Year: 2021
Type: preprint
Abstract: With the growth of natural language processing techniques and demand for improved software engineering efficiency, there is an emerging interest in translating intention from human languages to programming languages. 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 draw parallels with program synthesis efforts. We then consider semantic parsing works from an evolutionary perspective, with specific analyses on neuro-symbolic methods, architecture, and supervision. We then analyze advancements in frameworks for semantic parsing for code generation. In closing, we present what we believe are some of the emerging open challenges in this domain.
Source: arXiv (Cornell University)
Authors: Lee, Celine, Gottschlich, Justin, Roth, Dan
Institutions: Intel (United States), University of Pennsylvania
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3161250433