MAST's repositories
convolutional-attention
Repository for the code of the "A Convolutional Attention Network for Extreme Summarization of Source Code" paper
OpenVocabCodeNLM
Contains the code for our ICSE 2020 paper: Big Code != Big Vocabulary: Open-Vocabulary Language Models for Source Code and for its earlier pre-print: Maybe Deep Neural Networks are the Best Choice for Modeling Source Code (https://arxiv.org/abs/1903.05734). This is the first open vocabulary language model for code that uses the byte pair encoding algorithm (BPE) to learn a segmentation of code tokens into subword units.
naturalize
Source code for the Naturalize project
api-mining
Probabilistic API Mining
sequence-mining
Probabilistic Sequence Mining
mineSStuBs
Hosts our tool for mining simple "stupid'' bugs (SStuBs).
codemining-core
A set of tools for extracting tokens and ASTs from code
itemset-mining
Probabilistic Itemset Mining
codemining-treelm
Tree Language Models
codemining-sequencelm
Sequential Language Models
codemining-utils
Utility classes for serialization, parameter loading, sampling and math
learnbigcode.github.io
Website for Learning from "Big Code"
mast-group.github.io
MAST Group Website
variable-naming-challenge
Source code related to the variable naming challenge
commitmining-tools
A set of tools for traversing a Git repository and possibly its files
js-analyser
Javascript analyser using Node and Esprima
js-random-tester
JS Random testing tool and new Definition File creator using old versions
maven-repo
Maven repository for jars not on maven central
DeepSStuBs
DeepSStuBs is a framework for learning single statement bug detectors from an existing code corpus.
js-analyser-util
Util package to analyse instrumented and collected data from Node.JS projects