LIGER blends symbolic and concrete traces to learn precise semantic program embeddings, outperforming syntax-based models on CoSET classification and code2seq on method name prediction while using fewer executions.
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
-
Learning Blended, Precise Semantic Program Embeddings
LIGER blends symbolic and concrete traces to learn precise semantic program embeddings, outperforming syntax-based models on CoSET classification and code2seq on method name prediction while using fewer executions.