VNU-UET Repository

API parameter recommendation based on language model and program analysis

Tran, Manh Cuong and Tran, Trung Kien and Nguyen, Minh Tan and Nguyen, Thu Trang and Nguyen, Son and Vo, Dinh Hieu (2021) API parameter recommendation based on language model and program analysis. In: THE 28TH ASIA-PACIFIC SOFTWARE ENGINEERING CONFERENCE.

Download (263kB) | Preview


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.

Item Type: Conference or Workshop Item (Paper)
Subjects: Information Technology (IT)
ISI/Scopus indexed conference
Divisions: Faculty of Information Technology (FIT)
Depositing User: Thu-Trang Nguyen
Date Deposited: 10 Dec 2021 10:57
Last Modified: 10 Dec 2021 10:57

Actions (login required)

View Item View Item