{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:36:44Z","timestamp":1742913404408,"version":"3.40.3"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031368882"},{"type":"electronic","value":"9783031368899"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-36889-9_27","type":"book-chapter","created":{"date-parts":[[2023,7,15]],"date-time":"2023-07-15T21:01:50Z","timestamp":1689454910000},"page":"402-417","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Finding Reusable Machine Learning Components to\u00a0Build Programming Language Processing Pipelines"],"prefix":"10.1007","author":[{"given":"Patrick","family":"Flynn","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tristan","family":"Vanderbruggen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunhua","family":"Liao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pei-Hung","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Murali","family":"Emani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xipeng","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,7,16]]},"reference":[{"key":"27_CR1","unstructured":"Google code jam. https:\/\/codingcompetitions.withgoogle.com\/codejam"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Ahmad, W., Chakraborty, S., Ray, B., Chang, K.W.: Unified pre-training for program understanding and generation. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 2655\u20132668. Association for Computational Linguistics, June 2021","DOI":"10.18653\/v1\/2021.naacl-main.211"},{"issue":"4","key":"27_CR3","first-page":"81","volume":"51","author":"M Allamanis","year":"2018","unstructured":"Allamanis, M., Barr, E.T., Devanbu, P., Sutton, C.: A survey of machine learning for big code and naturalness. ACM Comput. Surv. (CSUR) 51(4), 81 (2018)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Allamanis, M., Sutton, C.: Mining source code repositories at massive scale using language modeling. In: The 10th Working Conference on Mining Software Repositories, pp. 207\u2013216. IEEE (2013)","DOI":"10.1109\/MSR.2013.6624029"},{"issue":"5","key":"27_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3197978","volume":"51","author":"AH Ashouri","year":"2018","unstructured":"Ashouri, A.H., Killian, W., Cavazos, J., Palermo, G., Silvano, C.: A survey on compiler autotuning using machine learning. ACM Comput. Surv. 51(5), 1\u201342 (2018)","journal-title":"ACM Comput. Surv."},{"key":"27_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2021.103459","volume":"129","author":"J Bo\u017ei\u010d","year":"2021","unstructured":"Bo\u017ei\u010d, J., Tabernik, D., Sko\u010daj, D.: Mixed supervision for surface-defect detection: from weakly to fully supervised learning. Comput. Ind. 129, 103459 (2021)","journal-title":"Comput. Ind."},{"key":"27_CR7","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems, vol. 33, pp. 1877\u20131901 (2020)"},{"key":"27_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"27_CR9","unstructured":"Chami, I., Abu-El-Haija, S., Perozzi, B., R\u00e9, C., Murphy, K.: Machine learning on graphs: a model and comprehensive taxonomy (2020)"},{"key":"27_CR10","unstructured":"Chen, M., et al.: Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374 (2021)"},{"key":"27_CR11","unstructured":"Chen, X., Liu, C., Song, D.: Tree-to-tree neural networks for program translation. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, NIPS 2018, Red Hook, NY, USA, pp. 2552\u20132562. Curran Associates Inc. (2018)"},{"key":"27_CR12","unstructured":"Cummins, C., Fisches, Z., Ben-Nun, T., Hoefler, T., O\u2019Boyle, M., Leather, H.: ProGraML: a graph-based program representation for data flow analysis and compiler optimizations. In: Thirty-Eighth International Conference on Machine Learning (ICML) (2021)"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Cummins, C., Petoumenos, P., Wang, Z., Leather, H.: End-to-end deep learning of optimization heuristics. In: PACT. ACM (2017)","DOI":"10.1109\/PACT.2017.24"},{"key":"27_CR14","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"27_CR15","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16\\times 16$$ words: transformers for image recognition at scale (2020)"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Feng, Z., et al.: CodeBERT: a pre-trained model for programming and natural languages. arXiv preprint arXiv:2002.08155 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"27_CR17","unstructured":"Guo, D., et al.: GraphCodeBERT: pre-training code representations with data flow (2020)"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Hellendoorn, V.J., Bird, C., Barr, E.T., Allamanis, M.: Deep learning type inference. In: Proceedings of the 2018 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, ESEC\/FSE 2018, pp. 152\u2013162. Association for Computing Machinery, New York (2018)","DOI":"10.1145\/3236024.3236051"},{"issue":"3","key":"27_CR19","doi-asserted-by":"publisher","first-page":"2179","DOI":"10.1007\/s10664-019-09730-9","volume":"25","author":"X Hu","year":"2019","unstructured":"Hu, X., Li, G., Xia, X., Lo, D., Jin, Z.: Deep code comment generation with hybrid lexical and syntactical information. Empir. Softw. Eng. 25(3), 2179\u20132217 (2019). https:\/\/doi.org\/10.1007\/s10664-019-09730-9","journal-title":"Empir. Softw. Eng."},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Huang, J., et al.: CoSQA: 20,000+ web queries for code search and question answering (2021)","DOI":"10.18653\/v1\/2021.acl-long.442"},{"key":"27_CR21","unstructured":"Husain, H., Wu, H.H., Gazit, T., Allamanis, M., Brockschmidt, M.: CodeSearchNet challenge: evaluating the state of semantic code search (2019)"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Iyer, S., Konstas, I., Cheung, A., Zettlemoyer, L.: Mapping language to code in programmatic context (2018)","DOI":"10.18653\/v1\/D18-1192"},{"key":"27_CR23","doi-asserted-by":"crossref","unstructured":"Jain, P., Jain, A., Zhang, T., Abbeel, P., Gonzalez, J.E., Stoica, I.: Contrastive code representation learning. arXiv preprint arXiv:2007.04973 (2020)","DOI":"10.18653\/v1\/2021.emnlp-main.482"},{"key":"27_CR24","unstructured":"Jiang, X., Zheng, Z., Lyu, C., Li, L., Lyu, L.: TreeBERT: a tree-based pre-trained model for programming language. In: de Campos, C., Maathuis, M.H. (eds.) Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence. Proceedings of Machine Learning Research, vol. 161, pp. 54\u201363. PMLR, 27\u201330 July 2021"},{"key":"27_CR25","doi-asserted-by":"crossref","unstructured":"Just, R., Jalali, D., Ernst, M.D.: Defects4J: a database of existing faults to enable controlled testing studies for Java programs. In: Proceedings of the 2014 International Symposium on Software Testing and Analysis, ISSTA 2014, pp. 437\u2013440. Association for Computing Machinery, New York (2014)","DOI":"10.1145\/2610384.2628055"},{"key":"27_CR26","doi-asserted-by":"crossref","unstructured":"Kalyan, K.S., Rajasekharan, A., Sangeetha, S.: AMMUS: a survey of transformer-based pretrained models in natural language processing (2021)","DOI":"10.1016\/j.jbi.2021.103982"},{"key":"27_CR27","unstructured":"Kanade, A., Maniatis, P., Balakrishnan, G., Shi, K.: Learning and evaluating contextual embedding of source code (2020)"},{"key":"27_CR28","unstructured":"Kim, Y.J., et al.: Scalable and efficient MoE training for multitask multilingual models, September 2021"},{"key":"27_CR29","unstructured":"Koroteev, M.: BERT: a review of applications in natural language processing and understanding. arXiv preprint arXiv:2103.11943 (2021)"},{"key":"27_CR30","unstructured":"Lachaux, M.A., Roziere, B., Chanussot, L., Lample, G.: Unsupervised translation of programming languages (2020)"},{"key":"27_CR31","unstructured":"Li, Y., et al.: Competition-level code generation with AlphaCode. arXiv preprint arXiv:2203.07814 (2022)"},{"key":"27_CR32","doi-asserted-by":"crossref","unstructured":"Liao, C., Lin, P.H., Asplund, J., Schordan, M., Karlin, I.: DataRaceBench: a benchmark suite for systematic evaluation of data race detection tools. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201314 (2017)","DOI":"10.1145\/3126908.3126958"},{"key":"27_CR33","unstructured":"Lu, S., et al.: CodeXGLUE: a machine learning benchmark dataset for code understanding and generation. CoRR abs\/2102.04664 (2021)"},{"issue":"5","key":"27_CR34","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1109\/MM.2020.3012883","volume":"40","author":"M Maas","year":"2020","unstructured":"Maas, M.: A taxonomy of ML for systems problems. IEEE Micro 40(5), 8\u201316 (2020)","journal-title":"IEEE Micro"},{"key":"27_CR35","doi-asserted-by":"crossref","unstructured":"Mou, L., Li, G., Zhang, L., Wang, T., Jin, Z.: Convolutional neural networks over tree structures for programming language processing. In: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, pp. 1287\u20131293 (2016)","DOI":"10.1609\/aaai.v30i1.10139"},{"key":"27_CR36","doi-asserted-by":"crossref","unstructured":"Nguyen, A.T., Nguyen, T.T., Nguyen, T.N.: Divide-and-conquer approach for multi-phase statistical migration for source code (t). In: 2015 30th IEEE\/ACM International Conference on Automated Software Engineering (ASE), pp. 585\u2013596 (2015)","DOI":"10.1109\/ASE.2015.74"},{"key":"27_CR37","doi-asserted-by":"crossref","unstructured":"Phan, L., et al.: CoTexT: multi-task learning with code-text transformer. arXiv preprint arXiv:2105.08645 (2021)","DOI":"10.18653\/v1\/2021.nlp4prog-1.5"},{"key":"27_CR38","unstructured":"Puri, R., et al.: CodeNet: a large-scale AI for code dataset for learning a diversity of coding tasks (2021)"},{"key":"27_CR39","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et al.: Improving language understanding by generative pre-training (2018)"},{"issue":"10","key":"27_CR40","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1145\/3022671.2984041","volume":"51","author":"V Raychev","year":"2016","unstructured":"Raychev, V., Bielik, P., Vechev, M.: Probabilistic model for code with decision trees. SIGPLAN Not. 51(10), 731\u2013747 (2016)","journal-title":"SIGPLAN Not."},{"issue":"6","key":"27_CR41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s42979-021-00815-110.1007\/s42979-021-00815-1","volume":"2","author":"IH Sarker","year":"2021","unstructured":"Sarker, I.H.: Deep learning: a comprehensive overview on techniques, taxonomy, applications and research directions. SN Comput. Sci. 2(6), 1\u201320 (2021). https:\/\/doi.org\/10.1007\/s42979-021-00815-110.1007\/s42979-021-00815-1","journal-title":"SN Comput. Sci."},{"key":"27_CR42","doi-asserted-by":"crossref","unstructured":"Svajlenko, J., Islam, J.F., Keivanloo, I., Roy, C.K., Mia, M.M.: Towards a big data curated benchmark of inter-project code clones. In: 2014 IEEE International Conference on Software Maintenance and Evolution, pp. 476\u2013480 (2014)","DOI":"10.1109\/ICSME.2014.77"},{"issue":"4","key":"27_CR43","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3340544","volume":"28","author":"M Tufano","year":"2019","unstructured":"Tufano, M., Watson, C., Bavota, G., Penta, M.D., White, M., Poshyvanyk, D.: An empirical study on learning bug-fixing patches in the wild via neural machine translation. ACM Trans. Softw. Eng. Methodol. 28(4), 1\u201329 (2019)","journal-title":"ACM Trans. Softw. Eng. Methodol."},{"key":"27_CR44","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"27_CR45","unstructured":"Wang, X., et al.: SynCoBERT: syntax-guided multi-modal contrastive pre-training for code representation (2021)"},{"key":"27_CR46","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: CODE-MVP: learning to represent source code from multiple views with contrastive pre-training (2022)","DOI":"10.18653\/v1\/2022.findings-naacl.80"},{"key":"27_CR47","doi-asserted-by":"publisher","unstructured":"Wang, Y., Wang, W., Joty, S., Hoi, S.C.: Code T5: identifier-aware unified pre-trained encoder-decoder models for code understanding and generation. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Punta Cana, Dominican Republic, pp. 8696\u20138708. Association for Computational Linguistics, November 2021. https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.685","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"key":"27_CR48","doi-asserted-by":"crossref","unstructured":"Yin, P., Deng, B., Chen, E., Vasilescu, B., Neubig, G.: Learning to mine aligned code and natural language pairs from stack overflow. In: International Conference on Mining Software Repositories, MSR, pp. 476\u2013486. ACM (2018)","DOI":"10.1145\/3196398.3196408"},{"key":"27_CR49","unstructured":"Yu, J., et al.: Scaling autoregressive models for content-rich text-to-image generation (2022)"},{"key":"27_CR50","unstructured":"Zhou, Y., Liu, S., Siow, J., Du, X., Liu, Y.: Devign: effective vulnerability identification by learning comprehensive program semantics via graph neural networks (2019)"}],"container-title":["Lecture Notes in Computer Science","Software Architecture. ECSA 2022 Tracks and Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-36889-9_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,15]],"date-time":"2023-07-15T21:04:40Z","timestamp":1689455080000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-36889-9_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031368882","9783031368899"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-36889-9_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"16 July 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECSA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Software Architecture","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecsa2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conf.researchr.org\/home\/ecsa-2022","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"61","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"26","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"43% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2 tutorial papers","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}