Extending Source Code Pre-Trained Language Models to Summarise Decompiled Binaries.
Ali Al-KaswanToufique AhmedMaliheh IzadiAnand Ashok SawantPremkumar T. DevanbuArie van DeursenPublished in: CoRR (2023)
Keyphrases
- source code
- language model
- pre trained
- language modeling
- open source
- training data
- software systems
- retrieval model
- document retrieval
- probabilistic model
- n gram
- speech recognition
- open source software
- information retrieval
- training examples
- vector space model
- software maintenance
- query expansion
- test collection
- high level
- software repositories
- control signals
- smoothing methods
- data mining
- visual information
- training set
- relevance model