ICT in Developing Communities

Latest papers

• How Many Labels Does a Language Need? Annotation Budgets and Cross-Lingual Pooling for African-Language Text Classification

  Bhanu Prakash Vangala, Sowmya Guda, Navya Vangala · 1 October 2026

  Every text classifier for an African language begins with a budgeting question: how many labelled examples are needed, and can labels from other African languages stand in for them? We answer both questions empirically for 28 language-task pairs, news topic classification in 16 languages (MasakhaNEW…

• One Threshold Does Not Fit All Languages: Language-Conditional Deferral for Reliable and Efficient Low-Resource Text Classification

  Bhanu Prakash Vangala, Vangala Navya · 1 October 2026

  In the Global South, the lower-income countries of Africa, Asia, and Latin America where most of the world's languages are spoken, a deployed text classifier usually runs on ordinary CPUs, serves many languages with a single model, has few labeled examples in any of them, and relies on people to cat…

• RunyaNER: Auxiliary Language Selection for Runyankore NER

  Prosper Arineitwe Asiimwe, Francois Meyer, Jan Buys · 1 October 2026

  Cross-lingual zero-shot transfer and multilingual fine-tuning are promising approaches for NLP tasks such as Named Entity Recognition (NER) in low-resource languages, but in the absence of target language benchmarks, it is unclear which auxiliary language selection strategy leads to the best transfe…

• Towards Model as a Library: Offline, Community-Sourced AI for Low-Resource African Languages

  Fendji K. E. Jean Louis · 1 October 2026

  Large language models are frequently proposed as a route to AI-powered services for African communities, but they are least reliable exactly where the need is greatest: all African languages remain low-resource by any standard measure, and models trained on scraped, standardised text systematically …

• Yor\`{u}b\'{a} in Unicode: An Overview of a Problem

  K\'ol\'a T\'ub\`os\'un · 30 September 2026

  There is a recurrent problem in the writing of Yor\`ub\'a on the internet and on the computer that has proven intractable over the years. The language, along with other African languages that depend on diacritics for disambiguation, requires a small set of precomposed characters that Unicode does no…

• NaijaNLP: A Survey of Nigerian Low-Resource Languages

  Isa Inuwa-Dutse · 28 September 2026

  With over 500 languages in Nigeria, three languages - Hausa, Yor\`ub\'a and Igbo spoken by more than 175 million people, account for about 65% of the languages. However, these languages are classed as low-resource due to insufficient digital resources to support tasks in computational linguistics. W…

• Evaluating Ambient Clinical Scribes in India: The Need for Multilingual Real-World Clinical Conversation Data

  Siddharth D Jaiswal, Krithi S, Ashish Makani, Suvrankar Datta, Sunayana Sitaram, Mohit Jain · 16 September 2026

  Ambient clinical scribes (ACS) are being rapidly deployed at scale across Global South healthcare settings, aiming to reduce clinician documentation time, especially in overburdened environments like India. These ACS are primarily developed or distilled from models built and validated on Global Nort…

• Beyond Good Intentions: When Does the Framing of Multilingual and Low-Resource NLP Research Become a Caricature?

  Nedjma Ousidhoum, Noopur Zambare, Mohamed Abdalla · 1 September 2026

  Building language technologies and conducting NLP research for low-resource languages---particularly when led by native speakers or involving participatory research practices---are often framed as means of addressing inequality, serving local communities, and, at times, contributing to *decolonisati…

• The Annotation Bottleneck in Persian Text NLP: Persian as an Annotation-Scarce Language

  MohammadHossein Mortazavi, Mostafa Salehi, Hadi Veisi · 26 August 2026

  Persian (Farsi) is often described as a low-resource language in natural language processing, but that label collapses distinct shortages into a single category. This paper argues that Persian is more precisely described as annotation-scarce, provided that the term is understood as a property of its…

• Wazobia Eval: A Benchmark for Nigerian Pidgin Emotion Understanding, Sarcasm Detection, and Cultural Reasoning

  Stephanie Okoye · 25 August 2026

  Nigerian Pidgin is one of Africa's most widely spoken languages, yet remains severely underrepresented in language model evaluation. Existing benchmarks primarily focus on translation, transcription, or generic sentiment analysis, leaving critical aspects of culturally grounded language understandin…

• DonorRank: Donor Language Selection for Low-Resource Cross-Lingual Speech Recognition

  Akriti Dhasmana, Aarohi Srivastava, David Chiang · 13 August 2026

  Low-resource automatic speech recognition (ASR) commonly relies on cross-lingual transfer, where models are adapted from higher-resource donor languages. However, selecting donors remains challenging for spontaneous speech from under-resourced language communities, due to linguistic variation, evolv…

• Structural Silence: When AI Infrastructure Fails Speakers of Underrepresented Languages

  Avijit Roy, Proma Roy · 13 August 2026

  Artificial intelligence tools for education and language support are increasingly framed as scalable responses to access gaps in under-resourced communities. Yet the infrastructure underlying these tools, including training corpora, tokenization schemes, evaluation benchmarks, and deployment archite…

• Mwando: Leveraging AI to Preserve and Teach shiKomori

  Naira Abdou Mohamed, Haidar Nassur Said Ali, Mohamed Hazra, Naoufal Mohamed Soibira, Roushnaty Ali Yamani · 28 July 2026

  This paper presents Mwando, a virtual educational assistant designed to support the teaching and preservation of shiKomori, the language of the Comoros Islands. The system covers the four main dialectal variants (shiNgazidja, shiMwali, shiNdzuani and shiMaore) through a knowledge base constructed fr…

• Two Confounds in Cross-Model Value Comparison: Response Determinism and the Access Harness

  Hong-In Won, Jinseok Jang, Hyoseop Kim · 14 July 2026

  Cross-model comparisons read divergence in value dispositions as evidence that language models hold individuated values. Under single-draw measurement this conflates two quantities: a difference in central tendency (a genuine value difference) and a difference in response determinism (how sharply a …

• Building an ASR Solution for Training and Assessing Children's Reading

  Yacouba Diarra, Nouhoum Souleymane Coulibaly, Mamadou Dembele, Aymane Dembele, Michael Leventhal · 1 July 2026

  Automatic speech recognition for children's reading remains underdeveloped for most African languages, including Bambara, despite its potential value for reproducible literacy assessment. We present an open-source system for assessing children's reading in Bambara, developed through an end-to-end pr…

• Improving Survey Participation in Low-Literacy Populations Through Value-Sensitive Conversational AI

  Raj Gaurav Maurya · 1 July 2026

  Collecting reliable social data from low-literacy populations remains a persistent challenge, particularly when surveys involve sensitive topics and marginalized communities. Traditional paper-based and web-based survey modalities often suffer from high attrition and incomplete responses due to lite…

• Mapping the Artificial Intelligence Divide in Africa: Infrastructure, Accessibility and Capacity

  Abayomi O. Agbeyangi, Jose M. Lukose · 1 July 2026

  Artificial Intelligence (AI) has the potential to be transformative for development, but Africa is currently facing a fragmented and challenging "AI divide". This paper provides an empirical analysis of the current state of the AI landscape and how it compares with Africa's technological preparednes…

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

  Mahounan Pericles Adjovi, Victor Olufemi, Roald Eiselen, Prasenjit Mitra · 23 June 2026

  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-hou…

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

  Jan Cegin, Daniil Gurgurov, Yusser Al Ghussin, Simon Ostermann · 18 June 2026

  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 i…

• Complex Layout Classification in the Wild: A Low-Resource Approach with Layout-Preserving Augmentations

  Sharva Gogawale, Iddo Hakim, Gal Grudka, Mohammad Suliman, Omer Ventura, Daria Vasyutinsky-Shapira, Berat Kurar-Barakat, Nachum Dershowitz · 17 June 2026

  Many digitized corpora suffer from low resources because annotations may be scarce, page scans are noisy and of poor resolution, or layouts are structurally complex in ways that negatively affect the quality of automatic transcription. Developing robust classification models for low-resource languag…

• Information Security in Small-Scale Protests: Surveillance of Ugandan Anti-EACOP Protesters

  Ntezi Mbabazi, Rikke Bjerg Jensen · 29 May 2026

  We examine the information security practices of Ugandan climate activists protesting the development of the East African Crude Oil Pipeline (EACOP). We conducted five-week fieldwork in Kampala, Uganda, which included interviews with 13 anti-EACOP activists. Through an inductive analysis, we report …

• Benchmarking AI for low-resource contexts: Thinking beyond leaderboards

  Aakash Pant, Kavya Shah, Apoorv Agnihotri, Sneha Nikam, Prasaanth Balraj, Nakul Jain · 28 May 2026

  Existing AI evaluation practices often fail to capture how systems actually perform in low-resource environments, where operational constraints shape usability as much as model quality. Through a structured analysis of existing benchmark families across speech, chat/RAG, and vision systems, we ident…

• Information Access of the Oppressed: Freirean Design for Emancipatory Information Access

  Bhaskar Mitra, Nicola Neophytou, Sireesh Gururaja · 25 May 2026

  Online information access (IA) platforms are targets of authoritarian capture. We explore the question of how to safeguard our platforms and ensure emancipatory outcomes through the lens of Paulo Freire's theories of emancipatory pedagogy. Freire's theories provide a radically different lens for exp…

• Unpacking "Personal" Health Informatics for Proactive Collective Care

  Shyama Sastha Krishnamoorthy Srinivasan, Mohan Kumar, Pushpendra Singh · 21 May 2026

  Care is primarily a collective phenomenon, with a practice that involves sharing health and wellbeing information within a trusted "care circle" of family members and companions for sensemaking, interpretation, decision-making, and follow-through. However, current digital health tools and informatio…

• Why Low-Resource NLP Needs More Than Cross-Lingual Transfer: Lessons Learned from Luxembourgish

  Fred Philippy, Siwen Guo, Jacques Klein, Tegawendé F. Bissyandé · 12 May 2026

  Cross-lingual transfer has become a central paradigm for extending natural language processing (NLP) technologies to low-resource languages. By leveraging supervision from high-resource languages, multilingual language models can achieve strong task performance with little or no labeled target-langu…