Towards Automatic Composition of ASP Programs from Natural Language Specifications
This addresses the challenge of automating ASP coding for researchers and practitioners, but it is incremental as it moves the first step with a specific dataset and tool.
The paper tackles the problem of automatically composing Answer Set Programming (ASP) programs from natural language specifications, introducing a dataset for graph-related problems and a two-step architecture (NL2ASP) that uses neural machine translation and conversion tools, with an experiment confirming its viability.
This paper moves the first step towards automating the composition of Answer Set Programming (ASP) specifications. In particular, the following contributions are provided: (i) A dataset focused on graph-related problem specifications, designed to develop and assess tools for ASP automatic coding; (ii) A two-step architecture, implemented in the NL2ASP tool, for generating ASP programs from natural language specifications. NL2ASP uses neural machine translation to transform natural language into Controlled Natural Language (CNL) statements. Subsequently, CNL statements are converted into ASP code using the CNL2ASP tool. An experiment confirms the viability of the approach.