I am a researcher and machine learning enthusiast, interested in natural language processing, artificial intelligence, and various related areas.
Currently, I am a member of the Research team in SwiftKey, where our goal is to focus on potential future technologies, thinking a few years ahead. We divide our time between further improving our existing machine learning solutions and developing new ideas for future products.
I am also a member of Churchill College in the University of Cambridge, where I received a PhD degree with my thesis on minimally supervised dependency-based methods for natural language processing, under the supervision of Professor Ted Briscoe. I was working in the Natural Language and Information Processing Group in the Computer Laboratory.
Before that, in 2008-2009 I did an MPhil course in the Computer Lab, called Computer Speech, Text and Internet Technology. The topic of my dissertation was Adaptive Interactive Information Extraction.
I also studied three years in Tallinn University of Technology where I got my bachelor's degree with the thesis Creating a Model for Audiovisual Speech in Estonian.
My CV: Download
My main areas of interest include:
- distributional and compositional semantics
- unsupervised and semi-supervised learning
- neural networks and deep learning
- representation learning
- text mining
- information extraction
- (bio)medical applications of NLP
Piano, guitar, ballroom/latin dancing, nature, geocaching, good movies, good books
E-mail: marek ät marekrei dot com
Looking for hyponyms in vector space In Proceedings of the Eighteenth Conference on Computational Natural Language Learning (CoNLL-14) Baltimore, Maryland, United States, 2014
Parser lexicalisation through self-learning In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2013). Atlanta, United States, 2013
Minimally supervised dependency-based methods for natural language processing PhD thesis, University of Cambridge Cambridge, United Kingdom, 2013
Unsupervised Entailment Detection between Dependency Graph Fragments In Proceedings of the 2011 Workshop on Biomedical Natural Language Processing (BioNLP-11). Portland, United States, 2011
Intelligent Information Access from Scientific Papers Current Challenges in Patent Information Retrieval, edited by Mihai Lupu, Katja Mayer, John Tait and Anthony J. Trippe. Springer, Dordrecht, 2011
Combining Manual Rules and Supervised Learning for Hedge Cue and Scope Detection The 14th Conference on Natural Language Learning (CoNLL-10). Uppsala, Sweden, 2010
Adaptive Interactive Information Extraction MPhil thesis Computer Laboratory, University of Cambridge, 2009