ARSeek: Identifying API Resource using Code and Discussion on Stack Overflow
It is not a trivial problem to collect API-relevant examples, usages, and mentions on venues such as Stack Overflow. It requires efforts to correctly recognize whether the discussion refers to the API method that developers/tools are searching for. The content of the Stack Overflow thread, which consists of both text paragraphs describing the involvement of the API method in the discussion and the code snippets containing the API invocation, may refer to the given API method. Leveraging this observation, we develop ARSeek, a context-specific algorithm to capture the semantic and syntactic information of the paragraphs and code snippets in a discussion. ARSeek combines a syntactic word-based score with a score from a predictive model fine tuned from CodeBERT. ARSeek beats the state-of-the-art approach by 14% in terms of F1-score.
Mon 16 MayDisplayed time zone: Eastern Time (US & Canada) change
20:10 - 20:50 | Session 8: Search and Reuse: Libraries & APIsResearch / Replications and Negative Results (RENE) at ICPC room Chair(s): Masud Rahman Dalhousie University | ||
20:10 7mTalk | On the Effectiveness of Pretrained Models for API Learning Research Mohammad Abdul Hadi University of British Columbia, Imam Nur Bani Yusuf Singapore Management University, Ferdian Thung Singapore Management University, Kien Luong School of Computing and Information Systems, Singapore Management University, Fatemeh Hendijani Fard University of British Columbia, Lingxiao Jiang Singapore Management University, David Lo Singapore Management University Media Attached | ||
20:17 7mTalk | Deep API Learning Revisited Replications and Negative Results (RENE) Pre-print Media Attached | ||
20:24 7mTalk | ARSeek: Identifying API Resource using Code and Discussion on Stack Overflow Research Kien Luong School of Computing and Information Systems, Singapore Management University, Mohammad Abdul Hadi University of British Columbia, Ferdian Thung Singapore Management University, Fatemeh Hendijani Fard University of British Columbia, David Lo Singapore Management University Media Attached | ||
20:31 7mTalk | Benchmarking Library Recognition in Tweets Research Ting Zhang Singapore Management University, Divya Prabha CHANDRASEKARAN Singapore Management University, Ferdian Thung Singapore Management University, David Lo Singapore Management University Pre-print Media Attached | ||
20:38 12mLive Q&A | Q&A-Paper Session 8 Research | ||