Automatic Code Documentation Generation Using GPT-3
Junaed Younus Khan,Gias Uddin +1 more
- 06 Sep 2022
TL;DR: Codec is a GPT-3 based model pre-trained on both natural and programming languages that outperforms existing techniques even with basic settings like one-shot learning and achieves an overall BLEU score of 20.6 for six different programming languages.
read more
Abstract: Source code documentation is an important artifact for efficient software development. Code documentation could greatly benefit from automation since manual documentation is often labouring, resource and time-intensive. In this paper, we employed Codex for automatic code documentation creation. Codex is a GPT-3 based model pre-trained on both natural and programming languages. We find that Codex outperforms existing techniques even with basic settings like one-shot learning (i.e., providing only one example for training). Codex achieves an overall BLEU score of 20.6 for six different programming languages (11.2% improvement over earlier state-of-the-art techniques). Thus, Codex shows promise and warrants in-depth future studies for automatic code documentation generation to support diverse development tasks.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Figures
![Table 1: Statistics of CodeSearchNet [25]](/figures/table1-1-5v85uyhgqaep.webp)
Citations
A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4
Katikapalli Subramanyam Kalyan
TL;DR: A comprehensive survey which summarizes the recent research progress in multiple dimensions related to GPT-3 family large language models and discusses the performances of GLLMs in various downstream tasks, specific domains and multiple languages.
89
“What It Wants Me To Say”: Bridging the Abstraction Gap Between End-User Programmers and Code-Generating Large Language Models
Michael Xieyang Liu,Advait Sarkar,Carina Negreanu,Benjamin G. Zorn,Michael Williams,Neil Toronto,Andrew D. Gordon +6 more
- 13 Apr 2023
TL;DR: In this paper , the authors propose grounded abstraction matching, which bridges the abstraction gap by translating the code back into a systematic and predictable naturalistic utterance, which improves end-users' understanding of the scope and capabilities of the code-generating model, and the kind of language needed to use it effectively.
82
A survey of GPT-3 family large language models including ChatGPT and GPT-4
Katikapalli Subramanyam Kalyan
TL;DR: A survey of GPT-3 family large language models including ChatGPT and GPT-4 summarizes recent research progress in large language models and provides future research directions.
80
From Google Gemini to OpenAI Q* (Q-Star): A Survey of Reshaping the Generative Artificial Intelligence (AI) Research Landscape
Timothy R. McIntosh,Teo Sušnjak,Tong Liu,Paul Watters,Malka N. Halgamuge +4 more
TL;DR: The study highlighted the importance of incorporating ethical and human-centric methods in AI development, ensuring alignment with societal norms and welfare, and outlined a strategy for future AI research that focuses on a balanced and conscientious use of MoE, multimodality, and AGI in generative AI.
55
Towards an Understanding of Large Language Models in Software Engineering Tasks
Zibin Zheng,Kai-Chun Ning,Jiachi Chen,Yanlin Wang,Wenqing Chen,Lianghong Guo,Weicheng Wang +6 more
TL;DR: This paper is the first to comprehensively investigate and collate the research and products combining LLMs with software engineering, aiming to answer two questions: (1) What are the current integrations of LLMsWith software engineering?
References
•Proceedings Article
Attention is All you Need
Ashish Vaswani,Noam Shazeer,Niki Parmar,Jakob Uszkoreit,Llion Jones,Aidan N. Gomez,Lukasz Kaiser,Illia Polosukhin +7 more
- 12 Jun 2017
TL;DR: This paper proposed a simple network architecture based solely on an attention mechanism, dispensing with recurrence and convolutions entirely and achieved state-of-the-art performance on English-to-French translation.
Bleu: a Method for Automatic Evaluation of Machine Translation
Kishore Papineni,Salim Roukos,Todd Ward,Wei-Jing Zhu +3 more
- 06 Jul 2002
TL;DR: This paper proposed a method of automatic machine translation evaluation that is quick, inexpensive, and language-independent, that correlates highly with human evaluation, and that has little marginal cost per run.
•Posted Content
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Yinhan Liu,Myle Ott,Naman Goyal,Jingfei Du,Mandar Joshi,Danqi Chen,Omer Levy,Michael Lewis,Luke Zettlemoyer,Veselin Stoyanov +9 more
TL;DR: It is found that BERT was significantly undertrained, and can match or exceed the performance of every model published after it, and the best model achieves state-of-the-art results on GLUE, RACE and SQuAD.
•Proceedings Article
Language Models are Few-Shot Learners
Tom B. Brown,Benjamin Mann,Nick Ryder,Melanie Subbiah,Jared Kaplan,Prafulla Dhariwal,Arvind Neelakantan,Pranav Shyam,Girish Sastry,Amanda Askell,Sandhini Agarwal,Ariel Herbert-Voss,Gretchen Krueger,Thomas Henighan,Rewon Child,Aditya Ramesh,Daniel M. Ziegler,Jeffrey Wu,Clemens Winter,Christopher Hesse,Mark Chen,Eric Sigler,Mateusz Litwin,Scott Gray,Benjamin Chess,Jack Clark,Christopher Berner,Samuel McCandlish,Alec Radford,Ilya Sutskever,Dario Amodei +30 more
- 28 May 2020
TL;DR: GPT-3 achieves strong performance on many NLP datasets, including translation, question-answering, and cloze tasks, as well as several tasks that require on-the-fly reasoning or domain adaptation, such as unscrambling words, using a novel word in a sentence, or performing 3-digit arithmetic.
•Proceedings Article
Sequence to Sequence Learning with Neural Networks
Ilya Sutskever,Oriol Vinyals,Quoc V. Le +2 more
- 08 Dec 2014
TL;DR: The authors used a multilayered Long Short-Term Memory (LSTM) to map the input sequence to a vector of a fixed dimensionality, and then another deep LSTM to decode the target sequence from the vector.