SCELMo: Source Code Embeddings from Language Models.
Rafael-Michael KarampatsisCharles SuttonPublished in: CoRR (2020)
Keyphrases
- source code
- language model
- language modeling
- open source
- document retrieval
- n gram
- software systems
- probabilistic model
- test collection
- speech recognition
- query expansion
- retrieval model
- information retrieval
- language modelling
- vector space
- statistical language models
- software projects
- low dimensional
- software maintenance
- plagiarism detection
- high level
- vector space model
- software evolution
- smoothing methods
- program understanding
- dimensionality reduction
- software artifacts
- free software
- language models for information retrieval
- machine learning
- structured data
- high dimensional