{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T15:17:15Z","timestamp":1781623035429,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":63,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,5,21]],"date-time":"2022-05-21T00:00:00Z","timestamp":1653091200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61802167, 61802095"],"award-info":[{"award-number":["61802167, 61802095"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Cooperation Fund of Huawei-NJU Creative Laboratory for the Next Programming"},{"name":"National Natural Science Foundation of Jiangsu Province, China","award":["BK20201250"],"award-info":[{"award-number":["BK20201250"]}]},{"name":"NSF award","award":["2034508"],"award-info":[{"award-number":["2034508"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,5,21]]},"DOI":"10.1145\/3510003.3510096","type":"proceedings-article","created":{"date-parts":[[2022,7,5]],"date-time":"2022-07-05T22:42:59Z","timestamp":1657060979000},"page":"2006-2018","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":101,"title":["SPT-code"],"prefix":"10.1145","author":[{"given":"Changan","family":"Niu","sequence":"first","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuanyi","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vincent","family":"Ng","sequence":"additional","affiliation":[{"name":"University of Texas at Dallas"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jidong","family":"Ge","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liguo","family":"Huang","sequence":"additional","affiliation":[{"name":"Southern Methodist University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Luo","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,7,5]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2021"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.449"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3359591.3359735"},{"key":"e_1_3_2_1_4_1","volume-title":"International Conference on Learning Representations.","author":"Alon Uri","year":"2018","unstructured":"Uri Alon, Shaked Brody, Omer Levy, and Eran Yahav. 2018. code2seq: Generating Sequences from Structured Representations of Code. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_5_1","volume-title":"Structural Language Models of Code. In International Conference on Machine Learning. PMLR, 245--256","author":"Alon Uri","year":"2020","unstructured":"Uri Alon, Roy Sadaka, Omer Levy, and Eran Yahav. 2020. Structural Language Models of Code. In International Conference on Machine Learning. PMLR, 245--256."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290353"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization. 65--72","author":"Banerjee Satanjeev","year":"2005","unstructured":"Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments. In Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization. 65--72."},{"key":"e_1_3_2_1_8_1","unstructured":"Luca Buratti Saurabh Pujar Mihaela Bornea Scott McCarley Yunhui Zheng Gaetano Rossiello Alessandro Morari Jim Laredo Veronika Thost Yufan Zhuang and Giacomo Domeniconi. 2020. Exploring Software Naturalness through Neural Language Models. arXiv:2006.12641 [cs.CL]"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2021.3074309"},{"key":"e_1_3_2_1_10_1","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Chen Xinyun","year":"2018","unstructured":"Xinyun Chen, Chang Liu, and Dawn Song. 2018. Tree-to-tree Neural Networks for Program Translation. In Advances in Neural Information Processing Systems, Vol. 31. Curran Associates, Inc."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_3_2_1_12_1","volume-title":"International Conference on Learning Representations.","author":"Clark Kevin","year":"2019","unstructured":"Kevin Clark, Minh-Thang Luong, Quoc V Le, and Christopher D Manning. 2019. ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 4171--4186."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00056"},{"key":"e_1_3_2_1_15_1","volume-title":"ACCL: Architecting Highly Scalable Distributed Training Systems with Highly-Efficient Collective Communication Library","author":"Dong Jianbo","year":"2021","unstructured":"Jianbo Dong, Shaochuang Wang, Fei Feng, Zheng Cao, Heng Pan, Lingbo Tang, Pengcheng Li, Hao Li, Qianyuan Ran, Yiqun Guo, et al. 2021. ACCL: Architecting Highly Scalable Distributed Training Systems with Highly-Efficient Collective Communication Library. IEEE Micro (2021)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1154"},{"key":"e_1_3_2_1_18_1","volume-title":"Deep Code Search. In 2018 IEEE\/ACM 40th International Conference on Software Engineering (ICSE). IEEE, 933--944","author":"Gu Xiaodong","year":"2018","unstructured":"Xiaodong Gu, Hongyu Zhang, and Sunghun Kim. 2018. Deep Code Search. In 2018 IEEE\/ACM 40th International Conference on Software Engineering (ICSE). IEEE, 933--944."},{"key":"e_1_3_2_1_19_1","volume-title":"GraphCodeBERT: Pre-training Code Representations with Data Flow. In International Conference on Learning Representations, ICLR","author":"Guo Daya","year":"2021","unstructured":"Daya Guo, Shuo Ren, Shuai Lu, Zhangyin Feng, Duyu Tang, LIU Shujie, Long Zhou, Nan Duan, Alexey Svyatkovskiy, Shengyu Fu, et al. 2021. GraphCodeBERT: Pre-training Code Representations with Data Flow. In International Conference on Learning Representations, ICLR 2021."},{"key":"e_1_3_2_1_20_1","volume-title":"Deep Code Comment Generation. In 2018 IEEE\/ACM 26th International Conference on Program Comprehension (ICPC). IEEE, 200--20010","author":"Hu Xing","year":"2018","unstructured":"Xing Hu, Ge Li, Xin Xia, David Lo, and Zhi Jin. 2018. Deep Code Comment Generation. In 2018 IEEE\/ACM 26th International Conference on Program Comprehension (ICPC). IEEE, 200--20010."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-019-09730-9"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/314"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5844"},{"key":"e_1_3_2_1_24_1","unstructured":"Hamel Husain Ho-Hsiang Wu Tiferet Gazit Miltiadis Allamanis and Marc Brockschmidt. 2020. CodeSearchNet Challenge: Evaluating the State of Semantic Code Search. arXiv:1909.09436 [cs.LG]"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence","volume":"161","author":"Jiang Xue","year":"2021","unstructured":"Xue Jiang, Zhuoran Zheng, Chen Lyu, Liang Li, and Lei Lyu. 2021. TreeBERT: A tree-based pre-trained model for programming language. In Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, Vol. 161. PMLR, 54--63."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2007.256943"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"5121","author":"Kanade Aditya","year":"2020","unstructured":"Aditya Kanade, Petros Maniatis, Gogul Balakrishnan, and Kensen Shi. 2020. Learning and Evaluating Contextual Embedding of Source Code. In Proceedings of the 37th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 119). PMLR, 5110--5121."},{"key":"e_1_3_2_1_28_1","unstructured":"Rafael Michael Karampatsis and Charles Sutton. 2020. SCELMo: Source Code Embeddings from Language Models. arXiv:2004.13214 [cs.SE]"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-4012"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387904.3389268"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00087"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1394"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"e_1_3_2_1_35_1","volume-title":"Improving Code Summarization with Block-wise Abstract Syntax Tree Splitting. In 29th IEEE\/ACM International Conference on Program Comprehension, ICPC","author":"Lin Chen","year":"2021","unstructured":"Chen Lin, Zhichao Ouyang, Junqing Zhuang, Jianqiang Chen, Hui Li, and Rongxin Wu. 2021. Improving Code Summarization with Block-wise Abstract Syntax Tree Splitting. In 29th IEEE\/ACM International Conference on Program Comprehension, ICPC 2021."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.3115\/1118162.1118168"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3324884.3416591"},{"key":"e_1_3_2_1_38_1","volume-title":"Decoupled Weight Decay Regularization. In International Conference on Learning Representations.","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00041"},{"key":"e_1_3_2_1_40_1","volume-title":"Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers). 314--319","author":"Miceli-Barone Antonio Valerio","year":"2017","unstructured":"Antonio Valerio Miceli-Barone and Rico Sennrich. 2017. A Parallel Corpus of Python Functions and Documentation Strings for Automated Code Documentation and Code Generation. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers). 314--319."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17606"},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. 311--318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a Method for Automatic Evaluation of Machine Translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. 311--318."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"e_1_3_2_1_44_1","unstructured":"Alec Radford Jeff Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. (2019)."},{"key":"e_1_3_2_1_45_1","first-page":"1","article-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. Journal of Machine Learning Research 21, 140 (2020), 1--67.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_46_1","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 1073--1083","author":"Liu Peter J","year":"2017","unstructured":"Abigail See, Peter J Liu, and Christopher D Manning. 2017. Get To The Point: Summarization with Pointer-Generator Networks. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 1073--1083."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"e_1_3_2_1_49_1","volume-title":"International Conference on Machine Learning. PMLR, 5926--5936","author":"Song Kaitao","year":"2019","unstructured":"Kaitao Song, Xu Tan, Tao Qin, Jianfeng Lu, and Tie-Yan Liu. 2019. MASS: Masked Sequence to Sequence Pre-training for Language Generation. In International Conference on Machine Learning. PMLR, 5926--5936."},{"key":"e_1_3_2_1_50_1","volume-title":"Towards Automatically Generating Summary Comments for Java Methods. In 25th IEEE\/ACM International Conference on Automated Software Engineering, ASE","author":"Sridhara Giriprasad","year":"2010","unstructured":"Giriprasad Sridhara, Emily Hill, Divya Muppaneni, Lori Pollock, and K Vijay-Shanker. 2010. Towards Automatically Generating Summary Comments for Java Methods. In 25th IEEE\/ACM International Conference on Automated Software Engineering, ASE 2010. ACM, 43--52."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3417058"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330699"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340544"},{"key":"e_1_3_2_1_54_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is All You Need. In Advances in Neural Information Processing Systems. 5998--6008."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2019.00012"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238206"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17650"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.93"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPC52881.2021.00022"},{"key":"e_1_3_2_1_60_1","volume-title":"XLNET: Generalized Autoregressive Pretraining for Language Understanding. Advances in Neural Information Processing Systems 32","author":"Yang Zhilin","year":"2019","unstructured":"Zhilin Yang, Zihang Dai, Yiming Yang, Jaime Carbonell, Russ R Salakhutdinov, and Quoc V Le. 2019. XLNET: Generalized Autoregressive Pretraining for Language Understanding. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPC52881.2021.00010"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380383"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00086"}],"event":{"name":"ICSE '22: 44th International Conference on Software Engineering","location":"Pittsburgh Pennsylvania","acronym":"ICSE '22","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS"]},"container-title":["Proceedings of the 44th International Conference on Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3510003.3510096","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3510003.3510096","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:10:23Z","timestamp":1750183823000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3510003.3510096"}},"subtitle":["sequence-to-sequence pre-training for learning source code representations"],"short-title":[],"issued":{"date-parts":[[2022,5,21]]},"references-count":63,"alternative-id":["10.1145\/3510003.3510096","10.1145\/3510003"],"URL":"https:\/\/doi.org\/10.1145\/3510003.3510096","relation":{},"subject":[],"published":{"date-parts":[[2022,5,21]]},"assertion":[{"value":"2022-07-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}