{"total":47,"rows":[{"id":"2402.07827","title":"Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model","created":"2024-02-12","cited_by_count":295,"area":null},{"id":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92,"area":null},{"id":"2212.08620","title":"POTATO: The Portable Text Annotation Tool","created":"2022-12-16","cited_by_count":64,"area":null},{"id":"2206.03216","title":"Data Governance in the Age of Large-Scale Data-Driven Language Technology","created":"2022-05-04","cited_by_count":33,"area":null},{"id":"2412.04497","title":"Opportunities and Challenges of Large Language Models for Low-Resource Languages in Humanities Research","created":"2024-11-30","cited_by_count":27,"area":null},{"id":"2109.04715","title":"AfroMT: Pretraining Strategies and Reproducible Benchmarks for Translation of 8 African Languages","created":"2021-09-10","cited_by_count":24,"area":null},{"id":"2311.08391","title":"A Material Lens on Coloniality in NLP","created":"2023-11-14","cited_by_count":21,"area":null},{"id":"2104.02516","title":"AI4D -- African Language Program","created":"2021-04-06","cited_by_count":18,"area":null},{"id":"2408.17024","title":"InkubaLM: A small language model for low-resource African languages","created":"2024-08-30","cited_by_count":18,"area":null},{"id":"2202.12288","title":"Toward More Meaningful Resources for Lower-resourced Languages","created":"2022-02-24","cited_by_count":14,"area":null},{"id":"2205.02364","title":"KenSwQuAD -- A Question Answering Dataset for Swahili Low Resource Language","created":"2022-05-04","cited_by_count":12,"area":null},{"id":"2204.04306","title":"MMTAfrica: Multilingual Machine Translation for African Languages","created":"2022-04-08","cited_by_count":11,"area":null},{"id":"2208.12081","title":"Kencorpus: A Kenyan Language Corpus of Swahili, Dholuo and Luhya for Natural Language Processing Tasks","created":"2022-08-25","cited_by_count":9,"area":null},{"id":"2104.00366","title":"Low-Resource Neural Machine Translation for Southern African Languages","created":"2021-04-01","cited_by_count":7,"area":null},{"id":"2106.12834","title":"Multilingual transfer of acoustic word embeddings improves when training on languages related to the target zero-resource language","created":"2021-06-24","cited_by_count":7,"area":null},{"id":"2306.06804","title":"Neural Machine Translation for the Indigenous Languages of the Americas: An Introduction","created":"2023-06-11","cited_by_count":7,"area":null},{"id":"2409.05247","title":"Socially Responsible Data for Large Multilingual Language Models","created":"2024-09-08","cited_by_count":7,"area":null},{"id":"2505.20564","title":"The NaijaVoices Dataset: Cultivating Large-Scale, High-Quality, Culturally-Rich Speech Data for African Languages","created":"2025-05-26","cited_by_count":7,"area":null},{"id":"2102.06991","title":"The first large scale collection of diverse Hausa language datasets","created":"2021-02-13","cited_by_count":6,"area":null},{"id":"2103.08052","title":"Crowdsourced Phrase-Based Tokenization for Low-Resourced Neural Machine Translation: The Case of Fon Language","created":"2021-03-14","cited_by_count":6,"area":null},{"id":"2310.03639","title":"Evaluating Self-Supervised Speech Representations for Indigenous American Languages","created":"2023-10-05","cited_by_count":6,"area":null},{"id":"2406.08726","title":"Standard Language Ideology in AI-Generated Language","created":"2024-06-13","cited_by_count":5,"area":null},{"id":"2104.00041","title":"Domain-specific MT for Low-resource Languages: The case of Bambara-French","created":"2021-03-31","cited_by_count":4,"area":null},{"id":"2412.04100","title":"Missing Melodies: AI Music Generation and its \"Nearly\" Complete Omission of the Global South","created":"2024-12-05","cited_by_count":3,"area":null},{"id":"2603.13793","title":"GhanaNLP Parallel Corpora: Comprehensive Multilingual Resources for Low-Resource Ghanaian Languages","created":"2026-03-14","cited_by_count":3,"area":null},{"id":"2207.10524","title":"NusaCrowd: A Call for Open and Reproducible NLP Research in Indonesian Languages","created":"2022-07-21","cited_by_count":2,"area":null},{"id":"2510.07221","title":"How much speech data is necessary for ASR in African languages? An evaluation of data scaling in Kinyarwanda and Kikuyu","created":"2025-10-08","cited_by_count":2,"area":null},{"id":"2605.06901","title":"Reflections and New Directions for Human-Centered Large Language Models","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2103.15963","title":"Contextual Text Embeddings for Twi","created":"2021-03-29","cited_by_count":1,"area":null},{"id":"2103.16190","title":"AfriKI: Machine-in-the-Loop Afrikaans Poetry Generation","created":"2021-03-30","cited_by_count":1,"area":null},{"id":"2206.04039","title":"Resolving the Human Subjects Status of Machine Learning's Crowdworkers","created":"2022-06-08","cited_by_count":1,"area":null},{"id":"2401.13398","title":"Text Categorization Can Enhance Domain-Agnostic Stopword Extraction","created":"2024-01-24","cited_by_count":1,"area":null},{"id":"2404.07673","title":"Curated Datasets and Neural Models for Machine Translation of Informal Registers between Mayan and Spanish Vernaculars","created":"2024-04-11","cited_by_count":1,"area":null},{"id":"2409.01053","title":"A Perspective on Literary Metaphor in the Context of Generative AI","created":"2024-09-02","cited_by_count":1,"area":null},{"id":"2103.09325","title":"Graph Convolutional Network for Swahili News Classification","created":"2021-03-16","cited_by_count":0,"area":null},{"id":"2108.10791","title":"Ensuring the Inclusive Use of Natural Language Processing in the Global Response to COVID-19","created":"2021-08-11","cited_by_count":0,"area":null},{"id":"2407.05210","title":"Leveraging AI for Climate Resilience in Africa: Challenges, Opportunities, and the Need for Collaboration","created":"2024-04-24","cited_by_count":0,"area":null},{"id":"2412.13924","title":"Language verY Rare for All","created":"2024-12-18","cited_by_count":0,"area":null},{"id":"2505.18905","title":"Building a Functional Machine Translation Corpus for Kpelle","created":"2025-05-24","cited_by_count":0,"area":null},{"id":"2510.05644","title":"The African Languages Lab: A Collaborative Approach to Advancing Low-Resource African NLP","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2510.07203","title":"Sunflower: A New Approach To Expanding Coverage of African Languages in Large Language Models","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2601.06875","title":"An Ubuntu-Guided Large Language Model Framework for Cognitive Behavioral Mental Health Dialogue","created":"2026-01-11","cited_by_count":0,"area":null},{"id":"2603.29244","title":"The Thiomi Dataset: A Large-Scale Multimodal Corpus for Low-Resource African Languages","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.12477","title":"Mining Large Language Models for Low-Resource Language Data: Comparing Elicitation Strategies for Hausa and Fongbe","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.22828","title":"A Survey of Text and Speech Resources for Hausa and Fongbe: Availability, Quality, and Gaps for NLP Development","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2606.00596","title":"Toward Responsible and Epistemically Grounded Multilingual LLMs for Computational Social Science and Humanities","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2607.04814","title":"Evaluating the Effect of Linguistic Relatedness on Cross-Lingual Transfer in Large Multilingual Automatic Speech Recognition","created":"2026-07-06","cited_by_count":0,"area":null}],"next_cursor":null}