Unifying AST labels across languages and encoding paired graphs with a Graph Matching Network creates a shared semantic vector space that places functionally equivalent code from different languages near each other.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
DIAURec unifies intent and language modeling to reconstruct and optimize representations in prototype and distribution spaces, outperforming baselines on three datasets.
citing papers explorer
-
Bridging the Programming Language Gap: Constructing a Multilingual Shared Semantic Space through AST Unification and Graph Matching
Unifying AST labels across languages and encoding paired graphs with a Graph Matching Network creates a shared semantic vector space that places functionally equivalent code from different languages near each other.
-
DIAURec: Dual-Intent Space Representation Optimization for Recommendation
DIAURec unifies intent and language modeling to reconstruct and optimize representations in prototype and distribution spaces, outperforming baselines on three datasets.