Mon 18 Jun 2018 11:30 - 12:00 at Columbus Ballroom A - Code Search

Searching over large code corpora can be a powerful productivity tool for both beginner and experienced developers because it helps them quickly find examples of code related to their intent. Code search becomes even more attractive if developers could express their intent in natural language, similar to the interaction that Stack Overflow supports.

In this paper, we investigate the use of natural language processing and information retrieval techniques to carry out natural language search directly over source code, i.e. without having a curated Q&A forum such as Stack Overflow at hand. Our preliminary experiments using a benchmark derived from Stack Overflow and GitHub repositories shows promising results.

Mon 18 Jun

mapl-2018-papers
11:00 - 12:00: MAPL 2018 - Code Search at Columbus Ballroom A
mapl-2018-papers11:00 - 11:30
Talk
Fang-Hsiang SuColumbia University, New York, Jonathan BellGeorge Mason University, Gail KaiserColumbia University, New York, Baishakhi RayColumbia University, New York
mapl-2018-papers11:30 - 12:00
Talk
Saksham SachdevFacebook, Hongyu LiRice University, Sifei LuanFacebook, Seohyun KimFacebook, Koushik SenUniversity of California, Berkeley, Satish ChandraFacebook