Neural network trained on AST structural details repairs undeclared variable errors and infers types, reporting 81% success on location/identification and 80% on types for 1059 programs in the prutor dataset.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Automatic Repair and Type Binding of Undeclared Variables using Neural Networks
Neural network trained on AST structural details repairs undeclared variable errors and infers types, reporting 81% success on location/identification and 80% on types for 1059 programs in the prutor dataset.