TY  - CONF
ID  - SisLab4686
UR  - https://eprints.uet.vnu.edu.vn/eprints/id/eprint/4686/
A1  - Tran, Manh Cuong
A1  - Tran, Trung Kien
A1  - Nguyen, Minh Tan
A1  - Nguyen, Thu Trang
A1  - Nguyen, Son
A1  - Vo, Dinh Hieu
Y1  - 2021/12/06/
N2  - APIs are extensively and frequently used in source code to leverage existing libraries and improve programming productivity. However, correctly and effectively using APIs, es- pecially from unfamiliar libraries, is a non-trivial task. Although various approaches have been proposed for recommending API method calls in code completion, suggesting actual parameters for such APIs still needs further investigating. In this paper, we introduce FLUTE, an efficient and novel approach combining program analysis and language models for recommending API parameters. With FLUTE, the source code of programs is first analyzed to generate syntactically legal and type-valid candidates. Then, these candidates are ranked using language models. Our empirical results on two large real-world projects Netbeans and Eclipse indicate that FLUTE achieves 80% and +90% in Top- 1 and Top-5 Precision, which means the tool outperforms the state-of-the-art approach.
TI  - API parameter recommendation based on language model and program analysis
AV  - public
T2  - THE 28TH ASIA-PACIFIC SOFTWARE ENGINEERING CONFERENCE
ER  -