{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T06:47:56Z","timestamp":1773384476802,"version":"3.50.1"},"reference-count":61,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,3,17]],"date-time":"2022-03-17T00:00:00Z","timestamp":1647475200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,3,17]],"date-time":"2022-03-17T00:00:00Z","timestamp":1647475200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Empir Software Eng"],"published-print":{"date-parts":[[2022,5]]},"DOI":"10.1007\/s10664-022-10118-5","type":"journal-article","created":{"date-parts":[[2022,3,17]],"date-time":"2022-03-17T15:27:09Z","timestamp":1647530829000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["Can pre-trained code embeddings improve model performance? Revisiting the use of code embeddings in software engineering tasks"],"prefix":"10.1007","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0803-5609","authenticated-orcid":false,"given":"Zishuo","family":"Ding","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiyi","family":"Shang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tse-Hsun Peter","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,3,17]]},"reference":[{"key":"10118_CR1","doi-asserted-by":"publisher","unstructured":"Abuhamad M, AbuHmed T, Mohaisen A, Nyang D (2018) Large-scale and language-oblivious code authorship identification. In: Lie D, Mannan M, Backes M, Wang X (eds) Proceedings of the 2018 ACM SIGSAC conference on computer and communications security, CCS 2018, Toronto, ON, Canada, October 15\u201319, 2018. https:\/\/doi.org\/10.1145\/3243734.3243738. ACM, pp 101\u2013114","DOI":"10.1145\/3243734.3243738"},{"key":"10118_CR2","doi-asserted-by":"publisher","unstructured":"Allamanis M, Barr ET, Bird C, Sutton CA (2014) Learning natural coding conventions. In: Cheung S, Orso A, Storey MD (eds) Proceedings of the 22nd ACM SIGSOFT international symposium on foundations of software engineering, (FSE-22), Hong Kong, China, November 16\u201322, 2014. https:\/\/doi.org\/10.1145\/2635868.2635883. ACM, pp 281\u2013293","DOI":"10.1145\/2635868.2635883"},{"key":"10118_CR3","doi-asserted-by":"publisher","unstructured":"Allamanis M, Barr ET, Bird C, Sutton CA (2015) Suggesting accurate method and class names. In: Nitto ED, Harman M, Heymans P (eds) Proceedings of the 2015 10th joint meeting on foundations of software engineering, ESEC\/FSE 2015, Bergamo, Italy, August 30\u2013September 4, 2015. https:\/\/doi.org\/10.1145\/2786805.2786849. ACM, pp 38\u201349","DOI":"10.1145\/2786805.2786849"},{"key":"10118_CR4","unstructured":"Allamanis M, Peng H, Sutton CA (2016) A convolutional attention network for extreme summarization of source code. In: Balcan M, Weinberger KQ (eds) Proceedings of the 33nd international conference on machine learning, ICML 2016, New York City, NY, USA, June 19\u201324, 2016, JMLR.org, JMLR Workshop and Conference Proceedings. http:\/\/proceedings.mlr.press\/v48\/allamanis16.html, vol 48, pp 2091\u20132100"},{"key":"10118_CR5","unstructured":"Allamanis M, Brockschmidt M, Khademi M (2018) Learning to represent programs with graphs. In: 6th International conference on learning representations, ICLR 2018, Vancouver, BC, Canada, April 30\u2013May 3, 2018. Conference Track Proceedings, OpenReview.net. https:\/\/openreview.net\/forum?id=BJOFETxR-"},{"key":"10118_CR6","doi-asserted-by":"publisher","unstructured":"Alon U, Zilberstein M, Levy O, Yahav E (2018) A general path-based representation for predicting program properties. In: Foster JS, Grossman D (eds) Proceedings of the 39th ACM SIGPLAN conference on programming language design and implementation, PLDI 2018, Philadelphia, PA, USA, June 18\u201322, 2018. https:\/\/doi.org\/10.1145\/3192366.3192412. ACM, pp 404\u2013419","DOI":"10.1145\/3192366.3192412"},{"issue":"POPL","key":"10118_CR7","doi-asserted-by":"publisher","first-page":"40:1","DOI":"10.1145\/3290353","volume":"3","author":"U Alon","year":"2019","unstructured":"Alon U, Zilberstein M, Levy O, Yahav E (2019) code2vec: learning distributed representations of code. PACMPL 3(POPL):40:1\u201340:29. https:\/\/doi.org\/10.1145\/3290353","journal-title":"PACMPL"},{"key":"10118_CR8","doi-asserted-by":"publisher","unstructured":"Barbour L, Khomh F, Zou Y (2011) Late propagation in software clones. In: IEEE 27th international conference on software maintenance, ICSM 2011, Williamsburg, VA, USA, September 25\u201330, 2011. https:\/\/doi.org\/10.1109\/ICSM.2011.6080794. IEEE Computer Society, pp 273\u2013282","DOI":"10.1109\/ICSM.2011.6080794"},{"key":"10118_CR9","unstructured":"Bielik P, Raychev V, Vechev MT (2016) PHOG: probabilistic model for code. In: Balcan M, Weinberger K Q (eds) Proceedings of the 33nd international conference on machine learning, ICML 2016, New York City, NY, USA, June 19\u201324, 2016, JMLR.org, JMLR Workshop and conference proceedings. http:\/\/proceedings.mlr.press\/v48\/bielik16.html, vol 48, pp 2933\u20132942"},{"key":"10118_CR10","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1162\/tacl_a_00051","volume":"5","author":"P Bojanowski","year":"2017","unstructured":"Bojanowski P, Grave E, Joulin A, Mikolov T (2017) Enriching word vectors with subword information. Trans Assoc Comput Linguis 5:135\u2013146. https:\/\/transacl.org\/ojs\/index.php\/tacl\/article\/view\/999","journal-title":"Trans Assoc Comput Linguis"},{"key":"10118_CR11","doi-asserted-by":"publisher","unstructured":"B\u00fcch L, Andrzejak A (2019) Learning-based recursive aggregation of abstract syntax trees for code clone detection. In: Wang X, Lo D, Shihab E (eds) 26th IEEE international conference on software analysis, evolution and reengineering, SANER 2019, Hangzhou, China, February 24\u201327, 2019. https:\/\/doi.org\/10.1109\/SANER.2019.8668039. IEEE, pp 95\u2013104","DOI":"10.1109\/SANER.2019.8668039"},{"key":"10118_CR12","unstructured":"Chen Z, Monperrus M (2018) The remarkable role of similarity in redundancy-based program repair. arXiv:http:\/\/arxiv.org\/abs\/1811.05703"},{"issue":"5","key":"10118_CR13","doi-asserted-by":"publisher","first-page":"1843","DOI":"10.1007\/s10664-015-9402-8","volume":"21","author":"T Chen","year":"2016","unstructured":"Chen T, Thomas SW, Hassan AE (2016) A survey on the use of topic models when mining software repositories. Empir Softw Eng 21(5):1843\u20131919. https:\/\/doi.org\/10.1007\/s10664-015-9402-8","journal-title":"Empir Softw Eng"},{"key":"10118_CR14","doi-asserted-by":"publisher","unstructured":"Collard ML, Decker MJ, Maletic JI (2011) Lightweight transformation and fact extraction with the srcml toolkit. In: 11th IEEE working conference on source code analysis and manipulation, SCAM 2011, Williamsburg, VA, USA, September 25\u201326, 2011. https:\/\/doi.org\/10.1109\/SCAM.2011.19. IEEE Computer Society, pp 173\u2013184","DOI":"10.1109\/SCAM.2011.19"},{"key":"10118_CR15","doi-asserted-by":"publisher","unstructured":"Devlin J, Chang M, Lee K, Toutanova K (2019) BERT: pre-training of deep bidirectional transformers for language understanding. In: Burstein J, Doran C, Solorio T (eds) Proceedings of the 2019 conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2\u20137, 2019, vol 1 (Long and Short Papers). https:\/\/doi.org\/10.18653\/v1\/n19-1423. Association for Computational Linguistics, pp 4171\u20134186","DOI":"10.18653\/v1\/n19-1423"},{"key":"10118_CR16","doi-asserted-by":"crossref","unstructured":"Ding Z, Li H, Shang W (2022) Logentext: automatically generating logging texts using neural machine translation. In: SANER. IEEE","DOI":"10.1109\/SANER53432.2022.00051"},{"key":"10118_CR17","doi-asserted-by":"publisher","unstructured":"Dubinsky Y, Rubin J, Berger T, Duszynski S, Becker M, Czarnecki K (2013) An exploratory study of cloning in industrial software product lines. In: Cleve A, Ricca F, Cerioli M (eds) 17th European conference on software maintenance and reengineering, CSMR 2013, Genova, Italy, March 5\u20138, 2013. https:\/\/doi.org\/10.1109\/CSMR.2013.13. IEEE Computer Society, pp 25\u201334","DOI":"10.1109\/CSMR.2013.13"},{"key":"10118_CR18","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1109\/MSR.2019.00015","volume-title":"Proceedings of the 16th international conference on mining software repositories, MSR 2019, 26\u201327 May 2019","author":"V Efstathiou","year":"2019","unstructured":"Efstathiou V, Spinellis D (2019) Semantic source code models using identifier embeddings. In: Storey MD, Adams B, Haiduc S (eds) Proceedings of the 16th international conference on mining software repositories, MSR 2019, 26\u201327 May 2019. https:\/\/doi.org\/10.1109\/MSR.2019.00015. IEEE\/ACM, Montreal, pp 29\u201333"},{"key":"10118_CR19","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: Cohn T, He Y, Liu Y (eds) Findings of the association for computational linguistics: EMNLP 2020, online event, 16\u201320 november 2020. Association for Computational Linguistics, findings of ACL, vol EMNLP 2020. https:\/\/doi.org\/10.18653\/v1\/2020.findings-emnlp.139, pp 1536\u20131547","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"10118_CR20","doi-asserted-by":"publisher","unstructured":"Gilda S (2017) Source code classification using neural networks. IEEE, pp 1\u20136. https:\/\/doi.org\/10.1109\/JCSSE.2017.8025917","DOI":"10.1109\/JCSSE.2017.8025917"},{"key":"10118_CR21","unstructured":"Harer JA, Kim LY, Russell RL, Ozdemir O, Kosta LR, Rangamani A, Hamilton LH, Centeno GI, Key JR, Ellingwood PM, McConley MW, Opper JM, Chin SP, Lazovich T (2018) Automated software vulnerability detection with machine learning. arXiv:http:\/\/arxiv.org\/abs\/1803.04497"},{"key":"10118_CR22","doi-asserted-by":"publisher","first-page":"837","DOI":"10.1109\/ICSE.2012.6227135","volume-title":"34th International conference on software engineering, ICSE 2012, June 2\u20139, 2012","author":"A Hindle","year":"2012","unstructured":"Hindle A, Barr ET, Su Z, Gabel M, Devanbu PT (2012) On the naturalness of software. In: Glinz M, Murphy G C, Pezz\u00e8 M (eds) 34th International conference on software engineering, ICSE 2012, June 2\u20139, 2012. https:\/\/doi.org\/10.1109\/ICSE.2012.6227135. IEEE Computer Society, Zurich, pp 837\u2013847"},{"key":"10118_CR23","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1145\/3196321.3196334","volume-title":"Proceedings of the 26th conference on program comprehension, ICPC 2018, Gothenburg, Sweden, May 27\u201328, 2018","author":"X Hu","year":"2018","unstructured":"Hu X, Li G, Xia X, Lo D, Jin Z (2018) Deep code comment generation. In: Khomh F, Roy CK, Siegmund J (eds) Proceedings of the 26th conference on program comprehension, ICPC 2018, Gothenburg, Sweden, May 27\u201328, 2018. https:\/\/doi.org\/10.1145\/3196321.3196334. ACM, pp 200\u2013210"},{"key":"10118_CR24","first-page":"255","volume-title":"24th USENIX security symposium, USENIX security 15, Washington, D.C., USA, August 12\u201314, 2015","author":"AC Islam","year":"2015","unstructured":"Islam AC, Harang RE, Liu A, Narayanan A, Voss CR, Yamaguchi F, Greenstadt R (2015) De-anonymizing programmers via code stylometry. In: Jung J, Holz T (eds) 24th USENIX security symposium, USENIX security 15, Washington, D.C., USA, August 12\u201314, 2015. https:\/\/www.usenix.org\/conference\/usenixsecurity15\/technical-sessions\/presentation\/caliskan-islam. USENIX Association, pp 255\u2013270"},{"issue":"7","key":"10118_CR25","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1109\/TSE.2002.1019480","volume":"28","author":"T Kamiya","year":"2002","unstructured":"Kamiya T, Kusumoto S, Inoue K (2002) Ccfinder: a multilinguistic token-based code clone detection system for large scale source code. IEEE Trans Softw Eng 28(7):654\u2013670. https:\/\/doi.org\/10.1109\/TSE.2002.1019480","journal-title":"IEEE Trans Softw Eng"},{"key":"10118_CR26","first-page":"5110","volume-title":"Proceedings of the 37th international conference on machine learning, ICML 2020, 13\u201318 July 2020, Virtual Event, PMLR, Proceedings of Machine Learning Research, vol 119","author":"A Kanade","year":"2020","unstructured":"Kanade A, Maniatis P, Balakrishnan G, Shi K (2020) Learning and evaluating contextual embedding of source code. In: Proceedings of the 37th international conference on machine learning, ICML 2020, 13\u201318 July 2020, Virtual Event, PMLR, Proceedings of Machine Learning Research. http:\/\/proceedings.mlr.press\/v119\/kanade20a.html, vol 119, pp 5110\u20135121"},{"key":"10118_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ASE.2019.00011","volume-title":"34th IEEE\/ACM international conference on automated software engineering, ASE 2019, san diego, CA, USA, November 11\u201315, 2019","author":"HJ Kang","year":"2019","unstructured":"Kang HJ, Bissyand\u00e9 TF, Lo D (2019) Assessing the generalizability of code2vec token embeddings. In: 34th IEEE\/ACM international conference on automated software engineering, ASE 2019, san diego, CA, USA, November 11\u201315, 2019. https:\/\/doi.org\/10.1109\/ASE.2019.00011. IEEE, pp 1\u201312"},{"issue":"7","key":"10118_CR28","doi-asserted-by":"publisher","first-page":"939","DOI":"10.1016\/j.jss.2005.06.044","volume":"79","author":"S Kawaguchi","year":"2006","unstructured":"Kawaguchi S, Garg PK, Matsushita M, Inoue K (2006) Mudablue: an automatic categorization system for open source repositories. J Syst Softw 79(7):939\u2013953. https:\/\/doi.org\/10.1016\/j.jss.2005.06.044","journal-title":"J Syst Softw"},{"key":"10118_CR29","doi-asserted-by":"crossref","unstructured":"Kim Y (2014) Convolutional neural networks for sentence classification. arXiv:http:\/\/arxiv.org\/abs\/14085882","DOI":"10.3115\/v1\/D14-1181"},{"key":"10118_CR30","first-page":"1490","volume-title":"Proceedings of the 2016 conference of the North American chapter of the association for computational linguistics: human language technologies","author":"A Komninos","year":"2016","unstructured":"Komninos A, Manandhar S (2016) Dependency based embeddings for sentence classification tasks. In: Proceedings of the 2016 conference of the North American chapter of the association for computational linguistics: human language technologies, pp 1490\u20131500"},{"key":"10118_CR31","unstructured":"Li C, Li J, Song Y, Lin Z (2018a) Training and evaluating improved dependency-based word embeddings. In: McIlraith SA, Weinberger KQ (eds) Proceedings of the thirty-second AAAI conference on artificial intelligence, (AAAI-18), the 30th innovative applications of artificial intelligence (IAAI-18), and the 8th AAAI symposium on educational advances in artificial intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2\u20137, 2018. https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI18\/paper\/view\/16429. AAAI Press, pp 5836\u20135843"},{"issue":"5","key":"10118_CR32","doi-asserted-by":"publisher","first-page":"2655","DOI":"10.1007\/s10664-018-9595-8","volume":"23","author":"H Li","year":"2018","unstructured":"Li H, Chen TP, Shang W, Hassan AE (2018b) Studying software logging using topic models. Empir Softw Eng 23(5):2655\u20132694. https:\/\/doi.org\/10.1007\/s10664-018-9595-8","journal-title":"Empir Softw Eng"},{"key":"10118_CR33","unstructured":"Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, Levy O, Lewis M, Zettlemoyer L, Stoyanov V (2019) Roberta: a robustly optimized BERT pretraining approach. arXiv:http:\/\/arxiv.org\/abs\/1907.11692"},{"key":"10118_CR34","unstructured":"Masters D, Luschi C (2018) Revisiting small batch training for deep neural networks. arXiv:http:\/\/arxiv.org\/abs\/1804.07612"},{"key":"10118_CR35","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1109\/ICSM.1996.565012","volume-title":"1996 International conference on software maintenance (ICSM \u201996), 4\u20138 November 1996, Monterey, CA, USA, Proceedings","author":"J Mayrand","year":"1996","unstructured":"Mayrand J, Leblanc C, Merlo E (1996) Experiment on the automatic detection of function clones in a software system using metrics. In: 1996 International conference on software maintenance (ICSM \u201996), 4\u20138 November 1996, Monterey, CA, USA, Proceedings. https:\/\/doi.org\/10.1109\/ICSM.1996.565012. IEEE Computer Society, p 244"},{"key":"10118_CR36","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1145\/2597008.2597149","volume-title":"22nd International conference on program comprehension, ICPC 2014, Hyderabad, India, June 2\u20133, 2014","author":"PW McBurney","year":"2014","unstructured":"McBurney PW, McMillan C (2014) Automatic documentation generation via source code summarization of method context. In: Roy CK, Begel A, Moonen L (eds) 22nd International conference on program comprehension, ICPC 2014, Hyderabad, India, June 2\u20133, 2014. https:\/\/doi.org\/10.1145\/2597008.2597149. ACM, pp 279\u2013290"},{"key":"10118_CR37","volume-title":"1st International conference on learning representations, ICLR 2013, Scottsdale, Arizona, USA, May 2\u20134, 2013. Workshop Track Proceedings","author":"T Mikolov","year":"2013","unstructured":"Mikolov T, Chen K, Corrado G, Dean J (2013a) Efficient estimation of word representations in vector space. In: Bengio Y, Lecun Y (eds) 1st International conference on learning representations, ICLR 2013, Scottsdale, Arizona, USA, May 2\u20134, 2013. Workshop Track Proceedings. arXiv:http:\/\/arxiv.org\/abs\/1301.3781"},{"key":"10118_CR38","first-page":"3111","volume-title":"Proceedings of the 26th international conference on neural information processing systems. NIPS\u201913, vol 2","author":"T Mikolov","year":"2013","unstructured":"Mikolov T, Sutskever I, Chen K, Corrado G, Dean J (2013b) Distributed representations of words and phrases and their compositionality. In: Proceedings of the 26th international conference on neural information processing systems. NIPS\u201913, vol 2. http:\/\/dl.acm.org\/citation.cfm?id=2999792.2999959. Curran Associates Inc., pp 3111\u20133119"},{"key":"10118_CR39","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1109\/ICPC.2013.6613830","volume-title":"IEEE 21st international conference on program comprehension, ICPC 2013, San Francisco, CA, USA, 20\u201321 May, 2013","author":"L Moreno","year":"2013","unstructured":"Moreno L, Aponte J, Sridhara G, Marcus A, Pollock LL, Vijay-shanker K (2013) Automatic generation of natural language summaries for java classes. In: IEEE 21st international conference on program comprehension, ICPC 2013, San Francisco, CA, USA, 20\u201321 May, 2013. https:\/\/doi.org\/10.1109\/ICPC.2013.6613830. IEEE Computer Society, pp 23\u201332"},{"key":"10118_CR40","first-page":"1287","volume-title":"Proceedings of the thirtieth AAAI conference on artificial intelligence, February 12\u201317, 2016","author":"L Mou","year":"2016","unstructured":"Mou L, Li G, Zhang L, Wang T, Jin Z (2016) Convolutional neural networks over tree structures for programming language processing. In: Schuurmans D, Wellman MP (eds) Proceedings of the thirtieth AAAI conference on artificial intelligence, February 12\u201317, 2016. http:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI16\/paper\/view\/11775. AAAI Press, Phoenix, pp 1287\u20131293"},{"key":"10118_CR41","first-page":"311","volume-title":"Proceedings of the 40th annual meeting of the association for computational linguistics, July 6\u201312, 2002","author":"K Papineni","year":"2002","unstructured":"Papineni K, Roukos S, Ward T, Zhu W (2002) Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting of the association for computational linguistics, July 6\u201312, 2002. https:\/\/www.aclweb.org\/anthology\/P02-1040\/. ACL, Philadelphia, pp 311\u2013318"},{"key":"10118_CR42","first-page":"1532","volume-title":"Proceedings of the 2014 conference on empirical methods in natural language processing, EMNLP 2014, October 25\u201329, 2014, Doha, Qatar. A meeting of SIGDAT, a Special Interest Group of the ACL","author":"J Pennington","year":"2014","unstructured":"Pennington J, Socher R, Manning CD (2014) Glove: global vectors for word representation. In: Moschitti A, Pang B, Daelemans W (eds) Proceedings of the 2014 conference on empirical methods in natural language processing, EMNLP 2014, October 25\u201329, 2014, Doha, Qatar. A meeting of SIGDAT, a Special Interest Group of the ACL. https:\/\/www.aclweb.org\/anthology\/D14-1162\/. ACL, pp 1532\u20131543"},{"issue":"OOPSLA","key":"10118_CR43","doi-asserted-by":"publisher","first-page":"147:1","DOI":"10.1145\/3276517","volume":"2","author":"M Pradel","year":"2018","unstructured":"Pradel M, Sen K (2018) Deepbugs: a learning approach to name-based bug detection. PACMPL 2(OOPSLA):147:1\u2013147:25. https:\/\/doi.org\/10.1145\/3276517","journal-title":"PACMPL"},{"key":"10118_CR44","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1145\/2676726.2677009","volume-title":"Proceedings of the 42nd annual ACM SIGPLAN-SIGACT symposium on principles of programming languages, POPL 2015, Mumbai, India, January 15\u201317, 2015","author":"V Raychev","year":"2015","unstructured":"Raychev V, Vechev MT, Krause A (2015) Predicting program properties from \u201cbig code\u201d. In: Rajamani SK, Walker D (eds) Proceedings of the 42nd annual ACM SIGPLAN-SIGACT symposium on principles of programming languages, POPL 2015, Mumbai, India, January 15\u201317, 2015. https:\/\/doi.org\/10.1145\/2676726.2677009. ACM, pp 111\u2013124"},{"key":"10118_CR45","first-page":"45","volume-title":"Proceedings of the LREC 2010 workshop on new challenges for NLP frameworks, ELRA, Valletta, Malta","author":"R \u0158eh\u00e5\u0159ek","year":"2010","unstructured":"\u0158eh\u00e5\u0159ek R, Sojka P (2010) Software framework for topic modelling with large corpora. In: Proceedings of the LREC 2010 workshop on new challenges for NLP frameworks, ELRA, Valletta, Malta. http:\/\/is.muni.cz\/publication\/884893\/en, pp 45\u201350"},{"issue":"115","key":"10118_CR46","first-page":"64","volume":"541","author":"CK Roy","year":"2007","unstructured":"Roy CK, Cordy JR (2007) A survey on software clone detection research. Queen\u2019s School of Computing TR 541(115):64\u201368. https:\/\/doi.org\/10.1.1.62.7869","journal-title":"Queen\u2019s School of Computing TR"},{"key":"10118_CR47","doi-asserted-by":"publisher","first-page":"1157","DOI":"10.1145\/2884781.2884877","volume-title":"Proceedings of the 38th international conference on software engineering, ICSE 2016, Austin, TX, USA, May 14\u201322, 2016","author":"H Sajnani","year":"2016","unstructured":"Sajnani H, Saini V, Svajlenko J, Roy CK, Lopes CV (2016) Sourcerercc: scaling code clone detection to big-code. In: Dillon LK, Visser W, Williams L (eds) Proceedings of the 38th international conference on software engineering, ICSE 2016, Austin, TX, USA, May 14\u201322, 2016. https:\/\/doi.org\/10.1145\/2884781.2884877. ACM, pp 1157\u20131168"},{"key":"10118_CR48","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1145\/1858996.1859006","volume-title":"ASE 2010, 25th IEEE\/ACM international conference on automated software engineering, Antwerp, Belgium, September 20\u201324, 2010","author":"G Sridhara","year":"2010","unstructured":"Sridhara G, Hill E, Muppaneni D, Pollock LL, Vijay-Shanker K (2010) Towards automatically generating summary comments for java methods. In: Pecheur C, Andrews J, Nitto ED (eds) ASE 2010, 25th IEEE\/ACM international conference on automated software engineering, Antwerp, Belgium, September 20\u201324, 2010. https:\/\/doi.org\/10.1145\/1858996.1859006. ACM, pp 43\u201352"},{"issue":"OOPSLA","key":"10118_CR49","doi-asserted-by":"publisher","first-page":"233:1","DOI":"10.1145\/3428301","volume":"4","author":"Y Sui","year":"2020","unstructured":"Sui Y, Cheng X, Zhang G, Wang H (2020) Flow2vec: value-flow-based precise code embedding. CoRR 4 (OOPSLA):233:1\u2013233:27. https:\/\/doi.org\/10.1145\/3428301","journal-title":"CoRR"},{"key":"10118_CR50","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1109\/ICSME.2014.77","volume-title":"30th IEEE international conference on software maintenance and evolution, Victoria, BC, Canada, September 29\u2013October 3, 2014","author":"J Svajlenko","year":"2014","unstructured":"Svajlenko J, Islam JF, Keivanloo I, Roy CK, Mia MM (2014) Towards a big data curated benchmark of inter-project code clones. In: 30th IEEE international conference on software maintenance and evolution, Victoria, BC, Canada, September 29\u2013October 3, 2014. https:\/\/doi.org\/10.1109\/ICSME.2014.77. IEEE Computer Society, pp 476\u2013480"},{"key":"10118_CR51","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/MSR.2019.00014","volume-title":"Proceedings of the 16th international conference on mining software repositories, MSR 2019, 26\u201327 May 2019","author":"B Theeten","year":"2019","unstructured":"Theeten B, Vandeputte F, Cutsem TV (2019) Import2vec learning embeddings for software libraries. In: Storey MD, Adams B, Haiduc S (eds) Proceedings of the 16th international conference on mining software repositories, MSR 2019, 26\u201327 May 2019. https:\/\/doi.org\/10.1109\/MSR.2019.00014. IEEE\/ACM, Montreal, pp 18\u201328"},{"issue":"1","key":"10118_CR52","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10664-009-9108-x","volume":"15","author":"S Thummalapenta","year":"2010","unstructured":"Thummalapenta S, Cerulo L, Aversano L, Penta MD (2010) An empirical study on the maintenance of source code clones. Empir Softw Eng 15 (1):1\u201334. https:\/\/doi.org\/10.1007\/s10664-009-9108-x","journal-title":"Empir Softw Eng"},{"key":"10118_CR53","doi-asserted-by":"publisher","first-page":"542","DOI":"10.1145\/3196398.3196431","volume-title":"Proceedings of the 15th international conference on mining software repositories, MSR 2018, Gothenburg, Sweden, May 28\u201329, 2018","author":"M Tufano","year":"2018","unstructured":"Tufano M, Watson C, Bavota G, Penta MD, White M, Poshyvanyk D (2018) Deep learning similarities from different representations of source code. In: Zaidman A, Kamei Y, Hill E (eds) Proceedings of the 15th international conference on mining software repositories, MSR 2018, Gothenburg, Sweden, May 28\u201329, 2018. https:\/\/doi.org\/10.1145\/3196398.3196431. ACM, pp 542\u2013553"},{"key":"10118_CR54","doi-asserted-by":"publisher","first-page":"3308","DOI":"10.18653\/v1\/p19-1320","volume-title":"Proceedings of the 57th conference of the association for computational linguistics, ACL 2019, Florence, Italy, July 28\u2013August 2, 2019, vol 1: Long Papers, Association for Computational Linguistics","author":"S Vashishth","year":"2019","unstructured":"Vashishth S, Bhandari M, Yadav P, Rai P, Bhattacharyya C, Talukdar PP (2019) Incorporating syntactic and semantic information in word embeddings using graph convolutional networks. 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\u2013August 2, 2019, vol 1: Long Papers, Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/p19-1320, pp 3308\u20133318"},{"issue":"3","key":"10118_CR55","doi-asserted-by":"publisher","first-page":"582","DOI":"10.1007\/s10664-012-9230-z","volume":"19","author":"ML V\u00e1squez","year":"2014","unstructured":"V\u00e1squez ML, McMillan C, Poshyvanyk D, Grechanik M (2014) On using machine learning to automatically classify software applications into domain categories. Empir Softw Eng 19(3):582\u2013618. https:\/\/doi.org\/10.1007\/s10664-012-9230-z","journal-title":"Empir Softw Eng"},{"key":"10118_CR56","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1145\/2884781.2884804","volume-title":"Proceedings of the 38th international conference on software engineering, ICSE 2016, Austin, TX, USA, May 14\u201322, 2016","author":"S Wang","year":"2016","unstructured":"Wang S, Liu T, Tan L (2016) Automatically learning semantic features for defect prediction. In: Dillon LK, Visser W, Williams L (eds) Proceedings of the 38th international conference on software engineering, ICSE 2016, Austin, TX, USA, May 14\u201322, 2016. https:\/\/doi.org\/10.1145\/2884781.2884804. ACM, pp 297\u2013308"},{"key":"10118_CR57","volume-title":"6th International conference on learning representations, ICLR 2018, Vancouver, BC, Canada, April 30\u2013May 3, 2018. Conference Track Proceedings, OpenReview.net","author":"K Wang","year":"2018","unstructured":"Wang K, Singh R, Su Z (2018) Dynamic neural program embeddings for program repair. In: 6th International conference on learning representations, ICLR 2018, Vancouver, BC, Canada, April 30\u2013May 3, 2018. Conference Track Proceedings, OpenReview.net. https:\/\/openreview.net\/forum?id=BJuWrGW0Z"},{"key":"10118_CR58","doi-asserted-by":"publisher","first-page":"3034","DOI":"10.24963\/ijcai.2017\/423","volume-title":"Proceedings of the twenty-sixth international joint conference on artificial intelligence, IJCAI 2017, Melbourne, Australia, August 19\u201325, 2017, ijcai.org","author":"H Wei","year":"2017","unstructured":"Wei H, Li M (2017) Supervised deep features for software functional clone detection by exploiting lexical and syntactical information in source code. In: Sierra C (ed) Proceedings of the twenty-sixth international joint conference on artificial intelligence, IJCAI 2017, Melbourne, Australia, August 19\u201325, 2017, ijcai.org. https:\/\/doi.org\/10.24963\/ijcai.2017\/423, pp 3034\u20133040"},{"key":"10118_CR59","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1145\/2970276.2970326","volume-title":"Proceedings of the 31st IEEE\/ACM international conference on automated software engineering, ASE 2016, Singapore, September 3\u20137, 2016","author":"M White","year":"2016","unstructured":"White M, Tufano M, Vendome C, Poshyvanyk D (2016) Deep learning code fragments for code clone detection. In: Lo D, Apel S, Khurshid S (eds) Proceedings of the 31st IEEE\/ACM international conference on automated software engineering, ASE 2016, Singapore, September 3\u20137, 2016. https:\/\/doi.org\/10.1145\/2970276.2970326. ACM, pp 87\u201398"},{"key":"10118_CR60","doi-asserted-by":"publisher","first-page":"479","DOI":"10.1109\/SANER.2019.8668043","volume-title":"26th IEEE international conference on software analysis, evolution and reengineering, SANER 2019, Hangzhou, China, February 24\u201327, 2019","author":"M White","year":"2019","unstructured":"White M, Tufano M, Martinez M, Monperrus M, Poshyvanyk D (2019) Sorting and transforming program repair ingredients via deep learning code similarities. In: Wang X, Lo D, Shihab E (eds) 26th IEEE international conference on software analysis, evolution and reengineering, SANER 2019, Hangzhou, China, February 24\u201327, 2019. https:\/\/doi.org\/10.1109\/SANER.2019.8668043. IEEE, pp 479\u2013490"},{"key":"10118_CR61","doi-asserted-by":"publisher","first-page":"783","DOI":"10.1109\/ICSE.2019.00086","volume-title":"Proceedings of the 41st international conference on software engineering, ICSE 2019, Montreal, QC, Canada, May 25\u201331, 2019","author":"J Zhang","year":"2019","unstructured":"Zhang J, Wang X, Zhang H, Sun H, Wang K, Liu X (2019) A novel neural source code representation based on abstract syntax tree. In: Atlee JM, Bultan T, Whittle J (eds) Proceedings of the 41st international conference on software engineering, ICSE 2019, Montreal, QC, Canada, May 25\u201331, 2019. https:\/\/doi.org\/10.1109\/ICSE.2019.00086. IEEE\/ACM, pp 783\u2013794"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-022-10118-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10664-022-10118-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-022-10118-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,29]],"date-time":"2023-01-29T11:11:42Z","timestamp":1674990702000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10664-022-10118-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,17]]},"references-count":61,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,5]]}},"alternative-id":["10118"],"URL":"https:\/\/doi.org\/10.1007\/s10664-022-10118-5","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"value":"1382-3256","type":"print"},{"value":"1573-7616","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,17]]},"assertion":[{"value":"10 January 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 March 2022","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 declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of Interest"}}],"article-number":"63"}}