Search Results - "Chimoto, Everlyn Asiko"

GrammaMT: Improving Machine Translation with Grammar-Informed In-Context Learning by Ramos, Rita, Chimoto, Everlyn Asiko, ter Hoeve, Maartje, Schluter, Natalie

“…We introduce GrammaMT, a grammatically-aware prompting approach for machine translation that uses Interlinear Glossed Text (IGT), a common form of linguistic…”
Get full text

Very Low Resource Sentence Alignment: Luhya and Swahili by Chimoto, Everlyn Asiko, Bassett, Bruce A

“…Language-agnostic sentence embeddings generated by pre-trained models such as LASER and LaBSE are attractive options for mining large datasets to produce…”
Get full text

COMET-QE and Active Learning for Low-Resource Machine Translation by Chimoto, Everlyn Asiko, Bassett, Bruce A

“…Active learning aims to deliver maximum benefit when resources are scarce. We use COMET-QE, a reference-free evaluation metric, to select sentences for…”
Get full text

Critical Learning Periods: Leveraging Early Training Dynamics for Efficient Data Pruning by Chimoto, Everlyn Asiko, Gala, Jay, Ahia, Orevaoghene, Kreutzer, Julia, Bassett, Bruce A, Hooker, Sara

“…Neural Machine Translation models are extremely data and compute-hungry. However, not all data points contribute equally to model training and generalization…”
Get full text

Towards hate speech detection in low-resource languages: Comparing ASR to acoustic word embeddings on Wolof and Swahili by Jacobs, Christiaan, Rakotonirina, Nathanaël Carraz, Chimoto, Everlyn Asiko, Bassett, Bruce A, Kamper, Herman

“…We consider hate speech detection through keyword spotting on radio broadcasts. One approach is to build an automatic speech recognition (ASR) system for the…”
Get full text

State of NLP in Kenya: A Survey by Amol, Cynthia Jayne, Chimoto, Everlyn Asiko, Gesicho, Rose Delilah, Gitau, Antony M, Etori, Naome A, Kinyanjui, Caringtone, Ndung'u, Steven, Moruye, Lawrence, Ooko, Samson Otieno, Kitonga, Kavengi, Muhia, Brian, Gitau, Catherine, Ndolo, Antony, Wanzare, Lilian D. A, Kahira, Albert Njoroge, Tombe, Ronald

“…Kenya, known for its linguistic diversity, faces unique challenges and promising opportunities in advancing Natural Language Processing (NLP) technologies,…”
Get full text