Natural Language Processing (NLP) has improved rapidly in the past several years and has resulted in automated solutions for many practical problems. My research incorporates human expertise in various steps of the automation process: task definition, data acquisition, evaluation, interpretability, as well as hybrid human-in-the-loop approaches. I put an emphasis on the importance of improving the quantity and the quality of the data used by machine learning systems for training and testing. In this talk I will present my work on human-centric and data-centric NLP in the areas of misinformation, automatic hate speech detection, and developmental psychology.
Dr. Venelin Kovatchev is a post-doctoral research fellow, working on the Good Systems project with prof. Matt Lease since October 2021. He obtained his PhD (Cum Laude) in Cognitive Science and Language from the University of Barcelona, Spain, in July 2020. In 2020 and 2021 he was a postdoctoral research fellow at the University of Birmingham, UK. Dr. Kovatchev current research focuses on natural language processing, computational semantics, and curbing disinformation online.
Part of the Good Systems Postdoc Research Presentation Series.