A T5-based study of 8 context types for Java code completion finds that combining coding contexts yields +11% relative improvement, and a confidence-based ensemble of context models yields +22%.
Structural language models of code,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Deep Learning-based Code Completion: On the Impact on Performance of Contextual Information
A T5-based study of 8 context types for Java code completion finds that combining coding contexts yields +11% relative improvement, and a confidence-based ensemble of context models yields +22%.