Macho: Writing Programs with Natural Language and Examples
Anthony Cozzie, Samuel Talmadge King · 2012
Abstract—Current natural language programming systems avoid the difficulties of dealing with abstract and ambiguous concepts by restricting the input words to those comparable to a normal high-level programming language. Our system, language by asking the programmer to provide a unit test: one or more examples of correct input and output. This may seem unnecessarily complicated, but we show that natural language and examples have a surprising synergy both in constraining the ambiguity of the specification and in generating correct solutions. I.