Page 141 - 《软件学报》2026年第2期

620 软件学报 2026 年第 37 卷第 2 期

Proc. of the 29th IEEE/ACM Int’l Conf. on Program Comprehension. Madrid: IEEE, 2021. 184–195. [doi: 10.1109/ICPC52881.2021.
00026]
[36] Hu X, Li G, Xia X, Lo D, Jin Z. Deep code comment generation with hybrid lexical and syntactical information. Empirical Software
Engineering, 2020, 25(3): 2179–2217. [doi: 10.1007/S10664-019-09730-9]
[37] Lin CY. ROUGE: A package for automatic evaluation of summaries. 2004. https://aclanthology.org/W04-1013.pdf
[38] Banerjee S, Lavie A. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In: Proc. of
the 2005 ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization. Ann Arbor:
ACL, 2005. 65–72.
[39] Wu HQ, Zhao H, Zhang M. Code summarization with structure-induced Transformer. In: Proc. of the 2021 Findings of the Association
for Computational Linguistics: ACL-IJCNLP 2021. ACL, 2021. 1078–1090. [doi: 10.18653/V1/2021.FINDINGS-ACL.93]
[40] Gong Z, Gao CY, Wang YS, Gu WC, Peng Y, Xu ZL. Source code summarization with structural relative position guided Transformer.
arXiv:2202.06521, 2022.
[41] Tang Z, Shen XY, Li CY, Ge JD, Huang LG, Zhu ZL, Luo B. AST-Trans: Code summarization with efficient tree-structured attention. In:
Proc. of the 44th Int’l Conf. on Software Engineering. Pittsburgh: ACM, 2022. 150–162. [doi: 10.1145/3510003.3510224]
[42] Feng ZY, Guo DY, Tang DY, Duan N, Feng XC, Gong M, Shou LJ, Qin B, Liu T, Jiang DX, Zhou M, CodeBERT: A pre-trained model
for programming and natural languages. In: Proc. of the 2020 Findings of the Association for Computational Linguistics: EMNLP 2020.
ACL, 2020. 1536–1547. [doi: 10.18653/V1/2020.FINDINGS-EMNLP.139]
[43] Rozière B, Gehring J, Gloeckle F, Sootla S, Gat I, Tan XE, Adi Y, Liu JY, Sauvestre R, Remez T, Rapin J, Kozhevnikov A, Evtimov I,
Bitton J, Bhatt M, Ferrer CC, Grattafiori A, Xiong WH, Défossez A, Copet J, Azhar F, Touvron H, Martin L, Usunier N, Scialom T,
Synnaeve G. Code LLaMA: Open foundation models for code. arXiv:2308.12950, 2024.
[44] Guo DY, Zhu QH, Yang DJ, Xie ZD, Dong K, Zhang WT, Chen GT, Bi X, Wu Y, Li KY, Luo FL, Xiong YF, Liang WF. DeepSeek-
Coder: When the large language model meets programming—The rise of code intelligence. arXiv:2401.14196, 2024.
[45] Hui BY, Yang J, Cui ZY, Yang JX, Liu DYH, Zhang L, Liu TY, Zhang JJ, Yu BW, Lu KM, Dang K, Fan Y, Zhang YC, Yang A, Men R,
Huang F, Zheng B, Miao YB, Quan SHR, Feng YL, Ren XZ, Ren XC, Zhou JR, Lin JY. Qwen2.5-coder technical report.
arXiv:2409.12186, 2024.
[46] Mu FW, Chen X, Shi L, Wang S, Wang Q. Automatic comment generation via multi-pass deliberation. In: Proc. of the 37th IEEE/ACM
Int’l Conf. on Automated Software Engineering. Rochester: ACM, 2023. 14. [doi: 10.1145/3551349.3556917]
[47] Haldar R, Hockenmaier J. Analyzing the performance of large language models on code summarization. In: Proc. of the 2024 Joint Int’l
Conf. on Computational Linguistics, Language Resources and Evaluation. Torino: ACL, 2024. 995–1008.
[48] Zhu YX, Pan MX. Automatic code summarization: A systematic literature review. arXiv:1909.04352, 2019.
[49] Alon U, Brody S, Levy O, Yahav E. Code2seq: Generating sequences from structured representations of code. arXiv:1808.01400, 2019.
[50] Xu K, Wu LF, Wang ZG, Feng YS, Witbrock M, Sheinin V. Graph2Seq: Graph to sequence learning with attention-based neural
networks. arXiv:1804.00823, 2018.
[51] Ahmad W, Chakraborty S, Ray B, Chang KW. Unified pre-training for program understanding and generation. In: Proc. of the 2021 Conf.
of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. ACL, 2021.
2655–2668. [doi: 10.18653/V1/2021.NAACL-MAIN.211]

附中文参考文献
[2] 陈翔, 杨光, 崔展齐, 孟国柱, 王赞. 代码注释自动生成方法综述. 软件学报, 2021, 32(7): 2118–2141. http://www.jos.org.cn/1000-9825/
6258.htm [doi: 10.13328/j.cnki.jos.006258]

作者简介
李重, 博士, 助理研究员, CCF 专业会员, 主要研究领域为智能软件工程, 可信人工智能.
施超煊, 硕士, 主要研究领域为智能软件工程.
潘敏学, 博士, 教授, 博士生导师, CCF 高级会员, 主要研究领域为软件建模与验证, 程序分析与测试, 智能软件工程.
张天, 博士, 教授, 博士生导师, CCF 高级会员, 主要研究领域为模型驱动软件工程.
王林章, 博士, 教授, 博士生导师, CCF 会士, 主要研究领域为软件工程, 软件安全.
李宣东, 博士, 教授, 博士生导师, CCF 会士, 主要研究领域为软件工程, 系统软件, 可信软件, 形式化方法.