Dissertation in the field of Language Technology, Teemu Ruokolainen

The title of thesis is Contributions to Morphology Learning using Conditional Random Fields.

In the scope of this thesis, we approach the morphological tagging and segmentation problems using statistical, data-driven machine learning methodology. Using this approach, the processing systems are learned (estimated) based on training data prepared manually by a human expert. In particular, we focus on the highly influential conditional random field (CRF) model proposed for sequence tagging and segmentation in the early 2000s.

Opponent: Assistant Professor Chris Dyer, Carnegie Mellon University, USA

Supervisor: Professor Mikko Kurimo, Aalto University School of Electrical Engineering, Department of Signal Processing and Acoustics