# David Ifeoluwa Adelani ## Featured Co-authors - [Graham Neubig](/content/profile/graham-neubig/index.html) - 243 publications - [Junichi Yamagishi](/content/profile/junichi-yamagishi/index.html) - 127 publications - [Sebastian Riedel](/content/profile/sebastian-riedel/index.html) - 105 publications - [Dragomir Radev](/content/profile/dragomir-radev/index.html) - 71 publications - [Dietrich Klakow](/content/profile/dietrich-klakow/index.html) - 69 publications - [Sebastian Ruder](/content/profile/sebastian-ruder/index.html) - 68 publications - [Genta Indra Winata](/content/profile/genta-indra-winata/index.html) - 58 publications - [Pontus Stenetorp](/content/profile/pontus-stenetorp/index.html) - 45 publications - [Isao Echizen](/content/profile/isao-echizen/index.html) - 45 publications - [Mikel Artetxe](/content/profile/mikel-artetxe/index.html) - 41 publications - [Saif M. Mohammad](/content/profile/saif-m-mohammad/index.html) - 39 publications ## Research Publications ### [SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects](/content/publication/sib-200-a-simple-inclusive-and-big-evaluation-dataset-for-topic-classification-in-200-languages-and-dialects/index.html) Despite the progress we have recorded in the last few years in multilingual... ### [YORC: Yoruba Reading Comprehension dataset](/content/publication/yorc-yoruba-reading-comprehension-dataset/index.html) In this paper, we create YORC: a new multi-choice Yoruba Reading Comprehension dataset... ### [ÌròyìnSpeech: A multi-purpose Yorùbá Speech Corpus](/content/publication/iroyinspeech-a-multi-purpose-yoruba-speech-corpus/index.html) We introduce the ÌròyìnSpeech corpus – a new dataset influenced by a des... ### [Improving Language Plasticity via Pretraining with Active Forgetting](/content/publication/improving-language-plasticity-via-pretraining-with-active-forgetting/index.html) Pretrained language models (PLMs) are today the primary model for natural... ### [NollySenti: Leveraging Transfer Learning and Machine Translation for Nigerian Movie Sentiment Classification](/content/publication/nollysenti-leveraging-transfer-learning-and-machine-translation-for-nigerian-movie-sentiment-classification/index.html) Africa has over 2000 indigenous languages but they are under-represented... ### [MasakhaNEWS: News Topic Classification for African languages](/content/publication/masakhanews-news-topic-classification-for-african-languages/index.html) African languages are severely under-represented in NLP research due to ... ### [SemEval-2023 Task 12: Sentiment Analysis for African Languages (AfriSenti-SemEval)](/content/publication/semeval-2023-task-12-sentiment-analysis-for-african-languages-afrisenti-semeval/index.html) We present the first Africentric SemEval Shared task, Sentiment Analysis... ### [AfriSenti: A Twitter Sentiment Analysis Benchmark for African Languages](/content/publication/afrisenti-a-twitter-sentiment-analysis-benchmark-for-african-languages/index.html) Africa is home to over 2000 languages from over six language families ... ### [BLOOM+1: Adding Language Support to BLOOM for Zero-Shot Prompting](/content/publication/bloom-1-adding-language-support-to-bloom-for-zero-shot-prompting/index.html) The BLOOM model is a large open-source multilingual language model capable... ### [BibleTTS: a large, high-fidelity, multilingual, and uniquely African speech corpus](/content/publication/bibletts-a-large-high-fidelity-multilingual-and-uniquely-african-speech-corpus/index.html) BibleTTS is a large, high-quality, open speech dataset for ten languages... ### [TOKEN is a MASK: Few-shot Named Entity Recognition with Pre-trained Language Models](/content/publication/token-is-a-mask-few-shot-named-entity-recognition-with-pre-trained-language-models/index.html) Transferring knowledge from one domain to another is of practical import... ### [Task-Adaptive Pre-Training for Boosting Learning With Noisy Labels: A Study on Text Classification for African Languages](/content/publication/task-adaptive-pre-training-for-boosting-learning-with-noisy-labels-a-study-on-text-classification-for-african-languages/index.html) For high-resource languages like English, text classification is a well... ### [MCSE: Multimodal Contrastive Learning of Sentence Embeddings](/content/publication/mcse-multimodal-contrastive-learning-of-sentence-embeddings/index.html) Learning semantically meaningful sentence embeddings is an open problem ... ### [yosm: A new yoruba sentiment corpus for movie reviews](/content/publication/yosm-a-new-yoruba-sentiment-corpus-for-movie-reviews/index.html) A movie that is thoroughly enjoyed and recommended by an individual might... ### [Is BERT Robust to Label Noise? A Study on Learning with Noisy Labels in Text Classification](/content/publication/is-bert-robust-to-label-noise-a-study-on-learning-with-noisy-labels-in-text-classification/index.html) Incorrect labels in training data occur when human annotators make mistakes... ### [Multilingual Language Model Adaptive Fine-Tuning: A Study on African Languages](/content/publication/multilingual-language-model-adaptive-fine-tuning-a-study-on-african-languages/index.html) Multilingual pre-trained language models (PLMs) have demonstrated impressive... ### [Pre-Trained Multilingual Sequence-to-Sequence Models: A Hope for Low-Resource Language Translation?](/content/publication/pre-trained-multilingual-sequence-to-sequence-models-a-hope-for-low-resource-language-translation/index.html) What can pre-trained multilingual sequence-to-sequence models like mBART... ### [NaijaSenti: A Nigerian Twitter Sentiment Corpus for Multilingual Sentiment Analysis](/content/publication/naijasenti-a-nigerian-twitter-sentiment-corpus-for-multilingual-sentiment-analysis/index.html) Sentiment analysis is one of the most widely studied applications in NLP... ### [Preventing Author Profiling through Zero-Shot Multilingual Back-Translation](/content/publication/preventing-author-profiling-through-zero-shot-multilingual-back-translation/index.html) Documents as short as a single sentence may inadvertently reveal sensitive... ### [MasakhaNER: Named Entity Recognition for African Languages](/content/publication/masakhaner-named-entity-recognition-for-african-languages/index.html) We take a step towards addressing the under-representation of the African... ### [Privacy Guarantees for De-identifying Text Transformations](/content/publication/privacy-guarantees-for-de-identifying-text-transformations/index.html) Machine Learning approaches to Natural Language Processing tasks benefit... ### [Robust Differentially Private Training of Deep Neural Networks](/content/publication/robust-differentially-private-training-of-deep-neural-networks/index.html) Differentially private stochastic gradient descent (DPSGD) is a variation... ### [Distant Supervision and Noisy Label Learning for Low Resource Named Entity Recognition: A Study on Hausa and Yorùbá](/content/publication/distant-supervision-and-noisy-label-learning-for-low-resource-named-entity-recognition-a-study-on-hausa-and-yoruba/index.html) The lack of labeled training data has limited the development of natural... ### [Unsupervised Pidgin Text Generation By Pivoting English Data and Self-Training](/content/publication/unsupervised-pidgin-text-generation-by-pivoting-english-data-and-self-training/index.html) West African Pidgin English is a language that is significantly spoken... ### [Generating Sentiment-Preserving Fake Online Reviews Using Neural Language Models and Their Human- and Machine-based Detection](/content/publication/generating-sentiment-preserving-fake-online-reviews-using-neural-language-models-and-their-human-and-machine-based-detection/index.html) Advanced neural language models (NLMs) are widely used in sequence generation...