.png){kind=icon}
.png){kind=icon}
Return
A syntax-guided multi-task learning approach for Turducken-style code generation
.png){kind=icon}
PRE
AI
DOI：10.1007/s10664-023-10372-1.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Due to the development of pre-trained language models, automated code generation techniques have shown great promise in recent years. However, the generated code will not always adhere to syntactic constraints of the target language, especially in the case of Turducken-style code, where declarative code snippets are embedded within imperative programs. In this study, we summarize three significant challenges in regards to syntactic constraints: (1) the efficient representation of syntactic constraints, (2) the effective integration of syntactic information, and (3) the scalable syntax-first decoding algorithm. To address these challenges, we propose a syntax-guided multi-task learning approach TurduckenGen. Specifically, we first explicitly append the type information to the code tokens to capture the representation of syntactic constraints. Then we formalize code generation with syntactic constraint representation as an auxiliary task to enable the model to learn the syntactic constraints of the code. Finally, the syntactically correct code is selected accurately from the multiple candidates with the help of the compiler feedback. Extensive experiments and comprehensive analysis demonstrate the effectiveness and general applicability of our approach after being compared with six state-of-the-art baselines on two Turducken-style code datasets. Finally, we conducted a human study and found the code quality generated by our approach is better than baselines in terms of code readability and semantic similarity.
Keywords:
Syntactically-constrained code generation
Turducken-style code
Multi-task learning
CodeT5
Abstract syntax tree
Journal
IF:
3.6
Papers:
1.9K
Citations:
5.3K