A Survey on Semantic Parsing for Machine Programming

Over the last decade, the fields of natural language processing and understanding have seen major advances. Yet, while some of these techniques can be applied to programming language processing and understanding, there remain some fundamental differences. In this survey paper, we attempt to provide an overview of the growing body of research in this space. We begin by reviewing natural language semantic parsing techniques and extracting lessons from the evolution of semantic parsing. We then draw parallels between modern efforts in neural semantic parsing and program synthesis. In closing, we present what we believe are some of the emerging open challenges in this domain.