{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T05:34:44Z","timestamp":1736314484012,"version":"3.32.0"},"reference-count":66,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T00:00:00Z","timestamp":1732060800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T00:00:00Z","timestamp":1732060800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Singapore Data Science Consortium","award":["SDSC-2020-001"]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Empir Software Eng"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s10664-024-10576-z","type":"journal-article","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T02:44:58Z","timestamp":1732070698000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PTM4Tag+: Tag recommendation of stack overflow posts with pre-trained models"],"prefix":"10.1007","volume":"30","author":[{"given":"Junda","family":"He","sequence":"first","affiliation":[]},{"given":"Bowen","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Zhou","family":"Yang","sequence":"additional","affiliation":[]},{"given":"DongGyun","family":"Han","sequence":"additional","affiliation":[]},{"given":"Chengran","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Jiakun","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Zhipeng","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"David","family":"Lo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,20]]},"reference":[{"key":"10576_CR1","doi-asserted-by":"crossref","unstructured":"Adoma AF, Henry NM, Chen W (2020) Comparative analyses of bert, roberta, distilbert, and xlnet for text-based emotion recognition. In: 2020 17th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP), IEEE, pp 117\u2013121","DOI":"10.1109\/ICCWAMTIP51612.2020.9317379"},{"key":"10576_CR2","doi-asserted-by":"publisher","unstructured":"Ahmad WU, Chakraborty S, Ray B, Chang K (2021) Unified pre-training for program understanding and generation. In: Toutanova K, Rumshisky A, Zettlemoyer L, Hakkani-T\u00fcr D, Beltagy I, Bethard S, Cotterell R, Chakraborty T, Zhou Y (eds) Proceedings of the 2021 conference of the North American chapter of the association for computational linguistics: human language technologies, NAACL-HLT 2021, Online, June 6-11, 2021, Association for Computational Linguistics, pp 2655\u20132668. https:\/\/doi.org\/10.18653\/v1\/2021.naacl-main.211","DOI":"10.18653\/v1\/2021.naacl-main.211"},{"key":"10576_CR3","doi-asserted-by":"publisher","unstructured":"Baltes S, Dumani L, Treude C, Diehl S (2018) Sotorrent: reconstructing and analyzing the evolution of stack overflow posts. In: Zaidman A, Kamei Y, Hill E (eds) Proceedings of the 15th international conference on Mining Software Repositories, MSR 2018, Gothenburg, Sweden, May 28-29, 2018, ACM, pp 319\u201333. https:\/\/doi.org\/10.1145\/3196398.3196430","DOI":"10.1145\/3196398.3196430"},{"issue":"3","key":"10576_CR4","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1007\/s10664-012-9231-y","volume":"19","author":"A Barua","year":"2014","unstructured":"Barua A, Thomas SW, Hassan AE (2014) What are developers talking about? an analysis of topics and trends in stack overflow. Empir Softw Eng 19(3):619\u2013654","journal-title":"Empir Softw Eng"},{"key":"10576_CR5","doi-asserted-by":"crossref","unstructured":"Beltagy I, Lo K, Cohan A (2019) Scibert: a pretrained language model for scientific text. arXiv:1903.10676","DOI":"10.18653\/v1\/D19-1371"},{"key":"10576_CR6","doi-asserted-by":"publisher","unstructured":"Bowman SR, Angeli G, Potts C, Manning CD (2015) A large annotated corpus for learning natural language inference. In: Proceedings of the 2015 conference on empirical methods in natural language processing, Association for Computational Linguistics, Lisbon, Portugal, pp 632\u2013642. https:\/\/doi.org\/10.18653\/v1\/D15-1075https:\/\/aclanthology.org\/D15-1075","DOI":"10.18653\/v1\/D15-1075"},{"key":"10576_CR7","unstructured":"Buratti L, Pujar S, Bornea M, McCarley S, Zheng Y, Rossiello G, Morari A, Laredo J, Thost V, Zhuang Y, et\u00a0al. (2020) Exploring software naturalness through neural language models. arXiv:2006.12641"},{"issue":"3","key":"10576_CR8","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1037\/0033-2909.114.3.494","volume":"114","author":"N Cliff","year":"1993","unstructured":"Cliff N (1993) Dominance statistics: ordinal analyses to answer ordinal questions. Psychol Bull 114(3):494","journal-title":"Psychol Bull"},{"key":"10576_CR9","doi-asserted-by":"publisher","DOI":"10.4324\/9781315806730","volume-title":"Ordinal methods for behavioral data analysis","author":"N Cliff","year":"2014","unstructured":"Cliff N (2014) Ordinal methods for behavioral data analysis. Psychology Press"},{"key":"10576_CR10","unstructured":"Devlin J, Chang M, Lee K, Toutanova K (2018) BERT: pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805"},{"key":"10576_CR11","doi-asserted-by":"publisher","unstructured":"Feng Z, Guo D, Tang D, Duan N, Feng X, Gong M, Shou L, Qin B, Liu T, Jiang D, Zhou M (2020) CodeBERT: a pre-trained model for programming and natural languages. In: Findings of the association for computational linguistics: EMNLP 2020, Association for Computational Linguistics, Online, pp 1536\u20131547. https:\/\/doi.org\/10.18653\/v1\/2020.findings-emnlp.139https:\/\/aclanthology.org\/2020.findings-emnlp.139","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"issue":"1\u20132","key":"10576_CR12","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1093\/biomet\/52.1-2.203","volume":"52","author":"EA Gehan","year":"1965","unstructured":"Gehan EA (1965) A generalized wilcoxon test for comparing arbitrarily singly-censored samples. Biometrika 52(1\u20132):203\u2013224","journal-title":"Biometrika"},{"key":"10576_CR13","doi-asserted-by":"crossref","unstructured":"Giorgi J, Nitski O, Wang B, Bader G (2020) Declutr: deep contrastive learning for unsupervised textual representations. arXiv:2006.03659","DOI":"10.18653\/v1\/2021.acl-long.72"},{"key":"10576_CR14","unstructured":"Guo D, Ren S, Lu S, Feng Z, Tang D, Liu S, Zhou L, Duan N, Svyatkovskiy A, Fu S, Tufano M, Deng SK, Clement CB, Drain D, Sundaresan N, Yin J, Jiang D, Zhou M (2021) Graphcodebert: pre-training code representations with data flow. In: 9th International conference on learning representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021, OpenReview.net. https:\/\/openreview.net\/forum?id=jLoC4ez43PZ"},{"issue":"3","key":"10576_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3635711","volume":"33","author":"J He","year":"2024","unstructured":"He J, Zhou X, Xu B, Zhang T, Kim K, Yang Z, Thung F, Irsan IC, Lo D (2024) Representation learning for stack overflow posts: how far are we? ACM Trans Softw Eng Methodol 33(3):1\u201324","journal-title":"ACM Trans Softw Eng Methodol"},{"key":"10576_CR16","doi-asserted-by":"publisher","unstructured":"He J, Xu B, Yang Z, Han D, Yang C, Lo D (2022) Ptm4tag: sharpening tag recommendation of stack overflow posts with pre-trained models. In: Proceedings of the 30th IEEE\/ACM international conference on program comprehension, association for computing machinery, New York, NY, USA, ICPC \u201922, p 1-1. https:\/\/doi.org\/10.1145\/3524610.3527897","DOI":"10.1145\/3524610.3527897"},{"key":"10576_CR17","unstructured":"Hinton GE, Vinyals O, Dean J (2015) Distilling the knowledge in a neural network. arXiv:1503.02531"},{"key":"10576_CR18","unstructured":"Huang K, Altosaar J, Ranganath R (2020) Clinicalbert: modeling clinical notes and predicting hospital readmission. arXiv:1904.05342"},{"key":"10576_CR19","doi-asserted-by":"crossref","unstructured":"Huang J, Tang D, Shou L, Gong M, Xu K, Jiang D, Zhou M, Duan N (2021) Cosqa: 20,000+ web queries for code search and question answering. ArXiv:2105.13239","DOI":"10.18653\/v1\/2021.acl-long.442"},{"key":"10576_CR20","unstructured":"Huang Z, Xu W, Yu K (2015) Bidirectional lstm-crf models for sequence tagging. arXiv:1508.01991"},{"key":"10576_CR21","unstructured":"Husain H, Wu HH, Gazit T, Allamanis M, Brockschmidt M (2020) Codesearchnet challenge: evaluating the state of semantic code search. arXiv:1909.09436"},{"key":"10576_CR22","unstructured":"Jiang X, Zheng Z, Lyu C, Li L, Lyu L (2021) Treebert: a tree-based pre-trained model for programming language. In: de\u00a0Campos CP, Maathuis MH, Quaeghebeur E (eds) Proceedings of the thirty-seventh conference on uncertainty in artificial intelligence, UAI 2021, Virtual Event, 27-30 July 2021, AUAI Press, Proceedings of Machine Learning Research, vol 161, pp 54\u201363. https:\/\/proceedings.mlr.press\/v161\/jiang21a.html"},{"key":"10576_CR23","doi-asserted-by":"crossref","unstructured":"Jin D, Jin Z, Zhou JT, Szolovits P (2020) Is bert really robust? a strong baseline for natural language attack on text classification and entailment. Proceedings of the AAAI conference on artificial intelligence vol 34 pp 8018\u20138025","DOI":"10.1609\/aaai.v34i05.6311"},{"key":"10576_CR24","unstructured":"Lan T, Mao XL, Zhao Z, Wei W, Huang H (2020a) Self-attention comparison module for boosting performance on retrieval-based open-domain dialog systems. arXiv:2012.11357"},{"key":"10576_CR25","unstructured":"Lan Z, Chen M, Goodman S, Gimpel K, Sharma P, Soricut R (2020b) Albert: A lite bert for self-supervised learning of language representations. arXiv:1909.11942"},{"key":"10576_CR26","doi-asserted-by":"publisher","unstructured":"Lee J, Yoon W, Kim S, Kim D, Kim S, So CH, Kang J (2019) Biobert: a pre-trained biomedical language representation model for biomedical text mining. Bioinformati. https:\/\/doi.org\/10.1093\/bioinformatics\/btz682","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"10576_CR27","doi-asserted-by":"publisher","unstructured":"Lewis M, Liu Y, Goyal N, Ghazvininejad M, Mohamed A, Levy O, Stoyanov V, Zettlemoyer L (2020) BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Jurafsky D, Chai J, Schluter N, Tetreault JR (eds) Proceedings of the 58th annual meeting of the association for computational linguistics, ACL 2020, Online, July 5-10, 2020, Association for Computational Linguistics, pp 7871\u20137880. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.703","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"10576_CR28","doi-asserted-by":"publisher","first-page":"110783","DOI":"10.1016\/j.jss.2020.110783","volume":"170","author":"C Li","year":"2020","unstructured":"Li C, Xu L, Yan M, Lei Y (2020) Tagdc: a tag recommendation method for software information sites with a combination of deep learning and collaborative filtering. J Syst Softw 170:110783. https:\/\/doi.org\/10.1016\/j.jss.2020.110783","journal-title":"J Syst Softw"},{"key":"10576_CR29","doi-asserted-by":"crossref","unstructured":"Lin J, Liu Y, Zeng Q, Jiang M, Cleland-Huang J (2021) Traceability transformed: generating more accurate links with pre-trained bert models. In: 2021 IEEE\/ACM 43rd International Conference on Software Engineering (ICSE), IEEE, pp 324\u2013335","DOI":"10.1109\/ICSE43902.2021.00040"},{"key":"10576_CR30","doi-asserted-by":"publisher","unstructured":"Liu X, He P, Chen W, Gao J (2019a) Multi-task deep neural networks for natural language understanding. In: Korhonen A, Traum DR, M\u00e0rquez L (eds) Proceedings of the 57th conference of the association for computational linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, vol 1: Long Papers, Association for Computational Linguistics, pp 4487\u20134496. https:\/\/doi.org\/10.18653\/v1\/p19-1441","DOI":"10.18653\/v1\/p19-1441"},{"key":"10576_CR31","unstructured":"Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, Levy O, Lewis M, Zettlemoyer L, Stoyanov V (2019b) Roberta: a robustly optimized bert pretraining approach. arXiv:1907.11692"},{"key":"10576_CR32","doi-asserted-by":"publisher","unstructured":"Maity SK, Panigrahi A, Ghosh S, Banerjee A, Goyal P, Mukherjee A (2019) Deeptagrec: a content-cum-user based tag recommendation framework for stack overflow. In: Azzopardi L, Stein B, Fuhr N, Mayr P, Hauff C, Hiemstra D (eds) Advances in information retrieval - 41st European conference on IR research, ECIR 2019, Cologne, Germany, April 14-18, 2019, Proceedings, Part II, Springer, Lecture Notes in Computer Science, vol 11438, pp 125\u2013131. https:\/\/doi.org\/10.1007\/978-3-030-15719-7_16","DOI":"10.1007\/978-3-030-15719-7_16"},{"key":"10576_CR33","doi-asserted-by":"publisher","unstructured":"Mashhadi E, Hemmati H (2021) Applying codebert for automated program repair of java simple bugs. In: 2021 IEEE\/ACM 18th international conference on Mining Software Repositories (MSR), pp 505\u201350.https:\/\/doi.org\/10.1109\/MSR52588.2021.00063","DOI":"10.1109\/MSR52588.2021.00063"},{"key":"10576_CR34","doi-asserted-by":"publisher","unstructured":"Ni J, \u00c1brego GH, Constant N, Ma J, Hall KB, Cer D, Yang Y (2022) Sentence-t5: scalable sentence encoders from pre-trained text-to-text models. In: Muresan S, Nakov P, Villavicencio A (eds) Findings of the association for computational linguistics: ACL 2022, Dublin, Ireland, May 22-27, 2022, Association for Computational Linguistics, pp 1864\u20131874. https:\/\/doi.org\/10.18653\/v1\/2022.findings-acl.146","DOI":"10.18653\/v1\/2022.findings-acl.146"},{"key":"10576_CR35","doi-asserted-by":"publisher","unstructured":"Phan L, Tran H, Le D, Nguyen H, Annibal J, Peltekian A, Ye Y (2021) CoTexT: multi-task learning with code-text transformer. In: Proceedings of the 1st workshop on natural language processing for programming (NLP4Prog 2021), Association for Computational Linguistics, Online, pp 40\u201347. https:\/\/doi.org\/10.18653\/v1\/2021.nlp4prog-1.5","DOI":"10.18653\/v1\/2021.nlp4prog-1.5"},{"key":"10576_CR36","doi-asserted-by":"crossref","unstructured":"Qu C, Yang L, Qiu M, Croft WB, Zhang Y, Iyyer M (2019) Bert with history answer embedding for conversational question answering. In: Proceedings of the 42nd international ACM SIGIR conference on research and development in information retrieval, pp 1133\u20131136","DOI":"10.1145\/3331184.3331341"},{"key":"10576_CR37","unstructured":"Raffel C, Shazeer N, Roberts A, Lee K, Narang S, Matena M, Zhou Y, Li W, Liu PJ (2020) Exploring the limits of transfer learning with a unified text-to-text transformer. J Mach Learn Res 21:140:1\u2013140:67. http:\/\/jmlr.org\/papers\/v21\/20-074.html"},{"key":"10576_CR38","doi-asserted-by":"crossref","unstructured":"Reimers N, Gurevych I (2019) Sentence-bert: sentence embeddings using siamese bert-networks. arXiv:1908.10084","DOI":"10.18653\/v1\/D19-1410"},{"key":"10576_CR39","doi-asserted-by":"publisher","unstructured":"Rothe S, Narayan S, Severyn A (2020) Leveraging pre-trained checkpoints for sequence generation tasks. Trans Assoc Comput Linguist 8:264\u201328. https:\/\/doi.org\/10.1162\/tacl_a_00313https:\/\/aclanthology.org\/2020.tacl-1.18","DOI":"10.1162\/tacl_a_00313"},{"key":"10576_CR40","doi-asserted-by":"crossref","unstructured":"Sarfraz F, Arani E, Zonooz B (2021) Knowledge distillation beyond model compression. In: 2020 25th International Conference on Pattern Recognition (ICPR), IEEE, pp 6136\u20136143","DOI":"10.1109\/ICPR48806.2021.9413016"},{"key":"10576_CR41","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","volume":"61","author":"J Schmidhuber","year":"2015","unstructured":"Schmidhuber J (2015) Deep learning in neural networks: an overview. Neural Netw 61:85\u2013117","journal-title":"Neural Netw"},{"key":"10576_CR42","doi-asserted-by":"crossref","unstructured":"Shi J, Yang Z, He J, Xu B, Lo D (2022) Can identifier splitting improve open-vocabulary language model of code? In: 2022 IEEE international conference on software analysis, evolution and reengineering (SANER), IEEE","DOI":"10.1109\/SANER53432.2022.00130"},{"key":"10576_CR43","doi-asserted-by":"crossref","unstructured":"Shi J, Yang Z, Kang HJ, Xu B, He J, Lo D (2024) Greening large language models of code. In: Proceedings of the 46th international conference on software engineering: software engineering in society, pp 142\u2013153","DOI":"10.1145\/3639475.3640097"},{"key":"10576_CR44","doi-asserted-by":"publisher","unstructured":"Shi J, Yang Z, Xu B, Kang HJ, Lo D (2023) Compressing pre-trained models of code into 3 mb. In: Proceedings of the 37th IEEE\/ACM international conference on automated software engineering, Association for Computing Machinery, New York, NY, USA, ASE. https:\/\/doi.org\/10.1145\/3551349.3556964","DOI":"10.1145\/3551349.3556964"},{"key":"10576_CR45","doi-asserted-by":"crossref","unstructured":"Sun C, Qiu X, Xu Y, Huang X (2020) How to fine-tune bert for text classification? arXiv:1905.05583","DOI":"10.1007\/978-3-030-32381-3_16"},{"key":"10576_CR46","doi-asserted-by":"crossref","unstructured":"Svyatkovskiy A, Deng SK, Fu S, Sundaresan N (2020) Intellicode compose: code generation using transformer. arXiv:2005.08025","DOI":"10.1145\/3368089.3417058"},{"key":"10576_CR47","doi-asserted-by":"crossref","unstructured":"Tabassum J, Maddela M, Xu W, Ritter A (2020) Code and named entity recognition in stackoverflow. arXiv:2005.01634","DOI":"10.18653\/v1\/2020.acl-main.443"},{"key":"10576_CR48","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems, pp 5998\u20136008"},{"key":"10576_CR49","doi-asserted-by":"publisher","unstructured":"Von\u00a0der Mosel J, Trautsch A, Herbold S (2022) On the validity of pre-trained transformers for natural language processing in the software engineering domain. IEEE Trans Softw Eng 1\u20131. https:\/\/doi.org\/10.1109\/TSE.2022.3178469","DOI":"10.1109\/TSE.2022.3178469"},{"issue":"5","key":"10576_CR50","doi-asserted-by":"publisher","first-page":"1017","DOI":"10.1007\/s11390-015-1578-2","volume":"30","author":"XY Wang","year":"2015","unstructured":"Wang XY, Xia X, Lo D (2015) Tagcombine: recommending tags to contents in software information sites. J Comput Sci Technol 30(5):1017\u20131035","journal-title":"J Comput Sci Technol"},{"key":"10576_CR51","doi-asserted-by":"publisher","unstructured":"Wang S, Lo D, Vasilescu B, Serebrenik A (2014) Entagrec: an enhanced tag recommendation system for software information sites. In: 2014 IEEE international conference on software maintenance and evolution, pp 291\u2013300. https:\/\/doi.org\/10.1109\/ICSME.2014.51","DOI":"10.1109\/ICSME.2014.51"},{"key":"10576_CR52","doi-asserted-by":"crossref","unstructured":"Wang S, Lo D, Vasilescu B, Serebrenik A (2018) Entagrec ++: an enhanced tag recommendation system for software information sites. Empir Softw Eng 23","DOI":"10.1007\/s10664-017-9533-1"},{"key":"10576_CR53","doi-asserted-by":"publisher","unstructured":"Wang Y, Wang W, Joty SR, Hoi SCH (2021) Codet5: identifier-aware unified pre-trained encoder-decoder models for code understanding and generation. In: Moens M, Huang X, Specia L, Yih SW (eds) Proceedings of the 2021 conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event \/ Punta Cana, Dominican Republic, 7-11 November, 2021, Association for Computational Linguistics, pp 8696\u20138708. https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.685","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"key":"10576_CR54","doi-asserted-by":"crossref","unstructured":"Wang S, Xu Y, Fang Y, Liu Y, Sun S, Xu R, Zhu C, Zeng M (2022a) Training data is more valuable than you think: a simple and effective method by retrieving from training data. In: Proceedings of the 60th annual meeting of the association for computational linguistics (Volume 1: Long Papers), pp 3170\u20133179","DOI":"10.18653\/v1\/2022.acl-long.226"},{"key":"10576_CR55","doi-asserted-by":"crossref","unstructured":"Wang X, Zhou K, rong Wen J, Zhao WX (2022b) Towards unified conversational recommender systems via knowledge-enhanced prompt learning. Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining","DOI":"10.1145\/3534678.3539382"},{"key":"10576_CR56","doi-asserted-by":"publisher","unstructured":"Williams A, Nangia N, Bowman S (2018) A broad-coverage challenge corpus for sentence understanding through inference. In: Proceedings of the 2018 conference of the north american chapter of the association for computational linguistics: human language technologies, vol 1 (Long Papers), Association for Computational Linguistics, New Orleans, Louisiana, pp 1112\u2013112. https:\/\/doi.org\/10.18653\/v1\/N18-1101https:\/\/aclanthology.org\/N18-1101","DOI":"10.18653\/v1\/N18-1101"},{"key":"10576_CR57","doi-asserted-by":"crossref","unstructured":"Xia X, Lo D, Wang X, Zhou B (2013) Tag recommendation in software information sites. In: Proceedings of the 10th working conference on mining software repositories, IEEE Press, MSR \u201913, pp 287-296","DOI":"10.1109\/MSR.2013.6624040"},{"key":"10576_CR58","doi-asserted-by":"publisher","unstructured":"Xu B, Hoang T, Sharma A, Yang C, Xia X, Lo D (2021) Post2vec: learning distributed representations of stack overflow posts. IEEE Trans Softw Eng 1. https:\/\/doi.org\/10.1109\/TSE.2021.3093761","DOI":"10.1109\/TSE.2021.3093761"},{"key":"10576_CR59","doi-asserted-by":"crossref","unstructured":"Yang C, Xu B, Khan\u00a0Younus J, Uddin G, Han D, Yang Z, Lo D (2022) Aspect-based api review classification: how far can pre-trained transformer model go? In: 29th IEEE international conference on software analysis, evolution and reengineering(SANER), IEEE","DOI":"10.1109\/SANER53432.2022.00054"},{"key":"10576_CR60","doi-asserted-by":"crossref","unstructured":"Zhang T, Xu B, Thung F, Haryono SA, Lo D, Jiang L (2020) Sentiment analysis for software engineering: how far can pre-trained transformer models go? In: 2020 IEEE International Conference on Software Maintenance and Evolution (ICSME), IEEE, pp 70\u201380","DOI":"10.1109\/ICSME46990.2020.00017"},{"key":"10576_CR61","first-page":"272","volume-title":"2017 IEEE 24th International Conference on Software Analysis","author":"P Zhou","year":"2017","unstructured":"Zhou P, Liu J, Yang Z, Zhou G (2017) Scalable tag recommendation for software information sites. 2017 IEEE 24th International Conference on Software Analysis. Evolution and Reengineering (SANER), IEEE, pp 272\u2013282"},{"key":"10576_CR62","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.infsof.2019.01.002","volume":"109","author":"P Zhou","year":"2019","unstructured":"Zhou P, Liu J, Liu X, Yang Z, Grundy J (2019) Is deep learning better than traditional approaches in tag recommendation for software information sites? Inf Softw Technol 109:1\u201313. https:\/\/doi.org\/10.1016\/j.infsof.2019.01.002","journal-title":"Inf Softw Technol"},{"key":"10576_CR63","doi-asserted-by":"crossref","unstructured":"Zhou X, Han D, Lo D (2021) Assessing generalizability of codebert. In: 2021 IEEE International Conference on Software Maintenance and Evolution (ICSME), IEEE, pp 425\u2013436","DOI":"10.1109\/ICSME52107.2021.00044"},{"key":"10576_CR64","doi-asserted-by":"crossref","unstructured":"Zhou X, Kim K, Xu B, Han D, He J, Lo D (2023a) Generation-based code review automation: how far are we\u2019. In: 2023 IEEE\/ACM 31st International Conference on Program Comprehension (ICPC), IEEE, pp 215\u2013226","DOI":"10.1109\/ICPC58990.2023.00036"},{"key":"10576_CR65","doi-asserted-by":"crossref","unstructured":"Zhou X, Xu B, Han D, Yang Z, He J, Lo D (2023b) Ccbert: Self-supervised code change representation learning. In: 2023 IEEE International Conference on Software Maintenance and Evolution (ICSME), IEEE, pp 182\u2013193","DOI":"10.1109\/ICSME58846.2023.00028"},{"key":"10576_CR66","doi-asserted-by":"crossref","unstructured":"Zhu Y, Kiros R, Zemel R, Salakhutdinov R, Urtasun R, Torralba A, Fidler S (2015) Aligning books and movies: towards story-like visual explanations by watching movies and reading books. In: The IEEE International Conference on Computer Vision (ICCV)","DOI":"10.1109\/ICCV.2015.11"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-024-10576-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10664-024-10576-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-024-10576-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,7]],"date-time":"2025-01-07T14:14:26Z","timestamp":1736259266000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10664-024-10576-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,20]]},"references-count":66,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10576"],"URL":"https:\/\/doi.org\/10.1007\/s10664-024-10576-z","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"type":"print","value":"1382-3256"},{"type":"electronic","value":"1573-7616"}],"subject":[],"published":{"date-parts":[[2024,11,20]]},"assertion":[{"value":"10 October 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 November 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no Conflict of interest\/Conflict of interest to declare that are relevant to this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"28"}}