معرفی
Wilker Ferreira Aziz is an Assistant Professor at the Institute for Logic, Language and Computation (ILLC) within the Faculty of Science at the University of Amsterdam, where he leads the Probabilistic Language Learning group. His primary affiliation is with the Natural Language Processing & Digital Humanities research unit.
His research focuses on the intersection of machine learning, natural language processing, and probabilistic modeling. Key areas of interest include language modeling, machine translation, syntactic parsing, text classification, and question answering. He develops techniques for probabilistic inference, gradient estimation, and uncertainty quantification in neural language models.
Dr. Aziz's recent publications demonstrate a strong focus on uncertainty in natural language generation, with multiple papers at top-tier conferences like EACL, EMNLP, and ICLR. His work examines how language models represent uncertainty compared to humans, calibration issues when humans disagree on labels, and methods for more robust decision-making in text generation.
- Best Paper Award at Coling 2020
He actively supervises both PhD and MSc students, with several ongoing PhD projects focusing on uncertainty in language models and neural text generation. Dr. Aziz serves on program committees for major ML and NLP conferences including ACL, EMNLP, NeurIPS, and ICLR, and has acted as area chair for several of these venues. His research has been supported through positions at the Mercury Machine Learning Lab, a collaboration between Booking.com, TU Delft, and the University of Amsterdam.
