Page 203 - 《软件学报》2026年第2期

682 软件学报 2026 年第 37 卷第 2 期

for code infilling and synthesis. In: Proc. of the 11th Int’l Conf. on Learning Representations. Kigali: OpenReview.net, 2023.
[36] 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]
[37] Wang Y, Wang WS, Joty S, Hoi SCH. CodeT5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and
generation. In: Proc. of the 2021 Conf. on Empirical Methods in Natural Language Processing. Punta Cana: ACL, 2021. 8696–8708. [doi:
10.18653/v1/2021.emnlp-main.685]
[38] Gao SZ, Gao CY, He YL, Zeng JC, Nie L, Xia X, Lyu M. Code structure guided Transformer for source code summarization. ACM
Trans. on Software Engineering and Methodology, 2023, 32(1): 23. [doi: 10.1145/3522674]
[39] Nagaraj Y, Gupta U. AST-MHSA: Code summarization using multi-head self-attention. arXiv:2308.05646, 2023.
[40] Shahbazi R, Fard F. APIContext2Com: Code comment generation by incorporating pre-defined API documentation. In: 2023 IEEE/ACM
31st Int’l Conf. on Program Comprehension. Melbourne: IEEE, 2023. 13–24. [doi: 10.1109/ICPC58990.2023.00012]
[41] Li MC, Yu HQ, Fan GS, Zhou ZY, Huang ZJ. Enhancing code summarization with action word prediction. Neurocomputing, 2024, 563:
126777. [doi: 10.1016/j.neucom.2023.126777]
[42] Sun WS, Fang CR, Chen YC, Zhang QJ, Tao GH, You YD, Han TX, Ge YF, Hu YL, Luo B, Chen ZY. An extractive-and-abstractive
framework for source code summarization. ACM Trans. on Software Engineering and Methodology, 2024, 33(3): 75. [doi: 10.1145/
3632742]
[43] Wang Y, Le H, Gotmare A, Bui N, Li JN, Hoi S. CodeT5+: Open code large language models for code understanding and generation. In:
Proc. of the 2023 Conf. on Empirical Methods in Natural Language Processing. Singapore: ACL, 2023. 1069–1088. [doi: 10.18653/v1/
2023.emnlp-main.68]
[44] Guo DY, Zhu QH, Yang DJ, Xie ZD, Dong K, Zhang WT, Chen GT, Bi X, Wu U, Li YK, 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] Sun Y, Wang SH, Li YK, Feng SK, Chen XY, Zhang H, Tian X, Zhu DX, Tian H, Wu H. ERNIE: Enhanced representation through
knowledge integration. arXiv:1904.09223, 2019.
[46] Clark K, Luong MT, Le QV, Manning CD. ELECTRA: Pre-training text encoders as discriminators rather than generators. arXiv:2003.
10555, 2020
[47] Li ZC, Li SS, Zhou GD. Pre-trained token-replaced detection model as few-shot learner. In: Proc. of the 29th Int’l Conf. on
Computational Linguistics. Gyeongju: ACL, 2022. 3274–3284.
[48] Antoun W, Baly F, Hajj H. AraELECTRA: Pre-training text discriminators for Arabic language understanding. In: Proc. of the 6th Arabic
Natural Language Processing Workshop. Kyiv: ACL, 2021. 191–195.
[49] He PC, Gao JF, Chen WZ. DeBERTaV3: Improving DeBERTa using ELECTRA-style pre-training with gradient-disentangled
embedding sharing. In: Proc. of the 11th Int’l Conf. on Learning Representations. Kigali: OpenReivew.net, 2023.
[50] Lachaux MA, Roziere B, Szafraniec M, Lample G. DOBF: A deobfuscation pre-training objective for programming languages. In: Proc.
of the 35th Int’l Conf. on Neural Information Processing Systems. Curran Associates Inc., 2021. 1147.
[51] Jain P, Jain A, Zhang TJ, Abbeel P, Gonzalez J, Stoica I. Contrastive code representation learning. In: Proc. of the 2021 Conf. on
Empirical Methods in Natural Language Processing. Punta Cana: ACL, 2021. 5954–5971. [doi: 10.18653/v1/2021.emnlp-main.482]
[52] Ding YRB, Buratti L, Pujar S, Morari A, Ray B, Chakraborty S. Contrastive learning for source code with structural and functional
properties. arXiv:2110.03868, 2021.
[53] Sennrich R, Haddow B, Birch A. Neural machine translation of rare words with subword units. In: Proc. of the 54th Annual Meeting of
the Association for Computational Linguistics (Vol. 1: Long Papers). Berlin: ACL, 2016. 1715–1725. [doi: 10.18653/v1/P16-1162]
[54] Radford A, Wu J, Child R, Luan D, Amodei D, Sutskever I. Language models are unsupervised multitask learners. OpenAI Blog, 2019,
1(8): 9.
[55] Vinyals O, Fortunato M, Jaitly N. Pointer networks. In: Proc. of the 29th Int’l Conf. on Neural Information Processing Systems. Montreal:
MIT Press, 2015. 2692–2700.
[56] Barone AVM, Sennrich R. A parallel corpus of Python functions and documentation strings for automated code documentation and code
generation. In: Proc. of the 8th Int’l Joint Conf. on Natural Language Processing (Vol. 2: Short Papers). Taipei: ACL, 2017. 314–319.
[57] Husain H, Wu HH, Gazit T, Allamanis M, Brockschmidt M. CodeSearchNet challenge: Evaluating the state of semantic code search.
arXiv:1909.09436, 2019.
[58] Papineni K, Roukos S, Ward T, Zhu WJ. BLEU: A method for automatic evaluation of machine translation. In: Proc. of the 40th Annual
Meeting of the Association for Computational Linguistics. Philadelphia: ACL, 2002. 311–318. [doi: 10.3115/1073083.1073135]