TransMap: Pinpointing Mistakes in Neural Code Translation (Artifact)

This is the artifact for the paper TransMap: Pinpointing Mistakes in Neural Code Translation in ESEC/FSE 2023 The latest artifact can be found here: https://github.com/HALOCORE/TransMap This artifact TransMap is a tool to pinpoint mistakes in neural code translation by Codex or ChatGPT. More specifically, it focuses on Python to JavaScript code translation. It takes a standalone Python program and its JavaScript translation (by Codex or ChatGPT) as input. It will first generate a source mapping between statements in the target program and the source program, using Codex or ChatGPT. Next, it will use the generated source map to aid in tracing the execution of the translated program and comparing it against the source reference program to pinpoint the mistakes in the translation.

GitHub Repository: https://github.com/HALOCORE/TransMap

Related Organizations

National University of Singapore
Singapore

Keywords

Code Translation, Large Language Models, Semantic Mistakes

Impact byBIP!

	selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	1
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Average
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Average
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Average