Unified Pre-training for Program Understanding and Generation
This work addresses the need for unified models in software engineering to handle diverse code-related tasks, though it is incremental as it builds on existing pre-training paradigms.
The paper tackles the problem of program understanding and generation by introducing PLBART, a sequence-to-sequence model pre-trained on Java and Python functions with natural language text, which outperforms or rivals state-of-the-art models in tasks like code summarization, generation, and translation across seven programming languages.
Code summarization and generation empower conversion between programming language (PL) and natural language (NL), while code translation avails the migration of legacy code from one PL to another. This paper introduces PLBART, a sequence-to-sequence model capable of performing a broad spectrum of program and language understanding and generation tasks. PLBART is pre-trained on an extensive collection of Java and Python functions and associated NL text via denoising autoencoding. Experiments on code summarization in the English language, code generation, and code translation in seven programming languages show that PLBART outperforms or rivals state-of-the-art models. Moreover, experiments on discriminative tasks, e.g., program repair, clone detection, and vulnerable code detection, demonstrate PLBART's effectiveness in program understanding. Furthermore, analysis reveals that PLBART learns program syntax, style (e.g., identifier naming convention), logical flow (e.g., if block inside an else block is equivalent to else if block) that are crucial to program semantics and thus excels even with limited annotations.