Abstract
Technologists with various personas such as data scientists, software architects, software engineers, data engineers and research scientists spend hours writing piece of code, using different algorithms and commenting their code snippets or scripts. However, it takes considerable amount of time to comment the code and customize these comments based on the knowledge level of audience. In an ideal world, if everyone belongs to the same persona which means similar background and skill set, having the same set of comments on source code repositories should be perfect. But with the advent of multiple personas in the recent years, there needs to be a mechanism wherein the comments are synthesized and custom tailored dynamically based on the persona viewing the code. The comments should be added at appropriate instances of the code to make it more readable, contextual, meaningful depending on the persona of the reader. In our paper, we propose a novel method to consider persona into account to generate comments for the source code using Natural Language Processing (NLP) and generative AI. The generated comments will takes into account the context and intention while writing the code. It also includes a real time feedback loop which helps enhance the persona understanding and model improvement.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Trim et al.: US11556709B2: text autocomplete using punctuation marks (2020)
Silverstein et al.: US20210264480A1: text processing based interface accelerating (2020)
Baughman et al.: US11481401B2: enhanced cognitive query construction (2020)
Kochura et al.: US11488240B2: dynamic chatbot session based on product image and description discrepancy (2020)
Hu, X., et al.: Deep code comment generation. In: ICPC 2018: Proceedings of the 26th Conference on Program Comprehension (2018)
Matskevich, S., et al.: Generating comments from source code with CCGs. In: NL4SE 2018: Proceedings of 4th ACM SIGSOFT Int. Workshop on NLP for Software Engineering (2018)
Chen, F., et al.: novel natural language summarization of program code via leveraging multiple input representations. Om: EMNLP 2021 (2021)
Liang, Y., et al.: Automatic generation of text descriptive comments for code blocks. In: AAAI 2018(2018)
Zhang et al.: Training deep code comment generation models via data augmentation. In: Internet ware (2020)
Banipal et al.: US20220215047A1: context-based text searching (2021)
Kwatra et al.: US11483262B2: contextually-aware personalized chatbot (2020)
Trim et al.: US20220188525A1: dynamic, real-time collaboration enhancement (2020)
Banipal et al.: US20220358237A1: secure data analytics (2021)
Cannon et al.: US20220164472A1: recommending post modifications to reduce sensitive data exposure (2020)
Banipal et al.: Smart system for multi-cloud pathways. In: IEEE Big Data (2022)
Banipal et al.: US11514507B2: virtual image prediction and generation (2020)
Banipal, I.S., Freed, A., Kwatra, S.: US11185780B2: artificial intelligence profiling (2017)
Banipal et al.: US20220309379A1: automatic identification of improved machine learning models (2021)
Banipal, I.S., Freed, A.: US20210042290A1: annotation assessment and adjudication (2019)
Banipal, I.S., Freed, A.: US11188517B2: annotation assessment and ground truth construction (2019)
Silverstein et al.: US11055119B1: feedback responsive Interface (2020)
Wang, X., et al.: KDGAN: knowledge distillation with generative adversarial networks (2018)
Iovine, A., et al.: CycleNER: an unsupervised training approach for named entity recognition. In: WWW 2022 (2022)
SystemML, IBM Research
Asthana et al.: Joint time-series learning framework for maximizing purchase order renewals (2021)
Trim, C., et al.: US20220012018A1: software programming assistant (2020)
Kwatra et al.: US11556335B1: annotating program code (2021)
Kwatra et al.: US11552966B2: generating and mutually maturing a knowledge corpus (2020)
Kwatra et al.: US11445042B2: correlating multiple media sources for personalized media content (2020)
Banipal et al.: Relational social media search engine. In: UT Dallas (2016)
Banipal et al.: US11188968B2: component based review system (2020)
Bravo, R., et al.: US10921887B2: cognitive state aware accelerated activity completion and amelioration (2019)
Gan, S.C., et al.: US11556385B2: cognitive processing resource allocation (2020)
Banipal et al.: US20220335302A1: cognitive recommendation of computing environment attributes (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Banipal, I.S., Asthana, S., Mazumder, S., Kochura, N. (2024). Intelligent Code Comments Morphing and Generation. In: Arai, K. (eds) Advances in Information and Communication. FICC 2024. Lecture Notes in Networks and Systems, vol 920. Springer, Cham. https://doi.org/10.1007/978-3-031-53963-3_46
Download citation
DOI: https://doi.org/10.1007/978-3-031-53963-3_46
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-53962-6
Online ISBN: 978-3-031-53963-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)