Sander Canisius Research page


The focus of my research is on the development and application of machine learning techniques for natural language processing. I am particularly interested in learning approaches to structured classification problems, that is, tasks in which the input is more complex than a simple vector of feature-value pairs and/or the output is more complex than a simple class label. Specific application domains I am working on, or have worked on in the past include shallow syntactic parsing and information extraction.

Machine learning
Focusing on more fundamental machine learning issues, with an emphasis on learning/classification approaches aimed at labelling sequentially-structured data.
Information extraction
Mostly, domain-specific information extraction based on the idea of exploiting partial redundancy on multiple levels of semantic annotation.
A brief overview of my master thesis research on shallow parsing of spoken Dutch.