Large language models (LLMs) have emerged as strong contenders in machine translation. Yet, they often fall behind specialized neural machine translation systems in addressing discourse phenomena, such as pronoun resolution and lexical cohesion at the document level. In the seminar, … Read More
Welcome to Priberam Labs
We think, execute and enjoy. Discover all the power of Priberam Labs.
What are the Priberam Labs
When developing our products, we often find challenges which are unanswered by current scientific knowledge. This is where the Priberam Labs come into play! We look beyond the current state of technology and try to build the foundations for the future.
Our approach
Machine Learning and Natural Language Processing
Our research team conducts applied and exploratory research in the areas of machine learning and natural language processing. Every day, we deal with challenging and stimulating problems, and use our creativity to design systems that learn from the data.
Our Goals Are
To push the boundaries of scientific knowledge
Transfer all our knowledge and investigation to our products.
Discover the Latest Seminars
Speech as a Biomarker for Disease Detection
Today’s overburdened health systems face numerous challenges, exacerbated by an aging population. Speech emerges as a ubiquitous biomarker with strong potential for the development of low-cost, remote testing tools for several diseases. In fact, speech encodes information about a plethora … Read More
Enhancing Uncertainty Estimation in Neural Networks
Neural networks are often overconfident about their predictions, which undermines their reliability and trustworthiness. In this presentation, I will present our work entitled Error-Driven Uncertainty Aware Training (EUAT), which aims to enhance the ability of neural classifiers to estimate their … Read More