work/

research interests

mining for meaning

Words have a particular meaning. While language users have no problems inferring those meanings, this is a difficult task for a computer system. I investigate whether and how a computer might be able to automatically extract meaning from large text collections.

dimensionality reduction

An important part of the research focuses on dimensionality reduction, and its application to meaning extraction. The use of large text collections brings about a large number of contexts in which a word occurs. Using a mathematical dimensionality reduction, the abundance of individual contexts can be reduced to a limited number of significant dimensions, containing latent semantics.

tensors

Another part of the research focuses on the use of tensors for natural language processing. Language can often be described as multi-way co-occurrences, and tensors provide a natural framework to capture and analyze such multi-way co-occurrences.

applications

My research has applications in various natural language processing tasks such as word sense induction and selectional preference acquisition.

Last updated: Friday 10 February 2017. Powered by Django.