Abstract
Natural language processing (NLP) involves the automated anal- ysis and manipulation of human language. This includes algo- rithms that can analyze text created by humans and algorithms that can generate text that appears natural. Nowadays, NLP methods are becoming increasingly prevalent to enhance various aspects of software development. Indeed, throughout the software development lifecycle, numerous natural language artifacts are produced. Therefore, the existence of NLP-based approaches and tools has opened up possibilities for improving the e ectiveness and productivity of software engineers, processes, and products. The second edition of the Natural Language-Based Software Engi- neering Workshop (NLBSE) took place in 2023 alongside the 45th International Conference on Software Engineering (ICSE 2023), where the research community engaged in discussions about these approaches. This event brought together researchers and practi- tioners from the elds of NLP and software engineering to ex- change experiences, establish future research directions, and pro- mote the adoption of NLP techniques and tools in tackling chal- lenges speci c to software engineering. In this paper, we present a summary of the 2nd edition of the workshop, which comprised three full papers, four short/position papers, ve tool competi- tion/demonstration papers, two keynote talks (\Automated Bug Management: Re ections & the Road Ahead" by David Lo and \Trends and Opportunities in the Application of Large Language Models: the Quest for Maximum E ect" by Albert Ziegler), fol- lowed by extensive discussion among NLBSE participants. More details can be found at https://nlbse2023.github.io/index. html
- Ha za Anisa Ahmed, Narmeen Zakaria Bawany, and Jawwad Ahmed Shamsi. Capbug-a framework for automatic bug categorization and prioritization using nlp and machine learning algorithms. IEEE Access, 9:50496{50512, 2021.Google ScholarCross Ref
- Ali Al-Kaswan and Maliheh Izadi. The (ab)use of open source code to train large language models. In 2023 IEEE/ACM 2nd International Workshop on Natural Language-Based Software Engineering (NLBSE 2023), Co-located with ICSE 2023, Melbourne, Australia, May 20, 2023, page To appear, 2023.Google ScholarCross Ref
- Ali Al-Kaswan, Maliheh Izadi, and Arie van Deursen. STACC: Code Comment Classi cation using Sentence Transformers. In 2023 IEEE/ACM 2nd International Workshop on Natural Language-Based Software Engineering (NLBSE 2023), Co-located with ICSE 2023, Melbourne, Australia, May 20, 2023, page To appear, 2023.Google Scholar
- Miltiadis Allamanis, Hao Peng, and Charles Sutton. A convolutional attention network for extreme summarization of source code. In Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19--24, 2016, pages 2091{2100, 2016.Google Scholar
- Venera Arnaoudova, Sonia Haiduc, Andrian Marcus, and Giuliano Antoniol. The use of text retrieval and natural language processing in software engineering. In 37th IEEE/ACM International Conference on Software Engineering, ICSE 2015, Florence, Italy, May 16--24, 2015, Volume 2, pages 949{950, 2015.Google ScholarCross Ref
- Manoj Bhat, Klym Shumaiev, Andreas Biesdorf, Uwe Hohenstein, and Florian Matthes. Automatic extraction of design decisions from issue management systems: A machine learning based approach. In Software Architecture - 11th European Conference, ECSA 2017, Canterbury, UK, September 11--15, 2017, Proceedings, pages 138{154, 2017.Google Scholar
- Giuseppe Colavito, Filippo Lanubile, and Nicole Novielli. Few-Shot Learning for Issue Report Classi cation. In 2023 IEEE/ACM 2nd International Workshop on Natural Language-Based Software Engineering (NLBSE 2023), Co-located with ICSE 2023, Melbourne, Australia, May 20, 2023, page To appear, 2023.Google Scholar
- Bas Cornelissen, Andy Zaidman, Arie van Deursen, Leon Moonen, and Rainer Koschke. A systematic survey of program comprehension through dynamic analysis. IEEE Trans. Software Eng., 35(5):684{702, 2009.Google ScholarDigital Library
- Fabiano Dalpiaz, Alessio Ferrari, Xavier Franch, and Cristina Palomares. Natural language processing for requirements engineering: The best is yet to come. IEEE Softw., 35(5):115{119, 2018.Google ScholarCross Ref
- Andrea Di Sorbo, Sebastiano Panichella, Carol V. Alexandru, Junji Shimagaki, Corrado Aaron Visaggio, Gerardo Canfora, and Harald C. Gall. What would users change in my app? summarizing app reviews for recommending software changes. In Proceedings of the 24th ACM SIGSOFT International Symposium on Foundations of Software Engineering, FSE 2016, Seattle, WA, USA, November 13--18, 2016, pages 499{510, 2016.Google ScholarDigital Library
- Andrea Di Sorbo, Sebastiano Panichella, Corrado Aaron Visaggio, Massimiliano Di Penta, Gerardo Canfora, and Harald C. Gall. Development emails content analyzer: Intention mining in developer discussions (T). In 30th IEEE/ACM International Conference on Automated Software Engineering, ASE 2015, Lincoln, NE, USA, November 9--13, 2015, pages 12{23, 2015.Google ScholarDigital Library
- Andrea Di Sorbo, Sebastiano Panichella, Corrado Aaron Visaggio, Massimiliano Di Penta, Gerardo Canfora, and Harald C. Gall. Exploiting natural language structures in software informal documentation. IEEE Trans. Software Eng., 47(8):1587{1604, 2021.Google ScholarCross Ref
- Andrea Di Sorbo, Corrado Aaron Visaggio, Massimiliano Di Penta, Gerardo Canfora, and Sebastiano Panichella. An nlp-based tool for software artifacts analysis. In IEEE International Conference on Software Maintenance and Evolution, ICSME 2021, Luxembourg, September 27 - October 1, 2021, pages 569{573. IEEE, 2021.Google ScholarCross Ref
- Andrea Di Sorbo, Fiorella Zampetti, Aaron Visaggio, Massimiliano Di Penta, and Sebastiano Panichella. Automated identi cation and qualitative characterization of safety concerns reported in uav software platforms. ACM Trans. Softw. Eng. Methodol., 32(3), apr 2023.Google Scholar
- Yaohou Fan, Chetan Arora, and Christoph Treude. Stop words for processing software engineering documents: Do they matter? In 2023 IEEE/ACM 2nd International Workshop on Natural Language-Based Software Engineering (NLBSE 2023), Co-located with ICSE 2023, Melbourne, Australia, May 20, 2023, page To appear, 2023.Google ScholarCross Ref
- Gerhard Fischer and Jonathan L. Ostwald. Knowledge management: Problems, promises, realities, and challenges. IEEE Intell. Syst., 16(1):60{72, 2001.Google ScholarDigital Library
- Vahid Garousi, Sara Bauer, and Michael Felderer. Nlp-assisted software testing: A systematic mapping of the literature. Information and Software Technology, 126:106321, 2020.Google ScholarCross Ref
- Yuan Huang, Shaohao Huang, Huanchao Chen, Xiangping Chen, Zibin Zheng, Xiapu Luo, Nan Jia, Xinyu Hu, and Xiaocong Zhou. Towards automatically generating block comments for code snippets. Information and Software Technology, 127:106373, 2020.Google ScholarCross Ref
- Amila Indika, Peter Y. Washington, and Anthony Peruma. Performance Comparison of Binary Machine Learning Classi ers in Identifying Code Comment Types: An Exploratory Study. In 2023 IEEE/ACM 2nd International Workshop on Natural Language-Based Software Engineering (NLBSE 2023), Co-located with ICSE 2023, Melbourne, Australia, May 20, 2023, page To appear, 2023.Google Scholar
- Siyuan Jiang, Ameer Armaly, and Collin McMillan. Automatically generating commit messages from di s using neural machine translation. In Proceedings of the 32nd IEEE/ACM International Conference on Automated Software Engineering, ASE 2017, Urbana, IL, USA, October 30 - November 03, 2017, pages 135{146, 2017.Google Scholar
- Rafael Kallis, Oscar Chaparro, Andrea Di Sorbo, and Sebastiano Panichella. Nlbse'22 tool competition. In 2022 IEEE/ACM 1st International Workshop on Natural Language-Based Software Engineering (NLBSE 2022), Co-located with ICSE 2022, Pittsburgh, PA, USA, May 8, 2022, pages 25{28. IEEE, 2022.Google Scholar
- Rafael Kallis, Maliheh Izadi, Luca Pascarella, Oscar Chaparro, and Pooja Rani. The nlbse'23 tool competition. In 2023 IEEE/ACM 2nd International Workshop on Natural Language-Based Software Engineering (NLBSE 2023), Co-located with ICSE 2023, Melbourne, Australia, May 20, 2023, page To appear, 2023.Google Scholar
- Rrezarta Krasniqi and Hyunsook Do. Exploring generalizability of nlp-based models for modern software development cross-domain environments. In 2023 IEEE/ACM 2nd International Workshop on Natural Language-Based Software Engineering (NLBSE 2023), Co-located with ICSE 2023, Melbourne, Australia, May 20, 2023, page To appear, 2023.Google Scholar
- Muhammad Laiq. An Intelligent Tool for Classifying Issue Reports. In 2023 IEEE/ACM 2nd International Workshop on Natural Language-Based Software Engineering (NLBSE 2023), Co-located with ICSE 2023, Melbourne, Australia, May 20, 2023, page To appear, 2023.Google Scholar
- Alexander LeClair, Siyuan Jiang, and Collin McMillan. A neural model for generating natural language summaries of program subroutines. In Proceedings of the 41st International Conference on Software Engineering, ICSE 2019, Montreal, QC, Canada, May 25--31, 2019, pages 795{806, 2019.Google ScholarDigital Library
- Ying Li, Haibo Wang, Huaien Zhang, and Shin Hwei Tan. Classifying Code Comments via Pre-trained Programming Language Model. In 2023 IEEE/ACM 2nd International Workshop on Natural Language-Based Software Engineering (NLBSE 2023), Co-located with ICSE 2023, Melbourne, Australia, May 20, 2023, page To appear, 2023.Google ScholarCross Ref
- Bilel Matmti and Fatemeh Fard. Evaluating code comment generation with summarized api docs. In 2023 IEEE/ACM 2nd International Workshop on Natural Language-Based Software Engineering (NLBSE 2023), Co-located with ICSE 2023, Melbourne, Australia, May 20, 2023, page To appear, 2023.Google ScholarCross Ref
- Sebastiano Panichella, Gabriele Bavota, Massimiliano Di Penta, Gerardo Canfora, and Giuliano Antoniol. How developers' collaborations identi ed from di erent sources tell us about code changes. In 30th IEEE International Conference on Software Maintenance and Evolution, Victoria, BC, Canada, September 29 - October 3, 2014, pages 251{260, 2014.Google Scholar
- Sebastiano Panichella, Andrea Di Sorbo, Emitza Guzman, Corrado Aaron Visaggio, Gerardo Canfora, and Harald C. Gall. How can i improve my app? classifying user reviews for software maintenance and evolution. In Rainer Koschke, Jens Krinke, and Martin P. Robillard, editors, 2015 IEEE International Conference on Software Maintenance and Evolution, ICSME 2015, Bremen, Germany, September 29 - October 1, 2015, pages 281{290. IEEE Computer Society, 2015.Google Scholar
- Sebastiano Panichella and Nik Zaugg. An empirical investigation of relevant changes and automation needs in modern code review. Empirical Software Engineering, 25(6):4833{4872, 2020.Google ScholarDigital Library
- Denis Pashchenko. Digitalization in software engineering and IT business. Int. J. Softw. Sci. Comput. Intell., 12(2):1{14, 2020.Google ScholarCross Ref
- Pooja Rani, Sebastiano Panichella, Manuel Leuenberger, Andrea Di Sorbo, and Oscar Nierstrasz. How to identify class comment types? A multi-language approach for class comment classi cation. J. Syst. Softw., 181:111047, 2021.Google ScholarDigital Library
- Mohammed Latif Siddiq, Abdus Samee, Sk Ruhul Azgor, Md. Asif Haider, Shehabul Islam Sawraz, and Joanna Cecilia da Silva Santos. Zero-shot prompting for code complexity prediction using github copilot. In 2023 IEEE/ACM 2nd International Workshop on Natural Language-Based Software Engineering (NLBSE 2023), Co-located with ICSE 2023, Melbourne, Australia, May 20, 2023, page To appear, 2023.Google ScholarCross Ref
- Taryn Takebayashi, Anthony Peruma, Mohamed Wiem Mkaouer, and Christian Newman. An exploratory study on the usage and readability of messages within assertion methods of test cases. In 2023 IEEE/ACM 2nd International Workshop on Natural Language-Based Software Engineering (NLBSE 2023), Co-located with ICSE 2023, Melbourne, Australia, May 20, 2023, page To appear, 2023.Google ScholarCross Ref
- Adriano Torres, Sebastian Baltes, Christoph Treude, and Markus Wagner. Applying information theory to software evolution. In 2023 IEEE/ACM 2nd International Workshop on Natural Language-Based Software Engineering (NLBSE 2023), Co-located with ICSE 2023, Melbourne, Australia, May 20, 2023, page To appear, 2023.Google ScholarCross Ref
- Liping Zhao, Waad Alhoshan, Alessio Ferrari, Keletso J Letsholo, Muideen Ajagbe, Erol-Valeriu Chioasca, and Riza Theresa Batista-Navarro. Natural language processing (nlp) for requirements engineering (re): A systematic mapping study. ACM Computing Surveys, 2020.Google Scholar
- Yu Zhou, Changzhi Wang, Xin Yan, Taolue Chen, Sebastiano Panichella, and Harald Gall. Automatic detection and repair recommendation of directive defects in java api documentation. IEEE Trans. on Software Engineering, 46(9):1004{1023, 2020.Google ScholarCross Ref
Recommendations
Summary of the 1st Natural Language-based Software Engineering Workshop (NLBSE 2022)
Natural language processing (NLP) refers to automatic computa- tional processing of human language, including both algorithms that take human-produced text as input and algorithms that pro- duce natural-looking text as outputs. There is a widespread and ...
2nd International Workshop on Ontology-Driven Software Engineering
ODiSE'10: Ontology-Driven Software EngineeringThe 2nd International Workshop on Ontology-Driven Software Engineering, held at the ACM SPLASH 2010 conference, was organized with the aim of bringing together researchers and practitioners with an interest in discussing and analyzing the different ways ...
Comments