{"total":15,"rows":[{"id":"2204.08582","title":"MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages","created":"2022-04-18","cited_by_count":146,"area":null},{"id":"2205.03983","title":"Building Machine Translation Systems for the Next Thousand Languages","created":"2022-05-09","cited_by_count":69,"area":null},{"id":"2203.11764","title":"Listening to Affected Communities to Define Extreme Speech: Dataset and Experiments","created":"2022-03-22","cited_by_count":22,"area":null},{"id":"2505.21315","title":"Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead","created":"2025-05-27","cited_by_count":16,"area":null},{"id":"2303.03750","title":"Preparing the Vuk'uzenzele and ZA-gov-multilingual South African multilingual corpora","created":"2023-03-07","cited_by_count":12,"area":null},{"id":"2502.12301","title":"SMOL: Professionally translated parallel data for 115 under-represented languages","created":"2025-02-17","cited_by_count":12,"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":"2409.05247","title":"Socially Responsible Data for Large Multilingual Language Models","created":"2024-09-08","cited_by_count":7,"area":null},{"id":"2310.09141","title":"PuoBERTa: Training and evaluation of a curated language model for Setswana","created":"2023-10-13","cited_by_count":6,"area":null},{"id":"2111.06230","title":"Training Cross-Lingual embeddings for Setswana and Sepedi","created":"2021-11-11","cited_by_count":5,"area":null},{"id":"2212.09674","title":"LR-Sum: Summarization for Less-Resourced Languages","created":"2022-12-19","cited_by_count":5,"area":null},{"id":"2306.07426","title":"Izindaba-Tindzaba: Machine learning news categorisation for Long and Short Text for isiZulu and Siswati","created":"2023-06-12","cited_by_count":2,"area":null},{"id":"2408.02239","title":"Pula: Training Large Language Models for Setswana","created":"2024-08-05","cited_by_count":2,"area":null},{"id":"2102.02841","title":"Building Representative Corpora from Illiterate Communities: A Review of Challenges and Mitigation Strategies for Developing Countries","created":"2021-02-04","cited_by_count":0,"area":null},{"id":"2603.03316","title":"The Influence of Iconicity in Transfer Learning for Sign Language Recognition","created":"2026-02-09","cited_by_count":0,"area":null}],"next_cursor":null}