Reader (= Associate Professor)
School of Informatics
University of Edinburgh
Faculty Fellow, The Alan Turing Institute
Office: IF 3.26
Voice (W): +44 (0) 131 651 5634
Advice for PhD Students
at Google Scholar|
Software I Use
My research concerns a broad range of applications of probabilistic methods for machine learning, including software engineering, natural language processing, computer security, queueing theory, and sustainable energy. Although these applications are disparate, they are connected by an underlying statistical methodology in probabilistic modelling and techniques for approximate inference in graphical models.
My research strategy is based on the idea that sufficiently difficult applications motive the development of new methodology. I aim to develop new machine learning methods based on this interplay of theory and practice.
My position is funded through the Scottish Informatics and Computer Science Alliance.
My full list of publications is available. Or you might be interested in these recent highlights:
A Convolutional Attention Network for Extreme Summarization of Source Code. Miltiadis Allamanis, Hao Peng and Charles Sutton. In International Conference in Machine Learning (ICML). 2016.
Clustering with a Reject Option: Interactive Clustering as Bayesian Prior Elicitation. Akash Srivastava, James Zou, Ryan P. Adams and Charles Sutton. In Workshop on Human Interpretability in Machine Learning Workshop on Human Interpretability in Machine Learning (co-located with ICML). 2016.
Parameter-Free Probabilistic API Mining across GitHub. Jaroslav Fowkes and Charles Sutton. In Foundations of Software Engineering (FSE). 2016.
A Subsequence Interleaving Model for Sequential Pattern Mining. Jaroslav Fowkes and Charles Sutton. In ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2016.
Latent Bayesian melding for integrating individual and population models. Mingjun Zhong, Nigel Goddard and Charles Sutton. In Advances in Neural Information Processing Systems (NIPS). 2015.
Suggesting Accurate Method and Class Names. Miltiadis Allamanis, Earl T. Barr, Christian Bird and Charles Sutton. In Foundations of Software Engineering (FSE). 2015. (Neural network model that can suggest a name for a method or class, given the method’s body and signature.)
Mining idioms from source code. Miltos Allamanis and Charles Sutton. In Symposium on the Foundations of Software Engineering (FSE). 2014.
Learning Natural Coding Conventions. Miltiadis Allamanis, Earl T Barr, Christian Bird and Charles Sutton. In Symposium on the Foundations of Software Engineering (FSE). 2014.
(Winner, ACM SIGSOFT Distinguished Paper Award.)
An Introduction to Conditional Random Fields. Charles Sutton and Andrew McCallum. Foundations and Trends in Machine Learning 4 (4). 2012.
Some recent research projects include: Naturalize, a system for suggesting clear variable, parameter, and method names for programmers. Both an Eclipse plugin and continuous embeddings are available.
Finally, I have a collection of brief, tutorial-style research notes.
Here are some software, Web apps, and iDevice apps that I enjoy using.
Also, I have a list of random software tips I have collected.