A Semantic and Structural Transformer for Code Summarization Generation | |
Ruyi Ji3; Zhenyu Tong2; Tiejian Luo2; Jing Liu3; Libo Zhang1 | |
2023 | |
会议日期 | 2023.6.8 |
会议地点 | 澳大利亚 |
英文摘要 | Currently most methods cast code summarization generation as a machine translation task. Wherein the Transformer framework is a representative among them. Thanks to the attention mechanism in the Transformer, such a framework has achieved the state-of-the-art performance. Unfortunately, the Transformer encounters a series of challenges when generalizing to code summarization generation domain. Compared with natural language, code sequence is characterized by more complex multi-modal features, and difficult to extract these features only by the original Transformer structure. To further improve the performance, we make full use of code semantic and structural information in abstract syntax tree to build a simple yet effective framework, which consists of self-attention and graph based module to integrate code semantic information and syntax tree structure information. Besides, to compensate for the insufficiency of Transformer in encoding local features, we present a well-designed local RNN module. Extensive experiments show that the proposed method performs on par with the state-of-the-art methods on two public benchmarks, including Java and Python datasets. The comprehensive ablation studies further demonstrate the effectiveness of architecture design choices. The source code is released at https://github.com/tzv314159/SSTrans.git. |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/58515] ![]() |
专题 | 自动化研究所_模式识别国家重点实验室_图像与视频分析团队 |
通讯作者 | Libo Zhang |
作者单位 | 1.Institute of Software Chinese Academy of Sciences 2.University of Chinese Academy of Sciences 3.Institute of Automation Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Ruyi Ji,Zhenyu Tong,Tiejian Luo,et al. A Semantic and Structural Transformer for Code Summarization Generation[C]. 见:. 澳大利亚. 2023.6.8. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论