{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T00:39:21Z","timestamp":1790987961246,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":58,"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":[{"name":"National Natural Science Foundation of China","award":["61690203, 61872373, 62032019, U1936213"],"award-info":[{"award-number":["61690203, 61872373, 62032019, U1936213"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,5,21]]},"DOI":"10.1145\/3510003.3510062","type":"proceedings-article","created":{"date-parts":[[2022,7,5]],"date-time":"2022-07-05T18:42:59Z","timestamp":1657046579000},"page":"287-298","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":71,"title":["Bridging pre-trained models and downstream tasks for source code understanding"],"prefix":"10.1145","author":[{"given":"Deze","family":"Wang","sequence":"first","affiliation":[{"name":"National University of Defense Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhouyang","family":"Jia","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanshan","family":"Li","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Yu","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun","family":"Xiong","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Dong","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangke","family":"Liao","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,7,5]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n.d.]. Clang: a C language family frontend for LLVM. https:\/\/clang.llvm.org\/"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Wasi Uddin Ahmad Saikat Chakraborty Baishakhi Ray and Kai-Wei Chang. 2021. Unified Pre-training for Program Understanding and Generation. In NAACL.","DOI":"10.18653\/v1\/2021.naacl-main.211"},{"key":"e_1_3_2_1_3_1","volume-title":"Compilers: Principles, Techniques, and Tools","author":"Aho A.","year":"2006","unstructured":"A. Aho, M. Lam, R. Sethi, and J. Ullman. 2006. Compilers: Principles, Techniques, and Tools (2nd Edition).","edition":"2"},{"key":"e_1_3_2_1_4_1","volume-title":"ICML '09","author":"Bengio Yoshua","unstructured":"Yoshua Bengio, J. Louradour, Ronan Collobert, and J. Weston. 2009. Curriculum learning. In ICML '09."},{"key":"e_1_3_2_1_5_1","volume-title":"Language Models are Few-Shot Learners. ArXiv abs\/2005.14165","author":"Brown Tom B.","year":"2020","unstructured":"Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, J. Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, T. Henighan, R. Child, A. Ramesh, Daniel M. Ziegler, Jeff Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. ArXiv abs\/2005.14165 (2020)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462840"},{"key":"e_1_3_2_1_7_1","volume-title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. ArXiv abs\/1406.1078","author":"Cho Kyunghyun","year":"2014","unstructured":"Kyunghyun Cho, B. V. Merrienboer, \u00c7aglar Gul\u00e7ehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. ArXiv abs\/1406.1078 (2014)."},{"key":"e_1_3_2_1_8_1","volume-title":"Manning","author":"Clark Kevin","year":"2020","unstructured":"Kevin Clark, Minh-Thang Luong, Quoc V. Le, and Christopher D. Manning. 2020. ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators. ArXiv abs\/2003.10555 (2020)."},{"key":"e_1_3_2_1_9_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT.","author":"Devlin J.","year":"2019","unstructured":"J. Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0277(93)90058-4"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Zhangyin Feng Daya Guo Duyu Tang Nan Duan X. Feng Ming Gong Linjun Shou Bing Qin Ting Liu Daxin Jiang and M. Zhou. 2020. CodeBERT: A Pre-Trained Model for Programming and Natural Languages. ArXiv abs\/2002.08155 (2020).","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2563981"},{"key":"e_1_3_2_1_13_1","unstructured":"Daya Guo Shuo Ren Shuai Lu Zhangyin Feng Duyu Tang Shujie Liu Long Zhou Nan Duan Jian Yin Daxin Jiang and M. Zhou. 2021. GraphCodeBERT: Pre-training Code Representations with Data Flow. ArXiv abs\/2009.08366 (2021)."},{"key":"e_1_3_2_1_14_1","volume-title":"CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images. ArXiv abs\/1808.01097","author":"Guo S.","year":"2018","unstructured":"S. Guo, Weilin Huang, H. Zhang, Chenfan Zhuang, Dengke Dong, M. Scott, and Dinglong Huang. 2018. CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images. ArXiv abs\/1808.01097 (2018)."},{"key":"e_1_3_2_1_15_1","unstructured":"Guy Hacohen and D. Weinshall. 2019. On The Power of Curriculum Learning in Training Deep Networks. ArXiv abs\/1904.03626 (2019)."},{"key":"e_1_3_2_1_16_1","volume-title":"CodeSearchNet Challenge: Evaluating the State of Semantic Code Search. ArXiv abs\/1909.09436","author":"Husain H.","year":"2019","unstructured":"H. Husain, Ho-Hsiang Wu, Tiferet Gazit, Miltiadis Allamanis, and Marc Brockschmidt. 2019. CodeSearchNet Challenge: Evaluating the State of Semantic Code Search. ArXiv abs\/1909.09436 (2019)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Paras Jain Ajay Jain Tianjun Zhang P. Abbeel J. Gonzalez and I. Stoica. 2020. Contrastive Code Representation Learning. ArXiv abs\/2007.04973 (2020).","DOI":"10.18653\/v1\/2021.emnlp-main.482"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654918"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Yoon Kim. 2014. Convolutional Neural Networks for Sentence Classification. In EMNLP.","DOI":"10.3115\/v1\/D14-1181"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Tom Kocmi and Ondrej Bojar. 2017. Curriculum Learning and Minibatch Bucketing in Neural Machine Translation. In RANLP.","DOI":"10.26615\/978-954-452-049-6_050"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2008.11.014"},{"key":"e_1_3_2_1_23_1","volume-title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. ArXiv abs\/1910.13461","author":"Lewis M.","year":"2020","unstructured":"M. Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. 2020. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. ArXiv abs\/1910.13461 (2020)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Cao Liu Shizhu He Kang Liu and Jun Zhao. 2018. Curriculum Learning for Natural Answer Generation. In IJCAI.","DOI":"10.24963\/ijcai.2018\/587"},{"key":"e_1_3_2_1_25_1","volume-title":"A Systematic Survey of Prompting Methods in Natural Language Processing. ArXiv abs\/2107.13586","author":"Liu Pengfei","year":"2021","unstructured":"Pengfei Liu, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, and Graham Neubig. 2021. Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing. ArXiv abs\/2107.13586 (2021)."},{"key":"e_1_3_2_1_26_1","volume-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach. ArXiv abs\/1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, M. Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. ArXiv abs\/1907.11692 (2019)."},{"key":"e_1_3_2_1_27_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 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. ArXiv abs\/2102.04664 (2021)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00041"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2934906"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Nikita Moshkov Botond Mathe Attila Kert\u00e9sz-Farkas R\u00e9ka Hollandi and P. Horv\u00e1th. 2020. Test-time augmentation for deep learning-based cell segmentation on microscopy images. Scientific Reports 10 (2020).","DOI":"10.1038\/s41598-020-61808-3"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Lili Mou Ge Li L. Zhang T. Wang and Zhi Jin. 2016. Convolutional Neural Networks over Tree Structures for Programming Language Processing. In AAAI.","DOI":"10.1609\/aaai.v30i1.10139"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-45439-5_46"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Emmanouil Antonios Platanios Otilia Stretcu Graham Neubig B. P\u00f3czos and Tom Michael Mitchell. 2019. Competence-based Curriculum Learning for Neural Machine Translation. In NAACL-HLT.","DOI":"10.18653\/v1\/N19-1119"},{"key":"e_1_3_2_1_34_1","volume-title":"USENIX Security Symposium.","author":"Quiring Erwin","unstructured":"Erwin Quiring, A. Maier, and K. Rieck. 2019. Misleading Authorship Attribution of Source Code using Adversarial Learning. In USENIX Security Symposium."},{"key":"e_1_3_2_1_35_1","unstructured":"Md Rafiqul Islam Rabin Nghi D. Q. Bui Yijun Yu Lingxiao Jiang and M. A. Alipour. 2020. On the Generalizability of Neural Program Analyzers with respect to Semantic-Preserving Program Transformations. ArXiv abs\/2008.01566 (2020)."},{"key":"e_1_3_2_1_36_1","volume-title":"Liu","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam M. Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, W. Li, and Peter J. Liu. 2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. ArXiv abs\/1910.10683 (2020)."},{"key":"e_1_3_2_1_37_1","unstructured":"Goutham Ramakrishnan Jordan Henkel Zi Wang Aws Albarghouthi S. Jha and T. Reps. 2020. Semantic Robustness of Models of Source Code. ArXiv abs\/2002.03043 (2020)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0010-0277(99)00031-1"},{"key":"e_1_3_2_1_39_1","unstructured":"SantiagoMunz. 2021. Semantic Preserving Auto Transformation. https:\/\/github.com\/SantiagoMunz\/SPAT"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Imran A. Sheikh I. Illina D. Fohr and G. Linar\u00e8s. 2016. Learning Word Importance with the Neural Bag-of-Words Model. In Rep4NLP@ACL.","DOI":"10.18653\/v1\/W16-1626"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"e_1_3_2_1_42_1","volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR abs\/1409.1556","author":"Simonyan K.","year":"2015","unstructured":"K. Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. CoRR abs\/1409.1556 (2015)."},{"key":"e_1_3_2_1_43_1","volume-title":"Nationwide introduction of a new competency framework for undergraduate medical curricula: a collaborative approach. Swiss medical weekly 150","author":"Sohrmann M.","year":"2020","unstructured":"M. Sohrmann, C. Berendonk, M. Nendaz, R. Bonvin, and Swiss Working Group For Profiles Implementation. 2020. Nationwide introduction of a new competency framework for undergraduate medical curricula: a collaborative approach. Swiss medical weekly 150 (2020), w20201."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670313"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME.2014.77"},{"key":"e_1_3_2_1_46_1","volume-title":"Jie Fu, Minh C. Phan, Xingdi Yuan, J. Rao, S. C. Hui, and A. Zhang.","author":"Tay Yi","year":"2019","unstructured":"Yi Tay, Shuohang Wang, Anh Tuan Luu, Jie Fu, Minh C. Phan, Xingdi Yuan, J. Rao, S. C. Hui, and A. Zhang. 2019. Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives. ArXiv abs\/1905.10847 (2019)."},{"key":"e_1_3_2_1_47_1","volume-title":"Attention is All you Need. ArXiv abs\/1706.03762","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam M. Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. ArXiv abs\/1706.03762 (2017)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.01.103"},{"key":"e_1_3_2_1_49_1","volume-title":"Detecting Code Clones with Graph Neural Network and Flow-Augmented Abstract Syntax Tree. 2020 IEEE 27th International Conference on Software Analysis, Evolution and Reengineering (SANER)","author":"Wang Wenhan","year":"2020","unstructured":"Wenhan Wang, Ge Li, Bo Ma, Xin Xia, and Zhi Jin. 2020. Detecting Code Clones with Graph Neural Network and Flow-Augmented Abstract Syntax Tree. 2020 IEEE 27th International Conference on Software Analysis, Evolution and Reengineering (SANER) (2020), 261--271."},{"key":"e_1_3_2_1_50_1","unstructured":"Huihui Wei and Ming Li. 2017. Supervised Deep Features for Software Functional Clone Detection by Exploiting Lexical and Syntactical Information in Source Code. In IJCAI."},{"key":"e_1_3_2_1_51_1","volume-title":"Proceedings of machine learning research 116","author":"Wei Jerry W.","year":"2019","unstructured":"Jerry W. Wei, A. Suriawinata, L. Vaickus, Bing Ren, Xiaoying Liu, Jason Wei, and S. Hassanpour. 2019. Generative Image Translation for Data Augmentation in Colorectal Histopathology Images. Proceedings of machine learning research 116 (2019), 10--24."},{"key":"e_1_3_2_1_52_1","unstructured":"Benfeng Xu L. Zhang Zhendong Mao Q. Wang Hongtao Xie and Yongdong Zhang. 2020. Curriculum Learning for Natural Language Understanding. In ACL."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3428230"},{"key":"e_1_3_2_1_54_1","volume-title":"Neural Detection of Semantic Code Clones Via Tree-Based Convolution. 2019 IEEE\/ACM 27th International Conference on Program Comprehension (ICPC)","author":"Yu Hao","year":"2019","unstructured":"Hao Yu, Wing Lam, Long Chen, Ge Li, Tao Xie, and Qianxiang Wang. 2019. Neural Detection of Semantic Code Clones Via Tree-Based Convolution. 2019 IEEE\/ACM 27th International Conference on Program Comprehension (ICPC) (2019), 70--80."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"crossref","unstructured":"Huangzhao Zhang Z. Li Ge Li L. Ma Yang Liu and Zhi Jin. 2020. Generating Adversarial Examples for Holding Robustness of Source Code Processing Models. In AAAI.","DOI":"10.1609\/aaai.v34i01.5469"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00086"},{"key":"e_1_3_2_1_57_1","volume-title":"An Empirical Exploration of Curriculum Learning for Neural Machine Translation. ArXiv abs\/1811.00739","author":"Zhang Xuan","year":"2018","unstructured":"Xuan Zhang, Manish Kumar, Huda Khayrallah, Kenton Murray, Jeremy Gwinnup, Marianna J. Martindale, P. McNamee, Kevin Duh, and Marine Carpuat. 2018. An Empirical Exploration of Curriculum Learning for Neural Machine Translation. ArXiv abs\/1811.00739 (2018)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"crossref","unstructured":"Zhun Zhong L. Zheng Guoliang Kang Shaozi Li and Y. Yang. 2020. Random Erasing Data Augmentation. In AAAI.","DOI":"10.1609\/aaai.v34i07.7000"}],"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\/3510003.3510062","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3510003.3510062","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:12:04Z","timestamp":1750176724000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3510003.3510062"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,21]]},"references-count":58,"alternative-id":["10.1145\/3510003.3510062","10.1145\/3510003"],"URL":"https:\/\/doi.org\/10.1145\/3510003.3510062","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"}}]}}