Natural Language Processing
- Deep Learning for NLP: An Overview of Recent Trends
- Sequence-to-Sequence with Attention Model for Text Summarization
- Natural Language Processing with Python
Sequence to sequence
Tools
Source Code Processing
- GitHub research, visualization and talks
- awesome machine learning on sourcecode
- MAST
- MUSE
- Machine learning for source code analysis
- Machine Learning for Large Scale Code Analysis
- Mining software repositories
- Using Deep Learning to Understand Your Source Code
- One More Analysis of GitHub and StackOverflow Data with Google BigQuery
- Want people to actually answer your Stack Overflow question? Add a question mark.
- Catalog of references to StackOverflow questions found in GitHub sources
- Using Artificial Intelligence to Write Self-Modifying/Improving Programs
- Seminars on Applications of Deep Learning in Software Engineering and Programming Languages
- GitHub experiments
- How To Create Natural Language Semantic Search For Arbitrary Objects With Deep Learning
- Example Check
- How To Create Data Products That Are Magical Using Sequence-to-Sequence Models
Tools
Datasets
Software Metrics
Abstract Syntax Tree
- Introduction to AST
- Awesome AST
- AST on GitHub
- MacroPy
- typeshed
- GitHub AST Viewer
- saplings: library of algorithms and data structures for working with abstract syntax trees
- Conflerge: resolving conflict merges with ASTs
- deast: a Python 3 module to convert an abstract syntax tree (AST) into Python code
- horast: human-oriented abstract syntax tree for Python 3
lint
- pyflakes: checks Python source files for errors
- bellybutton: custom Python linting through AST expressions
- vermin: concurrently detect the minimum Python versions needed to run code
Code Recommendation
- Kite
- Codot competitors
- Software data mining and code recommendation
- ai.codes
- neural_complete: a neural network trained to help writing neural network code using autocomplete
- CLAMS
- Semantic code search
Sentiment Analysis
- Sentiment analysis of commit comments in GitHub: an empirical study
- The Emotional Side of Software Developers in JIRA
- Measuring code sentiment in a GitHub repository