Addressing Leakage in Self-Supervised Contextualized Code Retrieval

Autor:	Villmow, Johannes, Campos, Viola, Ulges, Adrian, Schwanecke, Ulrich
Rok vydání:	2022
Předmět:	Computer Science - Software Engineering Computer Science - Information Retrieval Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	We address contextualized code retrieval, the search for code snippets helpful to fill gaps in a partial input program. Our approach facilitates a large-scale self-supervised contrastive training by splitting source code randomly into contexts and targets. To combat leakage between the two, we suggest a novel approach based on mutual identifier masking, dedentation, and the selection of syntax-aligned targets. Our second contribution is a new dataset for direct evaluation of contextualized code retrieval, based on a dataset of manually aligned subpassages of code clones. Our experiments demonstrate that our approach improves retrieval substantially, and yields new state-of-the-art results for code clone and defect detection. Comment: 4 pages, 5 figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2204.11594 Zobrazit plný text záznamu View this record from Arxiv