{"total":30,"rows":[{"id":"2103.11811","title":"MasakhaNER: Named Entity Recognition for African Languages","created":"2021-03-22","cited_by_count":155,"area":null},{"id":"2309.07445","title":"SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects","created":"2023-09-14","cited_by_count":152,"area":null},{"id":"2204.06487","title":"Adapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-Tuning","created":"2022-04-13","cited_by_count":149,"area":null},{"id":"2205.02022","title":"A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation","created":"2022-05-04","cited_by_count":98,"area":null},{"id":"2211.03263","title":"AfroLM: A Self-Active Learning-based Multilingual Pretrained Language Model for 23 African Languages","created":"2022-11-07","cited_by_count":46,"area":null},{"id":"2212.10785","title":"SERENGETI: Massively Multilingual Language Models for Africa","created":"2022-12-21","cited_by_count":40,"area":null},{"id":"2305.11938","title":"XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages","created":"2023-05-19","cited_by_count":34,"area":null},{"id":"2304.09972","title":"MasakhaNEWS: News Topic Classification for African languages","created":"2023-04-19","cited_by_count":31,"area":null},{"id":"2310.14029","title":"LLM-Prop: Predicting Physical And Electronic Properties Of Crystalline Solids From Their Text Descriptions","created":"2023-10-21","cited_by_count":29,"area":null},{"id":"2203.08459","title":"KinyaBERT: a Morphology-aware Kinyarwanda Language Model","created":"2022-03-16","cited_by_count":27,"area":null},{"id":"2305.13989","title":"MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African Languages","created":"2023-05-23","cited_by_count":23,"area":null},{"id":"2402.08638","title":"SemRel2024: A Collection of Semantic Textual Relatedness Datasets for 13 Languages","created":"2024-02-13","cited_by_count":16,"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":"2410.20817","title":"The Zeno's Paradox of `Low-Resource' Languages","created":"2024-10-28","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":"2201.05609","title":"Multilingual Open Text Release 1: Public Domain News in 44 Languages","created":"2022-01-14","cited_by_count":10,"area":null},{"id":"2502.19582","title":"Where Are We? Evaluating LLM Performance on African Languages","created":"2025-02-26","cited_by_count":10,"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":"2212.09674","title":"LR-Sum: Summarization for Less-Resourced Languages","created":"2022-12-19","cited_by_count":5,"area":null},{"id":"2409.10965","title":"Cross-lingual transfer of multilingual models on low resource African Languages","created":"2024-09-17","cited_by_count":5,"area":null},{"id":"2308.09768","title":"NaijaRC: A Multi-choice Reading Comprehension Dataset for Nigerian Languages","created":"2023-08-18","cited_by_count":4,"area":null},{"id":"2304.12155","title":"The African Stopwords project: curating stopwords for African languages","created":"2023-03-21","cited_by_count":3,"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":"2412.09922","title":"Low-Resource Fast Text Classification Based on Intra-Class and Inter-Class Distance Calculation","created":"2024-12-13","cited_by_count":2,"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":"2403.06018","title":"Few-Shot Cross-Lingual Transfer for Prompting Large Language Models in Low-Resource Languages","created":"2024-03-09","cited_by_count":1,"area":null},{"id":"2507.15142","title":"A Case Against Implicit Standards: Homophone Normalization in Machine Translation for Languages that use the Ge'ez Script","created":"2025-07-20","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":"2506.09847","title":"Dataset of News Articles with Provenance Metadata for Media Relevance Assessment","created":"2025-06-11","cited_by_count":0,"area":null},{"id":"2609.32234","title":"KinyaMed: Seeds, Not Rows -- What a Corpus Requirement Written in the Wrong Unit Fails to Constrain","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}