Improving language plasticity via pretraining with active forgetting

Y Chen, K Marchisio, R Raileanu… - Advances in …, 2023 - proceedings.neurips.cc
Pretrained language models (PLMs) are today the primary model for natural language
processing. Despite their impressive downstream performance, it can be difficult to apply …

Aya model: An instruction finetuned open-access multilingual language model

A Üstün, V Aryabumi, ZX Yong, WY Ko… - ar** and Deploying End‐to‐End Machine Learning Systems for Social Impact: A Rubric and Practical Artificial Intelligence Case Studies From African Contexts
E Bainomugisha, J Nakatumba‐Nabende - Applied AI Letters, 2024 - Wiley Online Library
Artificial intelligence (AI) and machine learning have demonstrated the potential to provide
solutions to societal challenges, for example, automated crop diagnostics for smallholder …

Afrinames: Most asr models" butcher" african names

T Olatunji, T Afonja, BFP Dossou, AL Tonja… - arxiv preprint arxiv …, 2023 - arxiv.org
Useful conversational agents must accurately capture named entities to minimize error for
downstream tasks, for example, asking a voice assistant to play a track from a certain artist …

CoLaDa: A Collaborative Label Denoising Framework for Cross-lingual Named Entity Recognition

T Ma, Q Wu, H Jiang, BF Karlsson, T Zhao… - arxiv preprint arxiv …, 2023 - arxiv.org
Cross-lingual named entity recognition (NER) aims to train an NER system that generalizes
well to a target language by leveraging labeled data in a given source language. Previous …

PuoBERTa: Training and evaluation of a curated language model for Setswana

V Marivate, M Mots' Oehli, V Wagnerinst… - … African Conference for …, 2023 - Springer
Natural language processing (NLP) has made significant progress for well-resourced
languages such as English but lagged behind for low-resource languages like Setswana …