{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:49:18Z","timestamp":1772120958951,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T00:00:00Z","timestamp":1701302400000},"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":["62232003, 62102244, 62032004"],"award-info":[{"award-number":["62232003, 62102244, 62032004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CCF-Tencent Open Research Fund","award":["RAGR20220129"],"award-info":[{"award-number":["RAGR20220129"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,30]]},"DOI":"10.1145\/3611643.3616306","type":"proceedings-article","created":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T23:14:38Z","timestamp":1701386078000},"page":"363-374","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Self-Supervised Query Reformulation for Code Search"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8485-3577","authenticated-orcid":false,"given":"Yuetian","family":"Mao","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9162-9688","authenticated-orcid":false,"given":"Chengcheng","family":"Wan","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7945-9312","authenticated-orcid":false,"given":"Yuze","family":"Jiang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0529-6408","authenticated-orcid":false,"given":"Xiaodong","family":"Gu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2023,11,30]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"2001. Lucene. https:\/\/lucene.apache.org"},{"key":"e_1_3_2_2_2_1","unstructured":"2006. Apache Solr. https:\/\/solr.apache.org"},{"key":"e_1_3_2_2_3_1","unstructured":"2012. Index Tank. https:\/\/github.com\/LinkedInAttic\/indextank-engine"},{"key":"e_1_3_2_2_4_1","unstructured":"2019. CodeSearchNet.. https:\/\/github.com\/github\/CodeSearchNet"},{"key":"e_1_3_2_2_5_1","unstructured":"2019. PyTorch Lightning. https:\/\/www.pytorchlightning.ai"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3359591.3359735"},{"key":"e_1_3_2_2_7_1","volume-title":"NeurIPS 2020","author":"Brown Tom B.","year":"2020","unstructured":"Tom B. Brown, Benjamin Mann, Nick Ryder, and et. al. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems 33, NeurIPS 2020, December 6-12, 2020."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00116"},{"key":"e_1_3_2_2_9_1","volume-title":"Cross-Domain Deep Code Search with Meta Learning. In 44th IEEE\/ACM 44th International Conference on Software Engineering, ICSE 2022","author":"Chai Yitian","year":"2022","unstructured":"Yitian Chai, Hongyu Zhang, Beijun Shen, and Xiaodong Gu. 2022. Cross-Domain Deep Code Search with Meta Learning. In 44th IEEE\/ACM 44th International Conference on Software Engineering, ICSE 2022, Pittsburgh, PA, USA, May 25-27, 2022. ACM, 487\u2013498."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450127"},{"key":"e_1_3_2_2_11_1","unstructured":"R. C. Cornea and N. B. Weininger. 2014. Providing autocomplete suggestions."},{"key":"e_1_3_2_2_12_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Conference of the North American","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 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT, June 2-7, 2019, Volume 1. 4171\u20134186."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/SANER53432.2022.00028"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_3_2_2_15_1","volume-title":"Elasticsearch: the definitive guide: a distributed real-time search and analytics engine. O\u2019Reilly Media","author":"Gormley Clinton","unstructured":"Clinton Gormley and Zachary Tong. 2015. Elasticsearch: the definitive guide: a distributed real-time search and analytics engine. O\u2019Reilly Media, Inc.."},{"key":"e_1_3_2_2_16_1","volume-title":"Deep Code Search. In IEEE\/ACM 40th International Conference on Software Engineering, ICSE 2018. 933\u2013944","author":"Gu Xiaodong","year":"2018","unstructured":"Xiaodong Gu, Hongyu Zhang, and Sunghun Kim. 2018. Deep Code Search. In IEEE\/ACM 40th International Conference on Software Engineering, ICSE 2018. 933\u2013944."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524610.3527886"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2013.6606630"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2009.5070524"},{"key":"e_1_3_2_2_20_1","volume-title":"MSR","author":"Howard Matthew J","year":"2013","unstructured":"Matthew J Howard, Samir Gupta, Lori Pollock, and K Vijay-Shanker. 2013. Automatically mining software-based, semantically-similar words from comment-code mappings. In 10th working conference on mining software repositories, MSR 2013. 377\u2013386."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1645953.1645966"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0218194017400137"},{"key":"e_1_3_2_2_23_1","unstructured":"HuggingFace. 2022. T5-base model checkpoint. https:\/\/huggingface.co\/t5-base"},{"key":"e_1_3_2_2_24_1","volume-title":"Compressed sensing and its applications","author":"Jakubovitz Daniel","unstructured":"Daniel Jakubovitz, Raja Giryes, and Miguel RD Rodrigues. 2019. Generalization error in deep learning. In Compressed sensing and its applications. Springer, 153\u2013193."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/1568763.1568772"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2015.01.023"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00407"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2006.116"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.2307\/2983064"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME.2018.00048"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498516"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549160"},{"key":"e_1_3_2_2_33_1","volume-title":"Self-supervised learning: Generative or contrastive","author":"Liu Xiao","year":"2021","unstructured":"Xiao Liu, Fanjin Zhang, Zhenyu Hou, Li Mian, Zhaoyu Wang, Jing Zhang, and Jie Tang. 2021. Self-supervised learning: Generative or contrastive. IEEE transactions on Knowledge and data engineering, 35, 1 (2021), 857\u2013876."},{"key":"e_1_3_2_2_34_1","volume-title":"22nd IEEE International Conference on Software Analysis, Evolution, and Reengineering, SANER 2015","author":"Lu Meili","year":"2015","unstructured":"Meili Lu, Xiaobing Sun, Shaowei Wang, David Lo, and Yucong Duan. 2015. Query expansion via WordNet for effective code search. In 22nd IEEE International Conference on Software Analysis, Evolution, and Reengineering, SANER 2015, March 2-6, 2015. 545\u2013549."},{"key":"e_1_3_2_2_35_1","volume-title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1).","author":"Lu Shuai","year":"2021","unstructured":"Shuai Lu, Daya Guo, Shuo Ren, Junjie Huang, Alexey Svyatkovskiy, Ambrosio Blanco, Colin Clement, Dawn Drain, Daxin Jiang, and Duyu Tang. 2021. CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2010.09.133"},{"key":"e_1_3_2_2_37_1","volume-title":"International Conference on Learning Representations.","author":"Madry Aleksander","year":"2018","unstructured":"Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. 2018. Towards Deep Learning Models Resistant to Adversarial Attacks. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_38_1","volume-title":"Meeting of the Association for Computational Linguistics.","author":"Miller G. A.","year":"1990","unstructured":"G. A. Miller. 1990. Introduction to WordNet: An Online Lexical Database. In Meeting of the Association for Computational Linguistics."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.552"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510096"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/SMART50582.2020.9337081"},{"key":"e_1_3_2_2_42_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. J. Mach. Learn. Res., 21 (2020), 140:1\u2013140:67.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_2_43_1","volume-title":"Roy","author":"Rahman Mohammad Masudur","year":"2018","unstructured":"Mohammad Masudur Rahman and Chanchal K. Roy. 2018. Effective Reformulation of Query for Code Search Using Crowdsourced Knowledge and Extra-Large Data Analytics. In 2018 IEEE International Conference on Software Maintenance and Evolution, ICSME 2018, September 23-29, 2018. 473\u2013484."},{"key":"e_1_3_2_2_44_1","unstructured":"Alfr\u00e9d R\u00e9nyi. 1961. On measures of entropy and information. In The fourth Berkeley symposium on mathematical statistics and probability. 1."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2786805.2786855"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCITECHN.2016.7860264"},{"key":"e_1_3_2_2_47_1","volume-title":"\u0141 ukasz Kaiser, and Illia Polosukhin","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141 ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, 30 (2017)."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-017-9514-4"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/SANER48275.2020.9054840"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-013-9264-x"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524610.3527894"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532017"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"crossref","unstructured":"Gustavo Zomer and Ana Frankenberg-Garcia. 2021. Beyond Grammatical Error Correction: Improving L1-influenced research writing in English using pre-trained encoder-decoder models. In Findings of the Association for Computational Linguistics (EMNLP). 2534\u20132540.","DOI":"10.18653\/v1\/2021.findings-emnlp.216"}],"event":{"name":"ESEC\/FSE '23: 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","location":"San Francisco CA USA","acronym":"ESEC\/FSE '23","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3611643.3616306","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3611643.3616306","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:36:04Z","timestamp":1750178164000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3611643.3616306"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,30]]},"references-count":54,"alternative-id":["10.1145\/3611643.3616306","10.1145\/3611643"],"URL":"https:\/\/doi.org\/10.1145\/3611643.3616306","relation":{},"subject":[],"published":{"date-parts":[[2023,11,30]]},"assertion":[{"value":"2023-11-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}