Programming by examples

Abstract

99% of computer users do not know programming and hence struggle with repetitive tasks. Programming by Examples (PBE) can revolutionize this landscape by enabling users to synthesize intended programs from example based specifications. A key technical challenge in PBE is to search for programs that are consistent with the examples provided by the user. Our efficient search methodology is based on two key ideas: (i) Restriction of the search space to an appropriate domain-specific language (ii) A divide-and-conquer based search paradigm that inductively reduces the problem of synthesizing a program with a certain top-level operator to simpler synthesis problems over its sub-programs by leveraging the operator's inverse semantics. Another challenge in PBE is to resolve the ambiguity in the example based specification. Our ambiguity resolution methodology leverages two complementary approaches: (a) machine learning based ranking techniques that can pick an intended program from among those that satisfy the specification, and (b) active-learning based user interaction models. I will illustrate these various concepts using Flash Fill, FlashExtract, and FlashRelate---PBE technologies for data manipulation domains. These technologies, which have been released inside various Microsoft products, are useful for data scientists who spend 80% of their time wrangling with data. The Microsoft PROSE SDK allows easy construction of such technologies.