TranS^3: A Transformer-based Framework for Unifying Code Summarization and Code Search
By Wenhua Wang, Yuqun Zhang, Zhengran Zeng, Guandong Xu. 2020
40 citations recorded by the source corpus.
Code summarization and code search have been widely adopted in sofwaredevelopmentandmaintenance. However, fewstudieshave explored the efcacy of unifying them. In this paper, we propose TranS^3 , a transformer-based framework to integrate code summarization with code search. Specifcally, for code summarization,TranS^3 enables an actor-critic network, where in the actor network, we encode the collected code snippets via transformer- and tree-transformer-based encoder and decode the given code snippet to generate its comment. Meanwhile, we iteratively tune the actor network via the feedback from the critic network for enhancing the quality of the generated comments. Furthermore, we import the generated comments to code search for enhancing its accuracy. To evaluatetheefectivenessof TranS^3 , we conduct a set of experimental studies and case studies where the experimental results suggest that TranS^3 can signifcantly outperform multiple state-of-the-art approaches in both code summarization and code search and the study results further strengthen the efcacy of TranS^3 from the developers' points of view.
Subfields: Artificial Intelligence, Information Systems, Software, Model Architectures, Code Generation & Program Synthesis
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Colin B. Clement
- Neel Sundaresan
- Alexey Svyatkovskiy
- Dawn Drain
- Jonathan Timcheck
- Steven C. H. Hoi
- Yue Wang
In Information Systems
In Software
In Model Architectures
In Code Generation & Program Synthesis
Citations in the corpus
- PyMT5: Multi-mode Translation of Natural Language and Python Code with Transformers (2020, background): “TranS 3 by Wang et al. (Wang et al., 2020) reports a best ROUGE-L of 51.27 on the same test set for code summarization, but does not specify which statistic they are reporting, so we cannot make strong conclusions about the performance of P Y MT5 compared to the state of the art.”