Public defence of Adam Ek's doctoral thesis

• Event: PhD Defence
• Presented by: Adam Ek
• Date: 08 September 2023

Cordially welcome to the public defence of Adam Ek’s doctoral thesis on Friday 8 September, at 10:15 in room J222, Faculty of Humanities. The title is “Studies in Language Structure using Deep Learning”.

Doctoral candidate: Adam Ek, University of Gothenburg

Supervisor: Jean-Phillipe Bernardy, University of Gothenburg Assistant supervisor: Stergios Chatzikiriakidis, University of Gothenburg

Opponent: Assistant Professor Lasha Abzianidze, Utrecht University

Committee: Professor, Stephen Clark, Head of ArtificiaI Intelligence, Quantinuum Docent Sara Stymne, Uppsala universitet Associate Professor Johannes Bjerva, Aalborg universitet

Chair: Associate Professor Asad Basheer Sayeed, Göteborgs universitet

Date: 2023-09-08

Title: Studies in Language Structure using Deep Learning

Abstract: This thesis deals with the discovery, prediction, and utilization of structural patterns in language using deep learning techniques. The thesis is divided into two sections. The first section gives an introduction to the tools used and the structures in language we are interested in. The second part presents six papers addressing the research questions. The first three papers deals with discovering and predicting patterns. In the first paper, we explore methods of composing word embeddings to predict morphological features. The second paper explores the possibility of using vector norms to approximate syntactic complexity. The third paper deals with predicting the depths of nested structures. The remaining three papers deal with using structures in language to make semantic predictions. The fourth paper explores using dependency trees to predict semantic predicate-argument structures using a rule-based system. The fifth paper explores modeling linguistic acceptability using syntactic and semantic labels. The sixth paper deals with exploring how punctuation affects natural language inference.

Full text: here