Search Results for author: Miltiadis Allamanis

Found 25 papers, 13 papers with code

VICause: Simultaneous Missing Value Imputation and Causal Discovery with Groups

no code implementations15 Oct 2021 Pablo Morales-Alvarez, Angus Lamb, Simon Woodhead, Simon Peyton Jones, Miltiadis Allamanis, Cheng Zhang

In this work we propose VICause, a novel approach to simultaneously tackle missing value imputation and causal discovery efficiently with deep learning.

Causal Discovery Imputation

CoRGi: Content-Rich Graph Neural Networks with Attention

no code implementations10 Oct 2021 Jooyeon Kim, Angus Lamb, Simon Woodhead, Simon Peyton Jones, Cheng Zheng, Miltiadis Allamanis

Graph representations of a target domain often project it to a set of entities (nodes) and their relations (edges).

Imputation Value prediction

Learning to Generate Code Sketches

no code implementations18 Jun 2021 Daya Guo, Alexey Svyatkovskiy, Jian Yin, Nan Duan, Marc Brockschmidt, Miltiadis Allamanis

Towards addressing this, we introduce Grammformers, transformer-based grammar-guided models that learn (without explicit supervision) to generate sketches -- sequences of tokens with holes.

Code Completion

Self-Supervised Bug Detection and Repair

1 code implementation26 May 2021 Miltiadis Allamanis, Henry Jackson-Flux, Marc Brockschmidt

Machine learning-based program analyses have recently shown the promise of integrating formal and probabilistic reasoning towards aiding software development.

Self-Supervised Learning

GLUECode: A Benchmark for Source Code Machine Learning Models

no code implementations1 Jan 2021 Anjan Karmakar, Julian Aron Prenner, Miltiadis Allamanis, Romain Robbes

To address this, we present GLUECode, Global and Local Understanding Evaluation of Code, a benchmark of diverse tasks to evaluate machine learning models of source code.

Copy that! Editing Sequences by Copying Spans

1 code implementation8 Jun 2020 Sheena Panthaplackel, Miltiadis Allamanis, Marc Brockschmidt

Neural sequence-to-sequence models are finding increasing use in editing of documents, for example in correcting a text document or repairing source code.

Typilus: Neural Type Hints

1 code implementation6 Apr 2020 Miltiadis Allamanis, Earl T. Barr, Soline Ducousso, Zheng Gao

The network uses deep similarity learning to learn a TypeSpace -- a continuous relaxation of the discrete space of types -- and how to embed the type properties of a symbol (i. e. identifier) into it.

One-Shot Learning

Learning to Encode and Classify Test Executions

no code implementations8 Jan 2020 Foivos Tsimpourlas, Ajitha Rajan, Miltiadis Allamanis

We use the labelled traces to train a neural network (NN) model to learn to distinguish runtime patterns for passing versus failing executions for a given program.

General Classification

CodeSearchNet Challenge: Evaluating the State of Semantic Code Search

10 code implementations20 Sep 2019 Hamel Husain, Ho-Hsiang Wu, Tiferet Gazit, Miltiadis Allamanis, Marc Brockschmidt

To enable evaluation of progress on code search, we are releasing the CodeSearchNet Corpus and are presenting the CodeSearchNet Challenge, which consists of 99 natural language queries with about 4k expert relevance annotations of likely results from CodeSearchNet Corpus.

Code Search Information Retrieval

Program Synthesis and Semantic Parsing with Learned Code Idioms

1 code implementation NeurIPS 2019 Richard Shin, Miltiadis Allamanis, Marc Brockschmidt, Oleksandr Polozov

Program synthesis of general-purpose source code from natural language specifications is challenging due to the need to reason about high-level patterns in the target program and low-level implementation details at the same time.

Code Generation Program Synthesis +1

The Adverse Effects of Code Duplication in Machine Learning Models of Code

1 code implementation16 Dec 2018 Miltiadis Allamanis

The field of big code relies on mining large corpora of code to perform some learning task.

Structured Neural Summarization

2 code implementations ICLR 2019 Patrick Fernandes, Miltiadis Allamanis, Marc Brockschmidt

Summarization of long sequences into a concise statement is a core problem in natural language processing, requiring non-trivial understanding of the input.

Source Code Summarization

Tree2Tree Neural Translation Model for Learning Source Code Changes

no code implementations30 Sep 2018 Saikat Chakraborty, Miltiadis Allamanis, Baishakhi Ray

Our evaluation shows the effectiveness of CODIT in learning and suggesting abstract change templates.

Software Engineering

Modelling Natural Language, Programs, and their Intersection

no code implementations NAACL 2018 Graham Neubig, Miltiadis Allamanis

As a result, in the past several years there has been an increasing research interest in methods that focus on the intersection of programming and natural language, allowing users to use natural language to interact with computers in the complex ways that programs allow us to do.

Semantic Parsing Text Generation

Generative Code Modeling with Graphs

1 code implementation ICLR 2019 Marc Brockschmidt, Miltiadis Allamanis, Alexander L. Gaunt, Oleksandr Polozov

Generative models for source code are an interesting structured prediction problem, requiring to reason about both hard syntactic and semantic constraints as well as about natural, likely programs.

Structured Prediction

Learning to Represent Programs with Graphs

1 code implementation ICLR 2018 Miltiadis Allamanis, Marc Brockschmidt, Mahmoud Khademi

Learning tasks on source code (i. e., formal languages) have been considered recently, but most work has tried to transfer natural language methods and does not capitalize on the unique opportunities offered by code's known syntax.

A Survey of Machine Learning for Big Code and Naturalness

no code implementations18 Sep 2017 Miltiadis Allamanis, Earl T. Barr, Premkumar Devanbu, Charles Sutton

We contrast programming languages against natural languages and discuss how these similarities and differences drive the design of probabilistic models.

SmartPaste: Learning to Adapt Source Code

no code implementations22 May 2017 Miltiadis Allamanis, Marc Brockschmidt

As first solutions, we design a set of deep neural models that learn to represent the context of each variable location and variable usage in a data flow-sensitive way.

Machine Translation Program Repair +2

Tailored Mutants Fit Bugs Better

no code implementations8 Nov 2016 Miltiadis Allamanis, Earl T. Barr, René Just, Charles Sutton

The results demonstrate that the location selection heuristics produce mutants more closely coupled to real faults for a given budget of mutation operator applications.

Software Engineering

A Convolutional Attention Network for Extreme Summarization of Source Code

5 code implementations9 Feb 2016 Miltiadis Allamanis, Hao Peng, Charles Sutton

Attention mechanisms in neural networks have proved useful for problems in which the input and output do not have fixed dimension.

Extreme Summarization Translation

Inducing Generalized Multi-Label Rules with Learning Classifier Systems

1 code implementation25 Dec 2015 Fani A. Tzima, Miltiadis Allamanis, Alexandros Filotheou, Pericles A. Mitkas

In recent years, multi-label classification has attracted a significant body of research, motivated by real-life applications, such as text classification and medical diagnoses.

Classification General Classification +2

Cannot find the paper you are looking for? You can Submit a new open access paper.