VarCLR: Variable Semantic Representation Pre-training via Contrastive Learning

Variable names are critical for conveying intended program behavior. Machine learning-based program analysis methods use variable name representations for a wide range of tasks, such as suggesting new variable names and bug detection. Ideally, such methods could capture semantic relationships betwee...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2022 IEEE/ACM 44th International Conference on Software Engineering (ICSE) s. 2327 - 2339
Hlavní autoři: Chen, Qibin, Lacomis, Jeremy, Schwartz, Edward J., Neubig, Graham, Vasilescu, Bogdan, Goues, Claire Le
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: ACM 01.05.2022
Témata:
Bit error rate
Codes
Computer bugs
Data models
Semantics
Syntactics
Training data
ISSN:1558-1225
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Variable names are critical for conveying intended program behavior. Machine learning-based program analysis methods use variable name representations for a wide range of tasks, such as suggesting new variable names and bug detection. Ideally, such methods could capture semantic relationships between names beyond syntactic similarity, e.g., the fact that the names average and mean are similar. Unfortunately, previous work has found that even the best of previous representation approaches primarily capture "relatedness" (whether two variables are linked at all), rather than "similarity" (whether they actually have the same meaning). We propose Varclr, a new approach for learning semantic representations of variable names that effectively captures variable similarity in this stricter sense. We observe that this problem is an excellent fit for contrastive learning, which aims to minimize the distance between explicitly similar inputs, while maximizing the distance between dissimilar inputs. This requires labeled training data, and thus we construct a novel, weakly-supervised variable renaming dataset mined from GitHub edits. We show that Varclr enables the effective application of sophisticated, general-purpose language models like BERT, to variable name representation and thus also to related downstream tasks like variable name similarity search or spelling correction. Varclr produces models that significantly outperform the state-of-the-art on IDBENCH, an existing benchmark that explicitly captures variable similarity (as distinct from relatedness). Finally, we contribute a release of all data, code, and pre-trained models, aiming to provide a drop-in replacement for variable representations used in either existing or future program analyses that rely on variable names.
ISSN:1558-1225
DOI:10.1145/3510003.3510162