Computational construction grammar is a branch of linguistics that aims to operationalize insights and analyses from construction grammar into concrete language processing models. These models can then be used in language technology applications, such as systems for human-computer interaction, question answering, robot instruction and intelligent tutoring.

This PHD project will investigate how construction grammars can be automatically learned by a computational entity (e.g. an autonomous agent), allowing it to communicate in its native environment. You will use a variety of machine learning techniques, ranging from deep neural networks to inductive logic programming. You will set up multi-agent simulations in which a population of autonomous agents makes use of these techniques to establish an effective and efficient communication system.

The PhD project will be partially embedded in the interdisciplinary research project COSMO (COgnitive Support in Manufacturing Operations) in the imec.ICON programme, in which the PHD project will apply and evaluate the research in real-world settings.

The PHD project is also embedded in imec’s research programme on Smart Education, in which interaction is required with researchers from ITEC, University of Ghent, VUB and imec.