Projects
Mark My Words! On the Automated Prediction of Lexical Difficulty for Foreign Language Readers KU Leuven
The goal of this doctoral research is to automatically predict difficult words in a text for non-native speakers. This prediction is crucial because good text comprehension is strongly determined by vocabulary. If a text contains too high a percentage of unknown words, the reader is likely to struggle to understand it. In order to provide good support to the non-native reader, we must first be able to predict the number of difficult words. ...
CELL: ContExtual machine Learning of Language translations KU Leuven
Recasting Transformer-based Language Models as a Tool for Analysis in both Linguistics and Other Fields with Text-driven Methodologies KU Leuven
Recent machine learning methods based on neural transformer architectures have greatly improved the state of the art for a wide range of natural language processing applications, such as machine translation and general natural language understanding. There is evidence that the self-supervised language modeling objective on which such neural methods are trained results in models that implicitly encode various kinds of linguistic knowledge, ...
Generative pretraining in vision and language KU Leuven
Speech Processing Techniques for Automatic Detection of Disorders in the Human Brain KU Leuven
Natural Language Processing (NLP) is the branch of artificial intelligence that allows computers to interpret and manipulate language. In this project, we apply NLP to spontaneous speech obtained in cognitively normal elderly persons and in patients who are in the early stages of Alzheimer's disease. We investigate to what extent NLP features of speech are related to individual brain properties: regional volume, functional connectivity and ...
Towards a mechanistic understanding of the emergence, evolution, acquisition and processing of human-like languages in populations of autonomous agents Vrije Universiteit Brussel
Challenging Language Models with Multilingual Terminology KU Leuven
A Comparison of Active and Interactive Listening in Secondary School Foreign Language Classrooms in Belgium and Turkey KU Leuven
A Comparison of Active and Interactive Listening in Secondary School Foreign Language Classrooms in Belgium and Turkey
While central to language learning, listening comprehension is the least understood and least researched skill (Vandergrift, 2007). There are many reasons for this, among which is the fact that listening is the most internalized (making it difficult to observe) and teacher-centered skill (Field, 2009); in addition, as ...