Models

Clara Meister, Gül Sena Altıntaş, Antoine Bosselut

EPFL · University of Toronto, Vector Institute

Multilingual Language Models Multilingual Language Model Evaluation Low-Resource Language Processing

Open paper AskPDF arXiv

Tokenizer choice affects multilingual language modeling, but vocabulary capacity is finite and vocabulary size is often constrained: improving representation for some languages often comes at the expense of others. We therefore ask whether tokenizer choice matters equally across languages, a question that the current literature leave unanswered. To this end, we train 123 language models spanning 54 tokenizers. In the main comparison, architecture, training corpus, training-token budget, and optimization are held fixed, so the models differ only in their tokenizer. We find that tokenizer choice matters more for languages with less language-model training data: across the 54 tokenizers, the standard deviation of a language's bits-per-byte (BPB) increases as its model training-data share decreases (Spearman rho = -0.52 over the 31 trained languages and -0.69 over the 28 written with word boundaries). Leaving a language out of tokenizer training raises its BPB in every language we study, and the penalty tends to be larger for languages with less language-model training data. Giving lower-resource languages a larger share of tokenizer-training data, however, does not unconditionally help those languages: both equal weighting and an allocation inverting the shares with respect to the language model training data increase their BPB, particularly when language-model training repeats data. Finally, which intrinsic tokenizer properties are associated with better BPB differs across languages, providing further evidence that what makes a good tokenizer depends on the language. We find that the metrics quantifying these properties can be successfully used to predict downstream models' pairwise BPB rankings, suggesting a practical strategy for screening tokenizer candidates before training language models.

Momentum

Related topics

Latest papers 342