mlsanityData to 14 Oct 2026

MasakhaNER 2.0: Africa-centric Transfer Learning for Named Entity Recognition

arXiv 2210.12391 ↗First posted 22 Oct 2022cs.CLcited by 38

Not on the map. Why?

Abstract (arXiv)

African languages are spoken by over a billion people, but are underrepresented in NLP research and development. The challenges impeding progress include the limited availability of annotated datasets, as well as a lack of understanding of the settings where current methods are effective. In this paper, we make progress towards solutions for these challenges, focusing on the task of named entity recognition (NER). We create the largest human-annotated NER dataset for 20 African languages, and we study the behavior of state-of-the-art cross-lingual transfer methods in an Africa-centric setting, demonstrating that the choice of source language significantly affects performance. We show that choosing the best transfer language improves zero-shot F1 scores by an average of 14 points across 20 languages compared to using English. Our results highlight the need for benchmark datasets and models that cover typologically-diverse African languages.

Key facts. Cited by 38 papers in the map (data through 14 Oct 2026). Builds on 36 of its 101 references that are in the map. First posted on arXiv 22 Oct 2022.

Builds on

36 of 101 references.

References · 36

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  3. 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,254
  4. 2020XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalizationcited by 742
  5. 2019How multilingual is Multilingual BERT?cited by 645
  6. 2021Datasets: A Community Library for Natural Language Processingcited by 530
  7. 2020MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfercited by 445
  8. 2020XCOPA: A Multilingual Dataset for Causal Commonsense Reasoningcited by 333
  9. 2019Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERTcited by 301
  10. 2019Cross-Lingual Ability of Multilingual BERT: An Empirical Studycited by 182
  11. 2021XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluationcited by 168
  12. 2020Participatory Research for Low-resourced Machine Translation: A Case Study in African Languagescited by 159
24 more
  1. 2021MasakhaNER: Named Entity Recognition for African Languagescited by 155
  2. 2022Adapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-Tuningcited by 149
  3. 2019Choosing Transfer Languages for Cross-Lingual Learningcited by 144
  4. 2020Intermediate-Task Transfer Learning with Pretrained Models for Natural Language Understanding: When and Why Does It Work?cited by 127
  5. 2021KLUE: Korean Language Understanding Evaluationcited by 114
  6. 2020Rethinking embedding coupling in pre-trained language modelscited by 103
  7. 2022A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translationcited by 98
  8. 2022NaijaSenti: A Nigerian Twitter Sentiment Corpus for Multilingual Sentiment Analysiscited by 64
  9. 2020Transfer Learning and Distant Supervision for Multilingual Transformer Models: A Study on African Languagescited by 52
  10. 2021Multilingual Autoregressive Entity Linkingcited by 50
  11. 2021ExplainaBoard: An Explainable Leaderboard for NLPcited by 50
  12. 2021AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languagescited by 50
  13. 2020Predicting Performance for Natural Language Processing Taskscited by 49
  14. 2021The Effect of Domain and Diacritics in Yor`ub'a-English Neural Machine Translationcited by 38
  15. 2019Massive vs. Curated Word Embeddings for Low-Resourced Languages. The Case of Yor`ub'a and Twicited by 33
  16. 2021AfroMT: Pretraining Strategies and Reproducible Benchmarks for Translation of 8 African Languagescited by 24
  17. 2021Dataset Geography: Mapping Language Data to Language Userscited by 22
  18. 2022Multi Task Learning For Zero Shot Performance Prediction of Multilingual Modelscited by 20
  19. 2019ner and pos when nothing is capitalizedcited by 15
  20. 2022Hausa Visual Genome: A Dataset for Multi-Modal English to Hausa Machine Translationcited by 13
  21. 2019Introducing RONEC -- the Romanian Named Entity Corpuscited by 12
  22. 2019A Finnish News Corpus for Named Entity Recognitioncited by 11
  23. 2022ANEC: An Amharic Named Entity Corpus and Transformer Based Recognizercited by 5
  24. 2019Named Entity Recognition for Nepali Languagecited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 20; 2024: 6; 2025: 5; 2026: 6.

38 papers.

Sort:

  1. 2023MEGA: Multilingual Evaluation of Generative AIcited by 293
  2. 2023SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialectscited by 152
  3. 2024A Survey on Multilingual Large Language Models: Corpora, Alignment, and Biascited by 84
  4. 2023Improving Language Plasticity via Pretraining with Active Forgettingcited by 43
  5. 2024IrokoBench: A New Benchmark for African Languages in the Age of Large Language Modelscited by 43
  6. 2023XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languagescited by 34
  7. 2022Frustratingly Easy Label Projection for Cross-lingual Transfercited by 33
  8. 2023MasakhaNEWS: News Topic Classification for African languagescited by 31
  9. 2023AfriQA: Cross-lingual Open-Retrieval Question Answering for African Languagescited by 23
  10. 2023MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African Languagescited by 23
  11. 2023Cultural Compass: Predicting Transfer Learning Success in Offensive Language Detection with Cultural Featurescited by 18
  12. 2023Translation and Fusion Improves Zero-shot Cross-lingual Information Extractioncited by 15
26 more
  1. 2023NollySenti: Leveraging Transfer Learning and Machine Translation for Nigerian Movie Sentiment Classificationcited by 14
  2. 2023HaVQA: A Dataset for Visual Question Answering and Multimodal Research in Hausa Languagecited by 12
  3. 2024MINERS: Multilingual Language Models as Semantic Retrieverscited by 11
  4. 2023NLNDE at SemEval-2023 Task 12: Adaptive Pretraining and Source Language Selection for Low-Resource Multilingual Sentiment Analysiscited by 10
  5. 2023AfriNames: Most ASR models "butcher" African Namescited by 7
  6. 2023`Ir`oy`inSpeech: A multi-purpose Yor`ub'a Speech Corpuscited by 7
  7. 2024LLMs in the Loop: Leveraging Large Language Model Annotations for Active Learning in Low-Resource Languagescited by 7
  8. 2023PuoBERTa: Training and evaluation of a curated language model for Setswanacited by 6
  9. 2023Adapting to the Low-Resource Double-Bind: Investigating Low-Compute Methods on Low-Resource African Languagescited by 3
  10. 2026GhanaNLP Parallel Corpora: Comprehensive Multilingual Resources for Low-Resource Ghanaian Languagescited by 3
  11. 2023MphayaNER: Named Entity Recognition for Tshivendacited by 2
  12. 2023CebuaNER: A New Baseline Cebuano Named Entity Recognition Modelcited by 2
  13. 2025Bridging Gaps in Natural Language Processing for Yor`ub'a: A Systematic Review of a Decade of Progress and Prospectscited by 2
  14. 2025Evaluating Modern Large Language Models on Low-Resource and Morphologically Rich Languages:A Cross-Lingual Benchmark Across Cantonese, Japanese, and Turkishcited by 2
  15. 2023CoLaDa: A Collaborative Label Denoising Framework for Cross-lingual Named Entity Recognitioncited by 1
  16. 2023FonMTL: Towards Multitask Learning for the Fon Languagecited by 1
  17. 2024MasonTigers at SemEval-2024 Task 1: An Ensemble Approach for Semantic Textual Relatednesscited by 1
  18. 2024What Happens When Small Is Made Smaller? Exploring the Impact of Compression on Small Data Pretrained Language Modelscited by 0
  19. 2025Using Machine Learning to Detect Fraudulent SMSs in Chichewacited by 0
  20. 2025Does Synthetic Data Help Named Entity Recognition for Low-Resource Languages?cited by 0
  21. 2025WolBanking77: Wolof Banking Speech Intent Classification Datasetcited by 0
  22. 2026An Ubuntu-Guided Large Language Model Framework for Cognitive Behavioral Mental Health Dialoguecited by 0
  23. 2026The Thiomi Dataset: A Large-Scale Multimodal Corpus for Low-Resource African Languagescited by 0
  24. 2026The Annotation Scarcity Paradox in Low-Resource NLP Evaluation: A Decade of Acceleration and Emerging Constraintscited by 0
  25. 2026A Survey of Text and Speech Resources for Hausa and Fongbe: Availability, Quality, and Gaps for NLP Developmentcited by 0
  26. 2026From Speech to Text Corpora: Evaluating ASR-Based Data Acquisition for Low-Resource Fongbe and Hausacited by 0