Augmenting commit classification by using fine-grained source code changes and a pre-trained deep neural language model.
Lobna GhadhabIlyes JenhaniMohamed Wiem MkaouerMontassar Ben MessaoudPublished in: Inf. Softw. Technol. (2021)
Keyphrases
- fine grained
- source code
- language model
- coarse grained
- pre trained
- open source
- language modeling
- document retrieval
- probabilistic model
- access control
- n gram
- machine learning
- information retrieval
- high level
- decision trees
- support vector
- retrieval model
- query expansion
- feature space
- query terms
- speech recognition
- training set
- supervised learning
- neural network
- learning algorithm
- case study
- database systems
- text classification
- feature extraction
- training data
- feature vectors