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

Jun 23, 2026cs.CL

A Pāninian Foundation for Indic Language Processing

More than a billion people communicate in Indic languages, yet the natural language processing infrastructure serving them remains fragmented and underdeveloped. The cause is structural: the field organizes its tools and benchmarks around individual languages or small subsets of genealogical language families, building separate analyzers, parsers, and datasets for each language and starting over for the next. This overlooks a deep regularity. Through more than two millennia of convergence around Sanskrit, Indic languages came to share a morphosyntactic architecture formalized in Pānini's grammar, the Astādhyāyī. This cuts across genealogical lines, uniting languages through a common framework. We argue that this Pāninian framework supplies a unifying computational architecture the field has lacked, and that benchmarks grounded explicitly in it would make Indic language systems more accurate, more data-efficient, and more transferable, effectively merging many apparently disparate and sparse Indic language resources into a single high-resource metalanguage bedrock. We propose a four-part benchmark suite to render this shared architecture explicit, measurable, and ready to be leveraged for practical applications. Moreover, we underscore the question it raises for interpretability research: whether neural models trained on these languages come to represent Pānini's categories on their own.

Ritwik Banerjee, Lav R. Varshney

Department of Computer Science, Stony Brook University, USA · AI Innovation Institute, Stony Brook University · AI Innovation Institute, Stony Brook University, USA +1

Multilingual Language Model Evaluation Low-Resource Language Processing Cross-Lingual Transfer

Jun 23, 2026eess.AS

A Fusion-Aware Two-Stage Framework for Mispronunciation Detection and Diagnosis in Low-Resource Modern Standard Arabic

Accurate phoneme recognition is pivotal for mispronunciation detection and diagnosis (MDD) in modern standard Arabic (MSA), yet remains constrained by data scarcity and the synthetic-real domain gap. This work proposes a two-stage end-to-end framework. It integrates a pre-trained encoder with causal dilated temporal convolutional networks to preserve fine-grained phonetic variations. A hierarchical two-stage strategy first learns general mappings from native/synthetic corpora, then adapts to scarce real learner data to mitigate domain shift without over-correction. Prediction stability is further enhanced via multi-checkpoint ensemble inference with N-gram rescoring. Evaluated on the QuranMB.v2 test set, our system achieves an F1-score of

0.7201

, a

63.1

% relative improvement over baseline (

0.4414

). This performance ranks at the top of the IqraEval.2 Challenge, establishing a new state-of-the-art for low-resource MSA in MDD.

Jing Yang, Shuqing Zhang, Yongyi Deng +5

School of Electronic Information, Wuhan University, Wuhan Hubei, 430072, China · School of Computing and Information Systems, University of Melbourne, Melbourne, Australia · Northwestern Polytechnical University +1

Domain Adaptation Speech Processing Automatic Speech Recognition Low-Resource Language Processing

Jun 23, 2026cs.SD

VieSpeaker: A Large-Scale Vietnamese Speaker Recognition Dataset Beyond Visual Dependency

Speaker recognition has advanced rapidly with large-scale training datasets, yet Vietnamese remains under-resourced, with existing corpora limited in scale and acoustic diversity. Most large-scale datasets rely on facial cues to link speech with speaker identities, restricting data collection to recordings where speakers appear on camera. We propose a face-independent dataset construction pipeline and introduce VieSpeaker, a large-scale Vietnamese speaker recognition dataset. Our approach leverages textual metadata and large language model reasoning to infer speaker identities from transcripts and contextual information. VieSpeaker contains approximately 902 hours of speech from 4,715 speakers. Experiments show that models trained on VieSpeaker achieve improved robustness and generalization compared to existing Vietnamese datasets. This work demonstrates the feasibility of face-independent dataset construction and provides a new direction for building large-scale speech resources.

Viet Hoang Pham, Tran Trung Nguyen, Bao Thu Ho +2

Hanoi University of Science and Technology, Hanoi, Vietnam

Speech Processing Low-Resource Language Processing

Jun 22, 2026cs.CL

QuechuaTok: Morphological Boundary Accuracy as a Necessary Metric for Tokenizer Evaluation in Agglutinative Low-Resource Languages

Tokenization is a foundational step in NLP pipelines, yet standard evaluation metrics such as fertility rate fail to capture morphological correctness for agglutinative languages. We present QuechuaTok, a systematic benchmark comparing four tokenization strategies - BPE, Unigram LM, WordPiece, and a morphology-aware PRPE tokenizer - for Southern Quechua (quz), a low-resource agglutinative language spoken by 8-10 million people in South America. Using a 200k-sentence corpus and the SQUOIA finite-state morphological analyzer (Rios, 2016) as silver standard, we evaluate three metrics: fertility rate, OOV rate, and morphological boundary accuracy (MorphAcc). Our results show that BPE achieves the lowest fertility rate (1.636 at 16k vocab) by memorizing surface word forms, while achieving only 6.67% MorphAcc. PRPE achieves 83.33% MorphAcc - the highest of all systems - demonstrating that fertility rate alone is insufficient to evaluate tokenizers for agglutinative languages. All code and models are publicly available at kaggle.com/code/macmaky/quechuatok

Maria Contreras

Universidad Peruana de Ciencias Aplicadas (UPC) Lima, Peru

Low-Resource Language Processing Subword Tokenization

Jun 22, 2026cs.CV

Koshur Pixel: a large-scale synthetic ocr dataset for kashmiri

Optical Character Recognition (OCR) for low-resource languages is often constrained by the lack of annotated training data and the complexity of script-specific rendering. Kashmiri, written primarily in the Perso-Arabic Nastaliq script, presents additional challenges due to contextual glyph shaping, dense ligatures, and orthographic variability. We introduce Koshur Pixel, the first large-scale synthetic OCR dataset for Kashmiri, comprising 613,078 image-text pairs generated from the KS-PRET-5M corpus using the SynthOCR-Gen framework. The dataset spans multiple fonts and textual granularities, ranging from individual words to full-page documents, and incorporates more than 25 augmentation strategies that emulate real-world document degradations. Koshur Pixel provides a scalable and cost-effective alternative to manual annotation, establishing a foundational resource for training OCR systems, digitizing Kashmiri textual heritage, and advancing language technologies for a severely under-resourced language.

Haq Nawaz Malik, Faizan Iqbal, Nahfid Nissar

Synthetic Data Generation Low-Resource Language Processing Optical Character Recognition

Jun 21, 2026cs.CL

ROMEVA: Geometry-Preserving Vocabulary Expansion for Roman Urdu Language Models

Multilingual Language Models like mBERT are widely used for low-resource NLP, yet their adaptation to morphologically inconsistent languages such as Roman Urdu remains underexplored. Roman Urdu spelling variation causes severe sub-word fragmentation, averaging 1.50 sub-words per token. We propose \textit{ROMEVA} (Roman Urdu Embedding-preserving Vocabulary Adaptation), which combines sub-word-average initialization and a PCA-guided anchor loss to stabilize embeddings during vocabulary expansion. Using a 36,130-comment Roman Urdu corpus, we add 500 highly fragmented tokens to mBERT and compare naive fine-tuning, sub-word-aware fine-tuning, and \textit{ROMEVA}. While \textit{ROMEVA} most effectively preserves the pretrained embedding space, naive fine-tuning achieves the strongest downstream sentiment classification performance. These findings reveal a disconnect between embedding stability and downstream performance, suggesting that stronger adaptation may be preferable to strict embedding preservation in morphologically inconsistent languages.

Mahnoor Khan, Afsheen Asif, Milhan Afzal Khan +2

School of Electrical Engineering and Computer Science (SEECS), National University of Sciences and Technology (NUST), Islamabad, Pakistan · Department of Computer Science, University of Agriculture Faisalabad, Faisalabad, Pakistan

Multilingual Language Models Word Embeddings Low-Resource Language Processing Representation Geometry in Language Models

Jun 21, 2026cs.SD

Neural Speaker Diarization via Multilingual Training: Evaluation on Low-Resource Nepali-Hindi Speech

Speaker diarization, the task of determining "who spoke when" in a multi-speaker recording, is a critical component in applications such as meeting transcription, accessibility tools, and multilingual information retrieval. While end-to-end neural diarization systems have achieved strong performance for English and other high-resource languages, their effectiveness degrades substantially for underrepresented languages where annotated speech data is scarce. This paper investigates speaker diarization for low-resource Nepali-Hindi speech through a multilingual training approach, comparing two modern architectures: EEND with encoder-decoder attractors (EEND-EDA) and EEND with Perceiver-based attractors (DiaPer). Both models are trained on a multilingual corpus combining English speech from LibriSpeech, diverse speaker recordings from VoxCeleb, and separately collected Nepali and Hindi audio, a setup designed to reduce language bias and encourage cross-lingual generalization. We evaluate both models across 2-speaker, 3-speaker, 4-speaker, and mixed-speaker scenarios on LibriSpeech, VoxCeleb, and Nepali-Hindi (NeHi) test sets. DiaPer achieves stronger overall performance than EEND-EDA, particularly in more challenging multi-speaker conditions, obtaining DERs of 3.28%, 2.02%, 4.05%, and 4.76% on NeHi 2-speaker, 3-speaker, 4-speaker, and mixed-speaker settings, respectively, compared to 1.50%, 9.68%, 16.17%, and 11.19% for EEND-EDA. These results demonstrate the viability of Perceiver-based end-to-end neural diarization for low-resource multilingual speech processing.

Samip Neupane, Sandesh Pokhrel, Sandesh Pyakurel +1

Department of Electronics and Computer Engineering, Pulchowk Campus, Institute of Engineering, Lalitpur, Nepal

Low-Resource Language Processing Speaker Diarization Cross-Lingual Transfer

Jun 20, 2026cs.CL

From Speech to Text Corpora: Evaluating ASR-Based Data Acquisition for Low-Resource Fongbe and Hausa

Low-resource African languages lack text corpora needed for language model training. We investigate whether ASR pipelines can extend text resources for two typologically distinct West African languages: Fongbe (tonal, diacritic-rich) and Hausa (non-tonal). We fine-tune MMS-300M on a curated 12.3-hour Fongbe dataset, achieving 9.48% WER on the ALFFA benchmark - a 78% relative reduction from the prior 44.04% baseline - while preserving tonal diacritics critical to the language. For Hausa, we apply an existing fine-tuned Whisper-Small model. We catalog 1,553 YouTube videos (236 hours) and process a subset of 424 videos (45.49 hours) selected to balance domain diversity with available computational resources, producing 6,770 transcribed segments. Human evaluation on 50 randomly sampled segments per language shows mean quality scores of 57.4/100 for Hausa and 36.5/100 for Fongbe, indicating that while Hausa transcriptions approach acceptable quality for corpus construction, Fongbe transcriptions require post-processing or improved models for production use. We release the curated dataset, fine-tuned model, transcribed corpus, and full video catalog following platform terms and ethical guidelines.

Mahounan Pericles Adjovi, Victor Olufemi, Roald Eiselen +1

Carnegie Mellon University Africa, Kigali, Rwanda · North-West University, South Africa

Automatic Speech Recognition Low-Resource Language Processing Low-Resource Speech Recognition Multilingual ASR

Jun 20, 2026cs.CL

Olfactory-Inspired Sparse Combinatorial Coding for Low-Resource Named Entity Recognition

Named Entity Recognition (NER) in low-resource languages suffers from limited supervision and a lack of high-quality pretrained embeddings. Biological olfaction, which relies on sparse combinatorial coding through receptor and glomerular organization, offers a compelling paradigm for learning robust representations under uncertainty. In this paper, we introduce a receptor-glomerular bottleneck - a novel, biologically-inspired olfactory architecture - between standard token embeddings and a BiLSTM-CRF sequence model. We evaluate our architecture across six multilingual datasets trained entirely from scratch (without pre-trained embeddings) under varied data-scale conditions, including a strict 1k-sentence low-resource control. Our results demonstrate that introducing a representation bottleneck yields F1 score improvements under severe data scarcity, primarily by acting as a powerful regularizer. Under the 1k capped training condition, at least one olfactory-inspired configuration achieves the highest mean F1 score across all six datasets. While these improvements represent near-ties with generic bottleneck controls for most languages, the olfactory architecture provides a significant advantage in languages like Bangla (+6.23% F1 over standard baseline and +8.47% F1 over the best control baseline) where generic bottlenecks degrade performance. We also observe improvements in the ultra-low-resource Telugu setting (+4.43% F1) at full-scale, and find that sparse specialization naturally emerges within the receptor layer. Our findings suggest that structured sparse coding inspired by olfactory networks serves as an effective inductive bias and regularizer when representations must be learned from limited or noisy supervision.

Bhushan Deshpande

Independent Researcher, India

Named Entity Recognition Representation Learning Low-Resource Language Processing Sparse Coding

Jun 20, 2026cs.CL

The Language-Energy Divide: Measuring Energy Costs of Multilingual LLM Inference

Large language models (LLMs) are increasingly deployed in multilingual settings, yet the energy costs of serving these models across different languages remain poorly understood. We present a systematic study of inference energy consumption across languages with ML.Energy framework (Chung et al., 2026). We find striking disparities: energy consumption per output token varies by up to 8.3 times across languages, while total energy for a fixed set of requests varies by up to 179 times between the cheapest (English, 17.6 kJ) and the most expensive (Pashto, 3,147 kJ) languages. Our analysis shows that this disparity is driven by two compounding factors: (1) higher per-token energy costs for languages using complex or rare scripts, and (2) more tokens generated for low-resource languages. Moreover, we find a double cost + performance penalty: languages with the highest energy footprints also tend to achieve the lowest task accuracy. We reveal that the energy divide persists across models, hardware, and tasks, suggesting a systemic energy inequity in multilingual LLM deployment. Finally, we recommend that the community treat energy as a first-class evaluation axis, extend reporting checklists and model cards to include it, and adopt deployment-side mitigations for better energy efficiency.

Naihao Deng, Alissa Shen, Yiming Feng +5

University of Michigan · University of Cambridge · University of Aberdeen

LLM Inference Efficiency Multilingual Language Models Multilingual Language Model Evaluation Low-Resource Language Processing

Jun 19, 2026cs.CL

Leveraging LaBSE with Progressive Curriculum Learning for Multicultural Polarization

Detecting online polarization remains a critical challenge, particularly in multilingual and multicultural contexts where intergroup hostility is prevalent. The problem is particularly challenging due to the data scarcity for these tasks in the low-resource languages. Identifying such phenomena has become an active area of research and is addressed in SemEval-2026 Task 9: Multilingual, Multicultural Online Polarization Detection. To address this problem we propose an architecture that leverages LaBSE embeddings - an unconventional choice typically reserved for retrieval tasks, to obtain strong cross-lingual learning which enhances scores in low-resource language by a score up to 0.2 macro F1. Furthermore, we provide a comprehensive ablation study evaluating the performance of diverse encoder models in the Qwen model family within a retrieval-based prompting framework. Our code will be soon available at https://github.com/carrycurious/PolarMind.

Sachin Sundar, Sandeep Kumar, Mothish M

Indian Institute of Technology, Kharagpur

Multilingual Language Models Low-Resource Language Processing

Jun 19, 2026cs.CL

OpenWER: Improving Cross-Lingual ASR Evaluation and Enabling Token-Based Accuracy Metrics

Advances in deep learning and end-to-end Automatic Speech Recognition (ASR) have enabled robust multilingual models, but evaluation metrics remain limited in assessing accuracy. Efforts to improve or replace the common metric Word Error Rate (WER) often focus on English, leaving evaluations for low-resource languages under-explored and hindering fair cross-lingual comparisons. We present OpenWER, an open-source implementation that improves WER robustness through language-specific normalisation and compound word detection. A token-based Levenshtein alignment preserves complementary metrics and allows metadata embedding for granular accuracy scores. Our analysis of 52 languages shows absolute WER reductions of up to 25% compared to common libraries. OpenWER contributes to fairness in ASR research by increasing the reliability of WER across diverse languages and enabling more comprehensive accuracy evaluations.

Korbinian Kuhn, Gottfried Zimmermann

Stuttgart Media University, Germany · University of Tübingen, Germany

ASR Evaluation Low-Resource Language Processing Multilingual ASR

Jun 18, 2026cs.CL

Phonemes to the Rescue: Multilingual Tokenization Based on International Phonetic Alphabet

Multilingual language models often exhibit performance disparities across languages that can arise as early as the tokenization stage. Widely-used subword tokenization approaches favor high-resource languages, and tokenizer-free methods still yield longer sequences for scripts with a higher bytes-per-character ratio. To address these shortcomings, we propose to use the International Phonetic Alphabet (IPA) as a language-agnostic input representation for multilingual tokenizers. IPA provides a compact symbol inventory, greater cross-lingual character overlap, and a more balanced byte-per-character distribution across languages. We train matched pairs of text vs. IPA subword tokenizers across 24 languages and 14 scripts and demonstrate that IPA tokenizers consistently improve tokenization quality, especially for non-Latin scripts, and generalize more effectively to unseen languages and scripts.

Milan Miletić, Julie Kallini, Ekaterina Shutova

University of Amsterdam · Stanford University

Multilingual Language Models Low-Resource Language Processing Subword Tokenization

Jun 18, 2026cs.CL

ReNikud: Audio-Supervised Hebrew Grapheme-to-Phoneme Conversion

Grapheme-to-phoneme (G2P) conversion for Modern Hebrew is needed for applications like text-to-speech (TTS), but is challenging due to the language's abjad writing system, which leaves vowels largely unwritten, creating substantial ambiguity. Standard approaches first predict vowel diacritics (nikud) to produce International Phonetic Alphabet (IPA) transcriptions, but this is limited: vocalization data is scarce and laborious to produce, it does not specify features such as lexical stress, and it reflects formal grammatical rules rather than everyday spoken pronunciation. Direct sequence-to-sequence IPA prediction, meanwhile, struggles on limited data and fails to exploit the character-level alignment characteristic of abjads. Our method, ReNikud, overcomes these limitations with two key insights: (1) Weak audio supervision via a phoneme-based automatic speech recognition (ASR) pseudo-labeling pipeline on thousands of hours of unlabeled Hebrew audio, yielding phonemic transcriptions that reflect natural spoken norms without manual annotation. (2) A pseudo-vocalization architecture that predicts IPA phonemes at each character position, enforcing character-level alignment as an inductive bias. Results on existing Hebrew G2P benchmarks and the new targeted MILIM benchmark for spoken Hebrew show that ReNikud surpasses previous state-of-the-art methods. We will release our code and trained models to support further work on Hebrew TTS and speech technologies.

Maxim Melichov, Yakov Kolani, Morris Alper

Independent Researcher · Carnegie Mellon University

TTS Synthesis Low-Resource Language Processing G2P Conversion

Jun 18, 2026cs.CL

IHUBERT: Vector-Based Semantic Deduplication and Domain-Balanced Pretraining for Persian Resources

Persian pretrained language models (PLMs) are still limited by the scarcity of large-scale, high-quality pretraining corpora and by insufficient evaluation beyond standard classification and NER tasks. We present IHUBERT, a monolingual Persian PLM trained from scratch with the RoBERTa-base encoder (125M parameters) on a 45 GB curated subset of the Sepahr-Danesh collection (about 7-8B tokens). To improve corpus quality and reduce redundancy, we employ a multi-stage preprocessing pipeline that includes normalization, exact and near-duplicate removal, anonymization, and vector-database-based semantic deduplication for distribution balancing control across domains and registers. We additionally train a 139k-vocabulary BPE tokenizer on the full pretraining corpus to better capture Persian morphology and orthographic variation. IHUBERT is evaluated on seven Persian NLU benchmarks covering NER, sentiment analysis, topic classification, NLI, extractive question answering, and relation extraction, using task-standard metrics (entity-level F1, Macro-F1, EM/F1). IHUBERT achieves its strongest gains on extractive QA, ranking first on both PQuAD (F1 88.3542) and ParsiNLU-RC (F1 49.0987), and attains the best result on FarsTail (Macro-F1 0.8350). On NER and topic classification, it remains competitive (e.g., 0.8308 F1 on ParsTwiNER; 0.7953 Macro-F1 on DigiMag), while relation extraction remains the main remaining gap (0.6684 Macro-F1 on PERLEX). A controlled tokenizer ablation on the IHUBERT pretraining corpus shows that BPE yields slightly lower subword fragmentation than WordPiece at matched vocabulary size, supporting our tokenization design. Overall, IHUBERT advances Persian language modeling through semantically curated large-scale pretraining and broad evaluation across both classification and comprehension-oriented tasks.

Arash Ghafouri, Mahdi Firouzmandi, Hossein Saberi +1

Department of Artificial Intelligence and Cognitive Science, Imam Hossein Comprehensive University, Tehran, Iran.

Language Model Pretraining Language Modeling Low-Resource Language Processing

Jun 17, 2026cs.CL

A BART-based approach with hierarchical strategy for Vietnamese abstractive multi-document summarization

In this technical report, we focus on solving the challenge of Vietnamese multi-document abstractive summarization, introduced in the International Workshop on Vietnamese Language and Speech Processing (VLSP) 2022. We choose to follow the popular hierarchical approach, i.e. condensing each document followed by aggregation and summarization. We propose a novel yet simple strategy to shorten documents that is driven by the golden summary, thus ensuring high correlation between stages of the hierarchical approach. Our method achieves a ROUGE2-F1 score of 0.2468 on the VLSP's public test set, and can produce fluent and concise summaries. Additionally, we utilize external sources for extra data, which greatly enhances the quantity of data for Vietnamese multi-document summarization. The additional data is made available for the community.

Vu Nguyen Nguyen Xuan, Huy Ngo Quang

Aimesoft JSC

Text Summarization Low-Resource Language Processing

Jun 17, 2026cs.CV

PorTEXTO: A European Portuguese Benchmark for Visual Text Extraction

European Portuguese (pt-PT) is largely absent from Optical Character Recognition (OCR) benchmarks, which skew toward high-resource languages. The few benchmarks that cover pt-PT focus on historical artifacts and literature. This work addresses modern OCR applications, introducing PorTEXTO, the first benchmark for contemporary and culturally relevant pt-PT visual text extraction. To ascertain quality, we employ an annotation pipeline combining transcriptions from a frontier LVLM with exhaustive review by native speakers. We observe a sharp performance drop from synthetic to real world samples in most models, and find that, currently, specialized multilingual data is a better driver for pt-PT performance than model size or resolution budget, motivating the release of open pt-PT OCR resources.

João Cardeira, Diogo Glória-Silva, Manuel Letras da Luz +4

NOVA School of Science and Technology · NOVA LINCS

Low-Resource Language Processing Optical Character Recognition

Jun 16, 2026cs.CL

Want Better Synthetic Data? Steer It: Activation Steering for Low-Resource Language Generation

Large language models (LLMs) have become an effective tool for synthetic data generation, including for low-resource languages, where generated data can improve downstream task performance. Current best-performing approaches typically rely on few-shot prompting with target-language examples, which increases inference costs and may reduce diversity through lexical anchoring. In this work, we investigate activation steering as an alternative for low-resource synthetic data generation. We study two steering strategies: Language Steering, which targets the linguistic identity of a language, and Quality Steering, which captures well-formedness by contrasting human-written and backtranslated text representations. We evaluate these methods across four open-source LLMs, multiple layers, and 11 typologically diverse languages by generating sentiment and topic classification data and finetuning smaller classifiers. Steering is applied in both zero-shot and few-shot prompting settings and compared against non-steered counterparts. Our results show that steering on early layers consistently improves the diversity of generated data while often yielding stronger downstream model performance, particularly for low-resource languages.

Jan Cegin, Daniil Gurgurov, Yusser Al Ghussin +1

Kempelen Institute of Intelligent Technologies, Bratislava, Slovakia · German Research Institute for Artificial Intelligence (DFKI), Saarbrücken, Germany

Language Model Steering Synthetic Data Generation for Language Models Low-Resource Language Processing Activation Steering

Jun 15, 2026cs.CL

Examining the Limits of Word2Vec with Toki Pona

Word2Vec's effectiveness at generating semantic embeddings has been widely validated, yet it has been tested almost exclusively on languages with large vocabulary inventories. This study examines whether Word2Vec can successfully capture semantic relationships within an extremely reduced vocabulary using data from Toki Pona, a constructed language with approximately 130 words. We sourced 1.4 million sentences (7.95 million tokens) from the Toki Pona community for training. Approximately 23% of sentences in the corpus contain non-Toki Pona tokens such as named entities, loanwords, and neologisms. To investigate whether this linguistic noise enhances or hinders performance -- a topic rarely addressed in word embedding literature -- we trained two distinct models: one retaining these incidental tokens and another filtering them out completely. Evaluation was conducted using quantitative methods measuring word proximity to semantic category centroids, automated silhouette scores via agglomerative clustering, and qualitative analysis utilizing representational similarity matrices compared against English. The results indicate that while sparse, non-core tokens do not affect the relative structure of the learned embeddings, they actually draw similar words closer together in the vector space. Importantly, Word2Vec's effectiveness depends more on distributional patterns than lexicon size even at this extreme lower bound.

Daniel Zhenhan Huang, Hongchen Wu

Georgia Institute of Technology Atlanta, GA

Text Embedding Evaluation Distributional Semantics Low-Resource Language Processing Text Embedding Models

Jun 15, 2026cs.CL

Surpassing Scale by Efficiency: A Compact 135M Parameter Foundational LLM Natively Adapted for the Bangla Language

While the NLP landscape is dominated by multi-billion parameter architectures, their deployment in low-resource, non-Latin scripts remains computationally prohibitive for edge configurations, mobile systems, and decentralized local hardware. This paper presents bangla-smollm-135m, a highly compact 135-million parameter decoder-only foundational model engineered explicitly for high-efficiency language modeling in the Bangla script. By leveraging a deterministic intersect-and-append token merging strategy between TituLLMs and SmolLM2-135M, the model overcomes subword script fragmentation without destabilizing early pretrained parameter states. In zero-shot multi-task benchmark evaluations (PIQA_bn, OpenBookQA_bn, CommonsenseQA_bn, and Bangla_MMLU), bangla-smollm-135m matches or outperforms models twice its size (Gemma-3-270m) and achieves parity with models in the 1B parameter tier. The model is available at rnnandi/bangla-smollm-135m

Rabindra Nath Nandi

Independent Researcher

Decoder-Only Language Models Small Language Models Low-Resource Language Processing

Jun 14, 2026cs.CV

A Text Recognition Dataset from Sahidic Coptic Ancient Manuscripts

In this work, we target Handwritten Text Recognition (HTR) in low-resource scenarios, which arise from underrepresented languages, rare scripts, and degraded visual conditions typical of historical documents. We introduce SCAM (Sahidic Coptic Ancient Manuscripts), a new line-level dataset built from digitized ancient manuscripts written in the extinct Sahidic Coptic dialect. The dataset reflects a realistic and challenging setting, as it combines heterogeneous acquisition conditions across libraries with typical manuscript degradations such as ink fading, bleed-through, and material deterioration. In addition to visual complexity, SCAM poses significant linguistic challenges due to the scarcity of resources for Sahidic Coptic, its uncommon alphabet, and dialect-specific diacritics. To support research in low-resource HTR, we benchmark several state-of-the-art approaches based on different paradigms, highlighting their limitations and strengths in this setting. Our results underline the gap between current HTR performance on well-resourced modern scripts and historically grounded, low-resource scenarios, thus providing a reference point for future developments.

Fabio Quattrini, Carmine Zaccagnino, Costanza Bianchi +2

University of Modena and Reggio Emilia, Modena, Italy

Online Handwriting Recognition Low-Resource Language Processing Optical Character Recognition

Jun 14, 2026cs.CL

Koshur Diacritizer: A Byte-Level Sequence-to-Sequence Model for Kashmiri Diacritic Restoration

Kashmiri, an Indo-Aryan language written in a modified Perso-Arabic script, frequently omits diacritic marks in digital text, creating ambiguity and challenging downstream NLP applications. We present Koshur Diacritizer, a ByT5-small byte-level sequence-to-sequence model for restoring diacritics in Kashmiri text. To support this task, we release a publicly available dataset of 23.7k aligned undiacritized diacritized Kashmiri sentence pairs. The proposed framework combines script-aware normalization, alignment validation, and skeleton-preserving inference to ensure reliable restoration while maintaining the original base-letter sequence. Experimental results on a held-out test set achieve a DERm of 0.2012 and a WER of 0.2159. Additionally, evaluation by a native Kashmiri linguistic expert yields a mean accuracy of 77.5%. The dataset, model, and source code are publicly released to provide a reproducible baseline for Kashmiri diacritic restoration and future low-resource language research.

Haq Nawaz Malik, Nahfid Nissar, Faizan Iqbal

ORCID: 0009-0003-1994-7640 · ORCID: 0009-0002-2805-4687 · ORCID: 0009-0002-8998-9347

Low-Resource Language Processing

Jun 13, 2026cs.CL

AmchiBias: Measuring Stereotypical Bias in Goan Identity Groups with a Minimal Pair Dataset in English and Konkani

Socio-cultural stereotypical bias is an important consideration in the development and deployment of NLP systems. It is however often considered only at the national level, despite rich subnational socio-cultural structures. We present AmchiBias, the first benchmark for measuring socio-cultural stereotypical bias for the Indian state of Goa with its unique historically multicultural setting. It covers various Goan identity groups and comprises 313 minimal pairs across eight sociodemographic dimensions in both English and Devanagari Konkani. We then evaluate stereotypical bias in five multilingual encoder models on this benchmark. We find near-chance scores in Konkani, reflecting language incompetence for general multilingual models and a lack of Goan cultural competence for Indian language models. Queried in English, models with a stronger Indian language coverage show higher bias for pan-Indian groups than hyperlocal Goan groups. This suggests the English signal reflects pan-Indian pretraining associations rather than genuine Goan cultural knowledge. Our findings highlight a critical gap in low-resource multilingual NLP evaluation for hyperlocal community identities.

Michelle Barbosa, Sebastian Padó, Franziska Weeber

Institute for Natural Language Processing, University of Stuttgart

Multilingual Language Model Evaluation Cultural Bias in Language Models Language Model Bias Evaluation Linguistic Bias in Language Models Low-Resource Language Processing

Jun 13, 2026cs.CL

PACUTE: Phonology-, Affix-, and Character-level Understanding of Tokens for Filipino

Large language models (LLMs) process text as sequences of subword tokens, which can obscure the character-level and morphological structure that underlies word formation. This limitation is most acute for languages with non-concatenative morphology, where standard tokenizers systematically misalign token boundaries with morpheme boundaries. We introduce PACUTE, a diagnostic benchmark of 4,600 tasks designed to evaluate morphological understanding in Filipino, a language characterized by productive infixation, reduplication, and diacritic-driven lexical distinctions that are typically absent from written text. PACUTE includes a hierarchical diagnostic framework of six compositional levels that localizes where morphological understanding breaks down. Evaluating open-weight LLMs and frontier commercial models, we find that open-weight models perform near chance on morpheme decomposition regardless of scale. Frontier models perform much better, often recovering individual affixes under contains-match scoring, but remain far below their character-level ceilings on compositional tasks of morpheme transformations and syllabification. These results identify productive morphological composition, rather than character access alone, as the persistent bottleneck for Filipino word-structure understanding.

Jann Railey Montalan, David Demitri Africa, Jimson Paulo Layacan +3

AI Singapore · Nanyang Technological University · UK AI Security Institute +2

LLM Evaluation Language Modeling Low-Resource Language Processing

Jun 13, 2026cs.CL

Equity with Efficiency: An Empirical Study of Tokenizers for Multilingual Large Language Models

Multilingual large language models (LLMs) depend on subword tokenization to bridge discrete text and continuous neural representation. State-of-the-art multilingual LLMs often use Byte-level Byte-Pair Encoding (BPE) tokenizers that structurally favor high-resource languages and Latin scripts. For speakers of underrepresented languages, particularly those across Southeast Asia, this bias inflates inference costs and widens cross-lingual capability gaps. We present the first systematic comparison of equitable tokenizers on a unified benchmark spanning 11 Southeast Asian languages. Beyond tokenizer-level analysis of compression efficiency and cross-lingual equity, we assess downstream task performance through controlled 1.5B-parameter language model training using the same training data. Our results show that Parity-aware BPE lies on the Pareto frontier of the efficiency-equity trade-off, achieving strong compression parity at competitive cost. Morphology-Driven Byte Encoding delivers the best semantic reasoning performance through morphologically richer representations, albeit at a higher computational expense. Byte Latent Transformer underperforms on downstream tasks, possibly because its architectural assumptions misalign with the constraints of limited low-resource training data. Together, our findings demonstrate that cross-lingual fairness and tokenization efficiency are not fundamentally at odds, and offer practical guidance for designing equitable multilingual models.

Kieron Seven Jun Wei Lee, Muhammad Reza Qorib, Andrew Ivan Soegeng +1

National University of Singapore · Carnegie Mellon University · SAP

Multilingual Language Models Social Bias in Language Models Low-Resource Language Processing Subword Tokenization

Jun 11, 2026cs.CL

SkMTEB: Slovak Massive Text Embedding Benchmark and Model Adaptation

We introduce SkMTEB, the first comprehensive MTEB-style text embedding benchmark for Slovak, a low-resource West Slavic language, comprising 31 datasets across 7 task types -- nearly 4

\times

the depth of existing multilingual benchmark coverage for Slovak. Our evaluation of 31 embedding models reveals that large instruction-tuned multilingual models achieve the strongest performance, while existing Slovak-specific models trained for NLU tasks transfer poorly to embedding tasks. To address the need for efficient, locally-deployable Slovak embeddings, we develop \texttt{e5-sk-small} (45M parameters) and \texttt{e5-sk-large} (365M) by applying vocabulary trimming and fine-tuning to Multilingual E5 models. Despite size reductions of up to 62%, our open-source models achieve competitive performance with proprietary APIs while remaining locally deployable for semantic search and retrieval-augmented generation (RAG). We release the benchmark, models, datasets, and code openly, hoping our approach offers a replicable path for other under-resourced languages.

Marek Šuppa, Andrej Ridzik, Daniel Hládek +2

Comenius University in Bratislava, Slovakia · Kempelen Institute of Intelligent Technologies, Bratislava, Slovakia · Technical University of Košice, Slovakia +1

Text Embeddings Word Embeddings Text Embedding Evaluation Low-Resource Language Processing Text Embedding Models

Jun 11, 2026cs.CL

An End-to-End Hybrid Framework for Rumour Detection in Low-Resources Algerian Dialect

The rapid growth of social media has intensified the spread of rumours. This issue is more challenging in the Algerian context due to the informal and code-switched nature of dialectal content, the scarcity of annotated resources, and the limited effectiveness of standard Arabic NLP tools on dialect text. This paper presents an end-to-end rumour detection hybrid framework for Algerian dialect social media content. We build a domain-specific annotated dataset by combining real social media posts, synthetic data, and the FASSILA corpus, with automatic labeling based on a similarity-based annotation process. A transliteration pipeline is also introduced to generate parallel datasets in Arabic script and Arabizi. We evaluate multiple approaches, including classical machine learning, deep learning, transformers, and hybrid models. Experimental results show that a hybrid approach combining transformer embeddings with a classical classifier achieves the best performance, reaching an F1-score of 0.84. We also find that domain-specific pre-training is more important than model size, with social media-trained models outperforming larger models trained on formal Arabic corpora. These results demonstrate the feasibility of rumour detection in low-resource Algerian dialect settings.

Dihia Lanasri, Fatima Benbarek

ATM Mobilis, USTHB Algiers, Algeria

Fake News Detection Low-Resource Language Processing

Jun 10, 2026cs.CL

AfriSUD: A Dependency Treebank Collection for Evaluating Models on African Languages

Despite their linguistic diversity and global significance, African languages remain underrepresented in research and resources to support NLP. We aim to bridge this gap by introducing AfriSUD, the first large-scale collection of syntactically annotated treebanks for nine diverse African languages spanning major language families and regions across Sub-Saharan Africa. Using the Surface-Syntactic Universal Dependencies (SUD) framework, our community-led effort provides high-quality, native-speaker verified data that capture typological key features such as agglutination and tone. We evaluate a range of models on AfriSUD for part-of-speech tagging and dependency parsing including non-transformer baselines, multilingual pretrained encoders, and LLMs. Our results reveal a significant syntax gap, where models still show clear limitations across the nine languages, suggesting that existing architectures may not fully capture the structural diversity of African-language syntax.

Happy Buzaaba, Cheikh Mouhamadou Bamba Dione, David Ifeoluwa Adelani +15

Princeton University · Laboratory for Artificial Intelligence, Princeton University · Gaston Berger University +20

Multilingual Language Model Evaluation Morphosyntactic Tagging Low-Resource Language Processing Dependency Parsing

Jun 10, 2026cs.CL

Semantic Grading of Written Answers in Low-Resource Language Bangla Using a Fine-Tuned Lightweight Language Model

Bangla is among the world's most widely spoken languages, yet it remains underserved in educational NLP research. In many remote and rural regions, access to qualified subject teachers is limited, and written answers are consequently graded largely by hand, restricting timely and consistent feedback. Automatic assessment is challenging because semantically correct responses can vary substantially in surface form. We present a bilingual (Bangla-English) evaluation system designed for low-resource educational settings that prioritizes semantic correctness over lexical overlap. Our approach fine-tunes a lightweight language model to grade each response using the question, reference answer, and student answer, producing a numeric score and concise, context-grounded feedback suitable for classroom deployment. We also construct a synthetic bilingual dataset to enable controlled training and evaluation. Across proprietary and open-source LLMs evaluated under a unified protocol, our QLoRA-tuned Qwen3-8B confirms consistent improvement by producing the most leakage-resistant feedback (RoRa = 0.819) in synthetic evaluation and the strongest agreement with human scores (rho = 0.936, MAE = 0.725) in a dedicated human study.

Meherun Farzana, Aniket Joarder, Mahmudul Hasan +1

Computer Science and Engineering, University of Dhaka

Educational Assessment Low-Resource Language Processing Automated Grading

Jun 10, 2026cs.CL

Lius: Translation Model Based Instructional Lingustic Using Continual Instruction Tuning In Kupang Malay

Large Language Models (LLMs) offer new potential for translation tasks but often experience performance degradation when handling low-resource languages. To address this limitation, we propose an approach for fine-tuning LLMs on a low-resource language, Kupang Malay. Our approach involves designing a set of instructions by leveraging explicit lexical and semantic features from a bilingual dictionary, and introducing Continual Instruction Tuning (CIT), a training paradigm that enables iterative instruction-based training. Experimental results demonstrate that our model, named Lius, yields notable improvements over standard instruction-tuned models by outperforming 4-6 points, and surpassing both Neural Machine Translation (NMT) and Multilingual LLM models by 10-13 points on several evaluation metrics. These findings highlight the potential of our approach to mitigate the reliance on large-scale parallel data in low-resource language translation.

Joanito Agili Lopo, Yunita Sari, Guntur Budi Herwanto

Department of Computer Science and Electronics Universitas Gadjah Mada

LLM Fine-Tuning Low-Resource MT Instruction Tuning Low-Resource Language Processing