ComFormer: Code Comment Generation via Transformer and Fusion Method-based Hybrid Code Representation
This addresses the issue of low-quality code comments for developers, but it appears incremental as it builds on existing neural machine translation approaches.
The paper tackles the problem of generating code comments to improve developer comprehension by proposing ComFormer, a method based on Transformer and hybrid code representation, which shows competitiveness against seven state-of-the-art baselines in performance measures and human study verification.
Developers often write low-quality code comments due to the lack of programming experience, which can reduce the efficiency of developers program comprehension. Therefore, developers hope that code comment generation tools can be developed to illustrate the functionality and purpose of the code. Recently, researchers mainly model this problem as the neural machine translation problem and tend to use deep learning-based methods. In this study, we propose a novel method ComFormer based on Transformer and fusion method-based hybrid code presentation. Moreover, to alleviate OOV (out-of-vocabulary) problem and speed up model training, we further utilize the Byte-BPE algorithm to split identifiers and Sim_SBT method to perform AST Traversal. We compare ComFormer with seven state-of-the-art baselines from code comment generation and neural machine translation domains. Comparison results show the competitiveness of ComFormer in terms of three performance measures. Moreover, we perform a human study to verify that ComFormer can generate high-quality comments.