Speaker: Eran Yahav, Technion
Title: PROGRAMMING WITH MILLIONS OF EXAMPLES
Abstract:
We
present a framework for data-driven synthesis, aiming to leverage the
collective programming knowledge captured in millions of open-source
projects. Our framework analyzes code snippets and extracts partial
temporal specifications. Technically, partial temporal specifications
are represented as symbolic automata – automata where transitions may be
labeled by variables, and a variable can be substituted by a letter, a
word, or a regular language. Using symbolic automata, we consolidate
separate examples to create a database of snippets that can be used for
semantic code-search and component synthesis. We have implemented our
approach in a tool called PRIME and applied it to analyze and
consolidate thousands of snippets per tested API.
This talk is based on work with Hila Peleg, Alon Mishne, Sharon Shoham, and Hongseok Yang