Miltiadis Allamanis

Publications
Influence

Learning to Represent Programs with Graphs

Miltiadis Allamanis, Marc Brockschmidt, M. Khademi
Computer Science, Mathematics
ICLR
1 November 2017

We propose to use graphs to represent both the syntactic and semantic structure of code and use graph-based deep learning methods to learn to reason over program structures. Expand

A Convolutional Attention Network for Extreme Summarization of Source Code

Miltiadis Allamanis, Hao Peng, Charles Sutton
Computer Science, Mathematics
ICML
9 February 2016

We introduce an attentional neural network that employs convolution on the input tokens to detect local time-invariant and long-range topical attention features in a context-dependent way. Expand

Suggesting accurate method and class names

Miltiadis Allamanis, E. Barr, C. Bird, Charles Sutton
Computer Science
ESEC/SIGSOFT FSE
30 August 2015

We introduce a neural probabilistic language model for source code that is specifically designed for the method naming problem. Expand

Mining source code repositories at massive scale using language modeling

Miltiadis Allamanis, Charles Sutton
Computer Science
10th Working Conference on Mining Software…
18 May 2013

The tens of thousands of high-quality open source software projects on the Internet raise the exciting possibility of studying software development by finding patterns across truly large source code repositories. Expand

Learning natural coding conventions

Miltiadis Allamanis, E. Barr, Charles Sutton
Computer Science
FSE
17 February 2014

We present NATURALIZE, a framework that learns the style of a codebase, and suggests revisions to improve stylistic consistency. Expand

Constrained Graph Variational Autoencoders for Molecule Design

Qi Liu, Miltiadis Allamanis, Marc Brockschmidt, Alexander L. Gaunt
Computer Science, Mathematics
NeurIPS
23 May 2018

We propose a novel probabilistic model for graph generation that builds gated graph neural networks into the encoder and decoder of a variational autoencoder. Expand

A Survey of Machine Learning for Big Code and Naturalness

Miltiadis Allamanis, E. Barr, Premkumar T. Devanbu, Charles Sutton
Computer Science
ACM Comput. Surv.
18 September 2017

We present a taxonomy based on the underlying design principles of each model and use it to navigate the literature. Expand

Deep learning type inference

Vincent J. Hellendoorn, C. Bird, E. Barr, Miltiadis Allamanis
Computer Science
ESEC/SIGSOFT FSE
26 October 2018

We propose DeepTyper, a deep learning model that understands which types naturally occur in certain contexts and relations and can provide type suggestions, which can often be verified by the type checker, even if it could not infer the type initially. Expand

Mining idioms from source code

Miltiadis Allamanis, Charles Sutton
Computer Science
FSE
1 April 2014

We present Haggis, a system for automatically mining code idioms from a corpus of previously written, idiomatic software projects. Expand

Bimodal Modelling of Source Code and Natural Language

Miltiadis Allamanis, Daniel Tarlow, A. Gordon, Y. Wei
Computer Science
ICML
6 July 2015

We consider the problem of building probabilistic models that jointly model short natural language utterances and source code snippets. Expand

Recommended Authors