Mark Granroth-Wilding

Current Research

My research interests lie in natural language processing (NLP), computational creativity and music processing/cognition. More

I am a postdoctoral research associate in the Discovery Group at the University of Helsinki, working with Hannu Toivonen. I work on the following projects:

  • Digital Language Typology
    Automatic discovery of language family relationships from raw text/speech. We focus in particular on low-resourced Uralic languages.
  • NewsEye
    Building a digital investigator for historical newspapers. Topic modelling for analysis of multilingual, noisy output from automated text recognition.
  • Embeddia
    Addressing the challenges of multilinguality in the EU using cross-lingual embeddings to allow existing monolingual resources to be used across languages. Multilingual techniques for news analysis and media production.

Teaching

In May 2019, I will be teaching a new masters-level course on Natural Language Processing.
More details...

Jan–Feb 2017, I ran a study group for students and researchers on Natural Language Generation for News Automation. More details...

History

From 2013 to 2016, I worked on the What-If Machine (WHIM) EU FP7 project with Stephen Clark. It concerned building a computational model of creativity, constructing a system that automatically produces ideas that may serve as the basis for cultural artefacts. More...

I completed my PhD at the University of Edinburgh with Mark Steedman in 2013. The project concerned the application of NLP techniques to music processing. We developed a grammar to model the structure of tonal harmony and used statistical parsing for automatic harmonic analysis. More...

I did a masters in Informatics at Edinburgh and an undergraduate degree in Computer Science at Cambridge University.

In 2008-9, I worked for Mercurytide.