2025/02/18 by Liangying Shao, Shao, Liangying, Yanfu Yan +5 · 2 citations
Computer Science · #Computation and Language (cs.CL) #Embedded Systems Design Techniques #FOS: Computer and information sciences #Model-Driven Software Engineering Techniques #Software Engineering Research
paper · pdf · doi:10.48550/arxiv.2502.12490
openalex publication_date 2025/02/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Deep learning-based code generation has completely transformed the way developers write programs today. Existing approaches to code generation have focused either on the Sequence-to-Sequence paradigm, which generates target code as a sequence of tokens, or the Sequence-to-Tree paradigm, which outputs code as a sequence of actions. While these two paradigms are intuitively complementary, their combination has not been previously explored. By comparing the code generated under these two paradigms, we find that integrating them holds significant potential. In this paper, we propose UniGenCoder for code-related generation tasks, which consists of a shared encoder, a shared decoder with a minimal set of additional parameters to unify two paradigms, and a selector that dynamically chooses optimal paradigm for each instance. Also, during the model training, we first perform the multi-task learning and distillation strategies to facilitate knowledge transfer between two paradigms, and then leverage contrastive learning to train the selector. Experimental results on the text-to-code and code-to-code generation tasks demonstrate the effectiveness of our proposed model. We release our code at https://github.com/DeepLearnXMU/UniGenCoder.