{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T17:13:14Z","timestamp":1772039594713,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T00:00:00Z","timestamp":1712880000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,12]]},"DOI":"10.1145\/3597503.3639125","type":"proceedings-article","created":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T16:43:26Z","timestamp":1712940206000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["GrammarT5: Grammar-Integrated Pretrained Encoder-Decoder Neural Model for Code"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5155-451X","authenticated-orcid":false,"given":"Qihao","family":"Zhu","sequence":"first","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1697-3451","authenticated-orcid":false,"given":"Qingyuan","family":"Liang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9990-9120","authenticated-orcid":false,"given":"Zeyu","family":"Sun","sequence":"additional","affiliation":[{"name":"Zhongguancun Laboratory, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8991-747X","authenticated-orcid":false,"given":"Yingfei","family":"Xiong","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8304-7055","authenticated-orcid":false,"given":"Lu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4541-3305","authenticated-orcid":false,"given":"Shengyu","family":"Cheng","sequence":"additional","affiliation":[{"name":"ZTE Corporation, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.211"},{"key":"e_1_3_2_1_2_1","unstructured":"Jacob Austin Augustus Odena Maxwell Nye Maarten Bosma Henryk Michalewski David Dohan Ellen Jiang Carrie Cai Michael Terry Quoc Le et al. 2021. Program synthesis with large language models. arXiv preprint arXiv:2108.07732 (2021)."},{"key":"e_1_3_2_1_3_1","volume-title":"Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al.","author":"Chen Mark","year":"2021","unstructured":"Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al. 2021. Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374 (2021)."},{"key":"e_1_3_2_1_4_1","volume-title":"Tree-to-tree neural networks for program translation. Advances in neural information processing systems 31","author":"Chen Xinyun","year":"2018","unstructured":"Xinyun Chen, Chang Liu, and Dawn Song. 2018. Tree-to-tree neural networks for program translation. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_2_1_5_1","unstructured":"Codeparrot. 2023. GitHub Code Dataset. https:\/\/huggingface.co\/datasets\/codeparrot\/github-code"},{"key":"e_1_3_2_1_6_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_7_1","unstructured":"Facebook. 2023. Pytorch. https:\/\/pytorch.org"},{"key":"e_1_3_2_1_8_1","volume-title":"Codebert: A pre-trained model for programming and natural languages. arXiv preprint arXiv:2002.08155","author":"Feng Zhangyin","year":"2020","unstructured":"Zhangyin Feng, Daya Guo, Duyu Tang, Nan Duan, Xiaocheng Feng, Ming Gong, LinjunShou, Bing Qin, Ting Liu, Daxin Jiang, et al. 2020. Codebert: A pre-trained model for programming and natural languages. arXiv preprint arXiv:2002.08155 (2020)."},{"key":"e_1_3_2_1_9_1","volume-title":"InCoder: A Generative Model for Code Infilling and Synthesis. In The Eleventh International Conference on Learning Representations.","author":"Fried Daniel","year":"2022","unstructured":"Daniel Fried, Armen Aghajanyan, Jessy Lin, Sida Wang, Eric Wallace, Freda Shi, Ruiqi Zhong, Scott Yih, Luke Zettlemoyer, and Mike Lewis. 2022. InCoder: A Generative Model for Code Infilling and Synthesis. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.499"},{"key":"e_1_3_2_1_11_1","volume-title":"Graphcodebert: Pre-training code representations with data flow. arXiv preprint arXiv:2009.08366","author":"Guo Daya","year":"2020","unstructured":"Daya Guo, Shuo Ren, Shuai Lu, Zhangyin Feng, Duyu Tang, Shujie Liu, Long Zhou, Nan Duan, Alexey Svyatkovskiy, Shengyu Fu, et al. 2020. Graphcodebert: Pre-training code representations with data flow. arXiv preprint arXiv:2009.08366 (2020)."},{"key":"e_1_3_2_1_12_1","unstructured":"Dan Hendrycks Steven Basart Saurav Kadavath Mantas Mazeika and Akul Arora. [n. d.]. Measuring Coding Challenge Competence With APPS. ([n. d.])."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.442"},{"key":"e_1_3_2_1_14_1","unstructured":"Huggingface. 2023. Accelerate. https:\/\/github.com\/huggingface\/accelerate"},{"key":"e_1_3_2_1_15_1","unstructured":"Huggingface. 2023. Huggingface Transformers. https:\/\/huggingface.co"},{"key":"e_1_3_2_1_16_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_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1192"},{"key":"e_1_3_2_1_18_1","volume-title":"Log Anomaly Detection Through GPT Log Anomaly Detection Through GPT-2 for Large Scale Systems. ZTE COMMUNICATIONS 21, 3","author":"Yuhe JI","year":"2023","unstructured":"Yuhe JI, Jing HAN, Yongxin ZHAO, Shenglin ZHANG, and Zican GONG. 2023. Log Anomaly Detection Through GPT Log Anomaly Detection Through GPT-2 for Large Scale Systems. ZTE COMMUNICATIONS 21, 3 (2023)."},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence (Proceedings of Machine Learning Research","volume":"63","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 (Proceedings of Machine Learning Research, Vol. 161), Cassio de Campos and Marloes H. Maathuis (Eds.). PMLR, 54--63. https:\/\/proceedings.mlr.press\/v161\/jiang21a.html"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380342"},{"key":"e_1_3_2_1_21_1","first-page":"21314","article-title":"Coderl: Mastering code generation through pretrained models and deep reinforcement learning","volume":"35","author":"Le Hung","year":"2022","unstructured":"Hung Le, Yue Wang, Akhilesh Deepak Gotmare, Silvio Savarese, and Steven Chu Hong Hoi. 2022. Coderl: Mastering code generation through pretrained models and deep reinforcement learning. Advances in Neural Information Processing Systems 35 (2022), 21314--21328.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.3115\/1220355.1220427"},{"key":"e_1_3_2_1_24_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_25_1","volume-title":"Shengyu Fu, and Shujie Liu.","author":"Lu Shuai","year":"2021","unstructured":"Shuai Lu, Daya Guo, Shuo Ren, Junjie Huang, Alexey Svyatkovskiy, Ambrosio Blanco, Colin B. Clement, Dawn Drain, Daxin Jiang, Duyu Tang, Ge Li, Lidong Zhou, Linjun Shou, Long Zhou, Michele Tufano, Ming Gong, Ming Zhou, Nan Duan, Neel Sundaresan, Shao Kun Deng, Shengyu Fu, and Shujie Liu. 2021. CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation. CoRR abs\/2102.04664 (2021)."},{"key":"e_1_3_2_1_26_1","volume-title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis. In The Eleventh International Conference on Learning Representations.","author":"Nijkamp Erik","year":"2022","unstructured":"Erik Nijkamp, Bo Pang, Hiroaki Hayashi, Lifu Tu, Huan Wang, Yingbo Zhou, Silvio Savarese, and Caiming Xiong. 2022. CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2015.36"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.170"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1105"},{"key":"e_1_3_2_1_30_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog 1 8 (2019) 9."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.5555\/3455716.3455856"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"e_1_3_2_1_33_1","volume-title":"Codebleu: a method for automatic evaluation of code synthesis. arXiv preprint arXiv:2009.10297","author":"Ren Shuo","year":"2020","unstructured":"Shuo Ren, Daya Guo, Shuai Lu, Long Zhou, Shujie Liu, Duyu Tang, Neel Sundaresan, Ming Zhou, Ambrosio Blanco, and Shuai Ma. 2020. Codebleu: a method for automatic evaluation of code synthesis. arXiv preprint arXiv:2009.10297 (2020)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017055"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6430"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3417058"},{"key":"e_1_3_2_1_38_1","unstructured":"Tree-Sitter. 2023. Tree-Sitter. https:\/\/tree-sitter.github.io\/tree-sitter"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340544"},{"key":"e_1_3_2_1_40_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","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. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_41_1","volume-title":"Syncobert: Syntax-guided multi-modal contrastive pre-training for code representation. arXiv preprint arXiv:2108.04556","author":"Wang Xin","year":"2021","unstructured":"Xin Wang, Yasheng Wang, Fei Mi, Pingyi Zhou, Yao Wan, Xiao Liu, Li Li, Hao Wu, Jin Liu, and Xin Jiang. 2021. Syncobert: Syntax-guided multi-modal contrastive pre-training for code representation. arXiv preprint arXiv:2108.04556 (2021)."},{"key":"e_1_3_2_1_42_1","volume-title":"Nghi DQ Bui, Junnan Li, and Steven CH Hoi.","author":"Wang Yue","year":"2023","unstructured":"Yue Wang, Hung Le, Akhilesh Deepak Gotmare, Nghi DQ Bui, Junnan Li, and Steven CH Hoi. 2023. Codet5+: Open code large language models for code understanding and generation. arXiv preprint arXiv:2305.07922 (2023)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3487570"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3196398.3196408"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1041"},{"key":"e_1_3_2_1_47_1","first-page":"7","article-title":"Auxiliary Fault Location on Commercial Equipment Based on Supervised Machine Learning","volume":"20","author":"Zhao Zipiao","year":"2022","unstructured":"Zipiao Zhao, Yongli Zhao, Boyuan Yan, and Dajiang Wang. 2022. Auxiliary Fault Location on Commercial Equipment Based on Supervised Machine Learning. ZTE Communications 20, S1 (2022), 7--15.","journal-title":"ZTE Communications"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3468544"},{"key":"e_1_3_2_1_49_1","volume-title":"Grape: Grammar-Preserving Rule Embedding.. In IJCAI. 4545--4551.","author":"Zhu Qihao","year":"2022","unstructured":"Qihao Zhu, Zeyu Sun, Wenjie Zhang, Yingfei Xiong, and Lu Zhang. 2022. Grape: Grammar-Preserving Rule Embedding.. In IJCAI. 4545--4551."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00126"}],"event":{"name":"ICSE '24: IEEE\/ACM 46th International Conference on Software Engineering","location":"Lisbon Portugal","acronym":"ICSE '24","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS","Faculty of Engineering of University of Porto"]},"container-title":["Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3597503.3639125","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3597503.3639125","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:49:12Z","timestamp":1750286952000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3597503.3639125"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,12]]},"references-count":50,"alternative-id":["10.1145\/3597503.3639125","10.1145\/3597503"],"URL":"https:\/\/doi.org\/10.1145\/3597503.3639125","relation":{},"subject":[],"published":{"date-parts":[[2024,4,12]]},"assertion":[{"value":"2024-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}