Cookies Policy
The website need some cookies and similar means to function. If you permit us, we will use those means to collect data on your visits for aggregated statistics to improve our service. Find out More
Accept Reject
  • Menu
Article

INESC TEC participates in an initiative for global digital inclusion

INESC TEC, through the Laboratory of Artificial Intelligence and Decision Support (LIAAD), contributes to a project focusing on identifying and classifying people’s opinions and feelings about products and services, included in texts written in different Nigerian languages.  

18th June 2021

This project is one of the initiatives selected in the Language 2020 Awards, an action promoted by Lacuna Fund, the first collaborative initiative in the world dedicated to provide the resources that data scientists, researchers and social entrepreneurs need to produce labelled datasets, in order to address the main issues within their communities.

The main goal of the project is to promote the global digital inclusion, by producing the first high-quality open datasets, with manual annotations, gathered from content included in digital platforms, and written in the three main Nigerian languages: Hausa, Igbo and Yoruba. These datasets are important for natural language processing tasks such as sentiment and emotion analysis, as well as the detection of hate speech and fake news.

“Languages spoken in Africa have few language resources, and those that do exist are insufficient, e.g., datasets for important Artificial Intelligence (AI) tasks. This project will play a key role in the development of information for African languages, encouraging the growth and dissemination of AI research in these locations, benefiting from these datasets”, said Shamsuddeen Muhammad, researcher at INESC TEC’s LIAAD.

The project is part of the PhD work of Shamsuddeen Muhammad, a PhD candidate at the University of Porto, under the supervision of Pavel Brazdil, researcher at LIAAD, and Alípio Jorge, coordinator of LIAAD.

The INESC TEC researchers mentioned in this news piece are associated with UP-FCUP and UP-FEP.