George Spithourakis

Machine Learner, PhD candidate in Computer Science

About

Research

I am a PhD candidate in Computer Science at University College London (UCL), supervised by Sebastian Riedel. My research interests lie in the intersection of Machine Learning and Natural Language Processing. I am particularly interested in grounded distributional semantics, neural models, structured prediction and optimisation. My research is supported by the Farr Institute of Health Informatics Research.

Education

I hold an MSc in Computational Statistics and Machine Learning from UCL and a diploma in Electrical and Computer Engineering (equivalent to MSc Telecommunications Engineering) from the National Technical University of Athens (NTUA).

Experience

Since 2013, I have been working as a Teaching Assistant at the Department of Computer Science at UCL. In the summer of 2016 I worked as an Applied Scientist Intern at Amazon Cambridge. In the summer of 2015 I interned at Microsoft Research. From 2009 to 2012, I worked as Research Assistant and Software Engineer at the Forecasting and Strategy Unit at NTUA.

Publications

  • G. Spithourakis, I. Augenstein, S. Riedel. Numerically Grounded Language Models for Semantic Error Correction. EMNLP, 2016, arxiv
  • G. Spithourakis, S. E. Petersen, S. Riedel. Clinical Text Prediction with Numerically Grounded Conditional Language Models. EMNLP, 2016, arxiv
  • J. Li, M. Galley, C. Brockett, G. Spithourakis, J. Gao, B. Dolan. A Persona-Based Neural Conversation Model. ACL, 2016, arxiv
  • G. Spithourakis, F. Petropoulos, K. Nikolopoulos and V. Assimakopoulos. Amplifying the learning effect via a forecasting and foresight support system. International Journal of Forecasting, 31(1):20-32, 2015.
  • G. Spithourakis, S. Petersen, and S. Riedel. Harnessing the predictive power of clinical narrative to resolve inconsistencies and omissions in EHRs. Short paper and poster presentation in 2nd Workshop on Machine Learning for Clinical Data Analysis, Healthcare and Genomics, NIPS 2014.
  • G. Spithourakis, F. Petropoulos, K. Nikolopoulos and V. Assimakopoulos. A systemic view of the ADIDA framework. IMA Journal of Management Mathematics, 25(2): 125-137, 2014.
  • F. Petropoulos, K. Nikolopoulos, G. Spithourakis and V. Assimakopoulos. Empirical heuristics for improving intermittent demand forecasting. Industrial Management & Data Systems, 113(5):683-696, 2013.
  • G. Spithourakis, F. Petropoulos, M.Z. Babai, K. Nikolopoulos and V. Assimakopoulos. Improving the performance of popular supply chain forecasting techniques: an empirical investigation. Supply Chain Forum: an International Journal, 12(4):16-25, 2012.

Contact

Email Address

g.{LastName}@cs.ucl.ac.uk

Visiting Address

G.6 5th Floor
One Euston Square
40 Melton Street
London NW1 2FD
United Kingdom

Postal Address

University College London
Dept. of Computer Science (1ES)
Gower Street
London WC1E 6BT
United Kingdom


Find me on ...