{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T06:05:28Z","timestamp":1773295528960,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T00:00:00Z","timestamp":1701302400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,30]]},"DOI":"10.1145\/3611643.3616291","type":"proceedings-article","created":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T23:14:38Z","timestamp":1701386078000},"page":"1548-1560","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Evaluating Transfer Learning for Simplifying GitHub READMEs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3274-8630","authenticated-orcid":false,"given":"Haoyu","family":"Gao","sequence":"first","affiliation":[{"name":"The University of Melbourne, Melbourne, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6919-2149","authenticated-orcid":false,"given":"Christoph","family":"Treude","sequence":"additional","affiliation":[{"name":"The University of Melbourne, Melbourne, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6276-9956","authenticated-orcid":false,"given":"Mansooreh","family":"Zahedi","sequence":"additional","affiliation":[{"name":"The University of Melbourne, Melbourne, Australia"}]}],"member":"320","published-online":{"date-parts":[[2023,11,30]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380405"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00122"},{"key":"e_1_3_2_2_3_1","volume-title":"Language models are few-shot learners. Advances in neural information processing systems, 33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, and Amanda Askell. 2020. Language models are few-shot learners. Advances in neural information processing systems, 33 (2020), 1877\u20131901."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W15-1604"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/asi.21577"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/2107679.2107680"},{"key":"e_1_3_2_2_7_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. CoRR, abs\/1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. CoRR, abs\/1810.04805 (2018), arXiv:1810.04805. arxiv:1810.04805"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510069"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1146"},{"key":"e_1_3_2_2_11_1","first-page":"23","article-title":"A new algorithm for data compression","volume":"12","author":"Gage Philip","year":"1994","unstructured":"Philip Gage. 1994. A new algorithm for data compression. C Users Journal, 12, 2 (1994), 23\u201338.","journal-title":"C Users Journal"},{"key":"e_1_3_2_2_12_1","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference. European Language Resources Association","author":"Gala N\u00faria","year":"2020","unstructured":"N\u00faria Gala, Ana\u00efs Tack, Ludivine Javourey-Drevet, Thomas Fran\u00e7ois, and Johannes C. Ziegler. 2020. Alector: A Parallel Corpus of Simplified French Texts with Alignments of Misreadings by Poor and Dyslexic Readers. In Proceedings of the Twelfth Language Resources and Evaluation Conference. European Language Resources Association, Marseille, France. 1353\u20131361. isbn:979-10-95546-34-4 https:\/\/aclanthology.org\/2020.lrec-1.169"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2015. Deep Residual Learning for Image Recognition. https:\/\/doi.org\/10.48550\/ARXIV.1512.03385 10.48550\/ARXIV.1512.03385","DOI":"10.48550\/ARXIV.1512.03385"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3196321.3196334"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_17_1","volume-title":"Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers. The COLING 2016 Organizing Committee","author":"Kajiwara Tomoyuki","year":"2016","unstructured":"Tomoyuki Kajiwara and Mamoru Komachi. 2016. Building a Monolingual Parallel Corpus for Text Simplification Using Sentence Similarity Based on Alignment between Word Embeddings. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers. The COLING 2016 Organizing Committee, Osaka, Japan. 1147\u20131158. https:\/\/aclanthology.org\/C16-1109"},{"key":"e_1_3_2_2_18_1","volume-title":"Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, ACL. The Association for Computer Linguistics","author":"Kauchak David","year":"2013","unstructured":"David Kauchak. 2013. Improving Text Simplification Language Modeling Using Unsimplified Text Data. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, ACL. The Association for Computer Linguistics, Sofia, Bulgaria. 1537\u20131546. https:\/\/aclanthology.org\/P13-1151\/"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1468-2958.2004.tb00738.x"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2019.00026"},{"key":"e_1_3_2_2_21_1","volume-title":"Controllable Sentence Simplification: Employing Syntactic and Lexical Constraints. CoRR, abs\/1910.04387","author":"Mallinson Jonathan","year":"2019","unstructured":"Jonathan Mallinson and Mirella Lapata. 2019. Controllable Sentence Simplification: Employing Syntactic and Lexical Constraints. CoRR, abs\/1910.04387 (2019), arXiv:1910.04387. arxiv:1910.04387"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2597008.2597149"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1093\/ijl\/3.4.235"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPC.2013.6613830"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/SANER48275.2020.9054828"},{"key":"e_1_3_2_2_26_1","volume-title":"Proceedings of the NAACL HLT 2010 Workshop on Computational Linguistics and Writing: Writing Processes and Authoring Aids. Association for Computational Linguistics, USA. 42\u201350","author":"Napoles Courtney","year":"2010","unstructured":"Courtney Napoles and Mark Dredze. 2010. Learning Simple Wikipedia: A Cogitation in Ascertaining Abecedarian Language. In Proceedings of the NAACL HLT 2010 Workshop on Computational Linguistics and Writing: Writing Processes and Authoring Aids. Association for Computational Linguistics, USA. 42\u201350."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-2036"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2008.11.001"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-018-9660-3"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377816.3381732"},{"key":"e_1_3_2_2_33_1","volume-title":"Sequence Level Training with Recurrent Neural Networks. In 4th International Conference on Learning Representations, ICLR","author":"Ranzato Marc\u2019Aurelio","year":"2016","unstructured":"Marc\u2019Aurelio Ranzato, Sumit Chopra, Michael Auli, and Wojciech Zaremba. 2016. Sequence Level Training with Recurrent Neural Networks. In 4th International Conference on Learning Representations, ICLR 2016, Yoshua Bengio and Yann LeCun (Eds.). San Juan, Puerto Rico. arxiv:1511.06732"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1806799.1806872"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2013.2297712"},{"key":"e_1_3_2_2_36_1","volume-title":"International encyclopedia of statistical science","author":"Rey Denise","unstructured":"Denise Rey and Markus Neuh\u00e4user. 2011. Wilcoxon-signed-rank test. In International encyclopedia of statistical science. Springer, 1658\u20131659."},{"key":"e_1_3_2_2_37_1","volume-title":"a distilled version of BERT: smaller, faster, cheaper and lighter. CoRR, abs\/1910.01108","author":"Sanh Victor","year":"2019","unstructured":"Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. CoRR, abs\/1910.01108 (2019), arXiv:1910.01108. arxiv:1910.01108"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-3758(00)00115-4"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3236024.3264598"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-12320-7_5"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/1858996.1859006"},{"key":"e_1_3_2_2_42_1","unstructured":"Sanja Stajner Iacer Calixto and Horacio Saggion. 2015. Automatic Text Simplification for Spanish: Comparative Evaluation of Various Simplification Strategies. In Recent Advances in Natural Language Processing RANLP Galia Angelova Kalina Bontcheva and Ruslan Mitkov (Eds.). RANLP 2015 Organising Committee \/ ACL Hissar Bulgaria. 618\u2013626. https:\/\/aclanthology.org\/R15-1080\/"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/2675133.2675215"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/2884781.2884800"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention Is All You Need. https:\/\/doi.org\/10.48550\/ARXIV.1706.03762 10.48550\/ARXIV.1706.03762","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"e_1_3_2_2_46_1","volume-title":"Online Encyclopedia. In Proceedings of the Ninth International Conference on Web and Social Media, ICWSM, Meeyoung Cha, Cecilia Mascolo, and Christian Sandvig (Eds.). AAAI Press","author":"Wagner Claudia","year":"2015","unstructured":"Claudia Wagner, David Garc\u00eda, Mohsen Jadidi, and Markus Strohmaier. 2015. It\u2019s a Man\u2019s Wikipedia? Assessing Gender Inequality in an Online Encyclopedia. In Proceedings of the Ninth International Conference on Web and Social Media, ICWSM, Meeyoung Cha, Cecilia Mascolo, and Christian Sandvig (Eds.). AAAI Press, University of Oxford, Oxford, UK. 454\u2013463. http:\/\/www.aaai.org\/ocs\/index.php\/ICWSM\/ICWSM15\/paper\/view\/10585"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-016-0043-6"},{"key":"e_1_3_2_2_48_1","volume-title":"Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics","author":"Woodsend Kristian","year":"2011","unstructured":"Kristian Woodsend and Mirella Lapata. 2011. Learning to Simplify Sentences with Quasi-Synchronous Grammar and Integer Programming. In Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Edinburgh, Scotland, UK.. 409\u2013420. https:\/\/aclanthology.org\/D11-1038"},{"key":"e_1_3_2_2_49_1","volume-title":"Google\u2019s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation. CoRR, abs\/1609.08144","author":"Wu Yonghui","year":"2016","unstructured":"Yonghui Wu, Mike Schuster, Zhifeng Chen, Quoc V. Le, Mohammad Norouzi, Wolfgang Macherey, Maxim Krikun, Yuan Cao, Qin Gao, Klaus Macherey, Jeff Klingner, Apurva Shah, Melvin Johnson, Xiaobing Liu, Lukasz Kaiser, Stephan Gouws, Yoshikiyo Kato, Taku Kudo, Hideto Kazawa, Keith Stevens, George Kurian, Nishant Patil, Wei Wang, Cliff Young, Jason Smith, Jason Riesa, Alex Rudnick, Oriol Vinyals, Greg Corrado, Macduff Hughes, and Jeffrey Dean. 2016. Google\u2019s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation. CoRR, abs\/1609.08144 (2016), arXiv:1609.08144. arxiv:1609.08144"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/552"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00139"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1062"},{"key":"e_1_3_2_2_53_1","volume-title":"A Constrained Sequence-to-Sequence Neural Model for Sentence Simplification. CoRR, abs\/1704.02312","author":"Zhang Yaoyuan","year":"2017","unstructured":"Yaoyuan Zhang, Zhenxu Ye, Yansong Feng, Dongyan Zhao, and Rui Yan. 2017. A Constrained Sequence-to-Sequence Neural Model for Sentence Simplification. CoRR, abs\/1704.02312 (2017), arXiv:1704.02312. arxiv:1704.02312"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_55_1","volume-title":"The Eleventh International Conference on Learning Representations, ICLR. OpenReview.net, Kigali, Rwanda. https:\/\/openreview.net\/pdf?id=92gvk82DE-","author":"Zhou Yongchao","year":"2023","unstructured":"Yongchao Zhou, Andrei Ioan Muresanu, Ziwen Han, Keiran Paster, Silviu Pitis, Harris Chan, and Jimmy Ba. 2023. Large Language Models are Human-Level Prompt Engineers. In The Eleventh International Conference on Learning Representations, ICLR. OpenReview.net, Kigali, Rwanda. https:\/\/openreview.net\/pdf?id=92gvk82DE-"},{"key":"e_1_3_2_2_56_1","volume-title":"COLING 2010, 23rd International Conference on Computational Linguistics, Proceedings of the Conference, Chu-Ren Huang and Dan Jurafsky (Eds.)","author":"Zhu Zhemin","year":"2010","unstructured":"Zhemin Zhu, Delphine Bernhard, and Iryna Gurevych. 2010. A Monolingual Tree-based Translation Model for Sentence Simplification. In COLING 2010, 23rd International Conference on Computational Linguistics, Proceedings of the Conference, Chu-Ren Huang and Dan Jurafsky (Eds.). Tsinghua University Press, Beijing, China. 1353\u20131361. https:\/\/aclanthology.org\/C10-1152\/"}],"event":{"name":"ESEC\/FSE '23: 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","location":"San Francisco CA USA","acronym":"ESEC\/FSE '23","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3611643.3616291","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3611643.3616291","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:36:03Z","timestamp":1750178163000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3611643.3616291"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,30]]},"references-count":55,"alternative-id":["10.1145\/3611643.3616291","10.1145\/3611643"],"URL":"https:\/\/doi.org\/10.1145\/3611643.3616291","relation":{},"subject":[],"published":{"date-parts":[[2023,11,30]]},"assertion":[{"value":"2023-11-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}