On ML-Based Program Translation: Perils and Promises
This work addresses the challenge of migrating legacy software to new programming languages for developers and organizations, though it is incremental as it builds on existing translators with added processing steps.
The paper tackled the problem of imperfect unsupervised machine learning-based program translators by analyzing their failure patterns and developing a rule-based program mutation engine for pre- and post-processing, which significantly improved state-of-the-art performance when combined with the translator.
With the advent of new and advanced programming languages, it becomes imperative to migrate legacy software to new programming languages. Unsupervised Machine Learning-based Program Translation could play an essential role in such migration, even without a sufficiently sizeable reliable corpus of parallel source code. However, these translators are far from perfect due to their statistical nature. This work investigates unsupervised program translators and where and why they fail. With in-depth error analysis of such failures, we have identified that the cases where such translators fail follow a few particular patterns. With this insight, we develop a rule-based program mutation engine, which pre-processes the input code if the input follows specific patterns and post-process the output if the output follows certain patterns. We show that our code processing tool, in conjunction with the program translator, can form a hybrid program translator and significantly improve the state-of-the-art. In the future, we envision an end-to-end program translation tool where programming domain knowledge can be embedded into an ML-based translation pipeline using pre- and post-processing steps.