US 12,321,735 B2
Syntax unit testing and fine-tuning of neural transcompilation models
Colin Bruce Clement, Seattle, WA (US); Yufan Huang, Shanghai (CN); Neelakantan Sundaresan, Bellevue, WA (US); Yiding Tian, Shanghai (CN); and Maoquan Wang, Shanghai (CN)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by MICROSOFT TECHNOLOGY LICENSING, LLC., Redmond, WA (US)
Filed on Dec. 23, 2022, as Appl. No. 18/088,492.
Prior Publication US 2024/0211224 A1, Jun. 27, 2024
Int. Cl. G06F 8/51 (2018.01); G06F 8/41 (2018.01); G06N 3/08 (2023.01)
CPC G06F 8/51 (2013.01) [G06F 8/41 (2013.01); G06N 3/08 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
a processor and a memory;
wherein the memory stores a program configured to be executed by the processor,
wherein the program comprises instructions that when executed by the processor perform actions that:
obtain a syntax unit test, wherein the syntax unit test comprises a first source code program written in a first programming language and a unit test;
execute a neural transcompilation model, given the syntax unit test, to generate a translation of the first source code program into a second programming language, wherein the first programming language differs from the second programming language;
determine a syntax translation defect in the translation of the first source code program into the second programming language generated by the neural transcompilation model, wherein the syntax translation defect represents a syntax element of the first programming language that the neural transcompilation model fails to translate into the second programming language; and
fine-tune the neural transcompilation model on a training dataset that includes the first source code program of the first programming language having the syntax translation defect with a semantically-equivalent translation that is syntactically-correct in the second programming language.