Linguine: A Natural-Language Programming Language with Formal Semantics and a Clean Compiler Pipeline

Abstract: Linguine is a natural-language-inspired programming language that enables users to write programs in a fluent, controlled subset of English while preserving formal semantics. The language introduces anaphoric constructs, such as pronoun variables (e.g., "it", "them"), that are statically resolved through referent-tracking analysis combined with a Hindley-Milner-style type system. Each pronoun is guaranteed to be unambiguous and well-typed at compile time. The Linguine compiler pipeline includes lexing, parsing, clause graph construction, desugaring into a typed intermediate representation, type inference, and abstract interpretation. This enables the early detection of semantic errors, such as undefined or type-inconsistent references. A lightweight backend currently generates Python code. This paper formalizes the core language, defines its typing and operational semantics, and proves the soundness of its pronoun resolution mechanism. An initial evaluation shows that Linguine allows the expression of concise and readable programs while supporting static verification. Linguine represents a step toward programming systems that prioritize human linguistic intuition while remaining grounded in formal methods and type-theoretic rigor.