A Bionic Natural Language Parser Equivalent to a Pushdown Automaton

TL;DR

This paper introduces a biologically inspired natural language parser that can handle all regular and context-free languages by integrating neural-inspired structures into an assembly calculus framework.

Contribution

It proposes a novel bionic parser based on assembly calculus with Recurrent and Stack Circuits, enabling it to parse all regular and context-free languages, unlike previous models.

Findings

BNLP can handle all regular languages.

BNLP can parse Dyck languages and context-free languages.

BNLP's automaton is equivalent to a PDA.

Abstract

Assembly Calculus (AC), proposed by Papadimitriou et al., aims to reproduce advanced cognitive functions through simulating neural activities, with several applications based on AC having been developed, including a natural language parser proposed by Mitropolsky et al. However, this parser lacks the ability to handle Kleene closures, preventing it from parsing all regular languages and rendering it weaker than Finite Automata (FA). In this paper, we propose a new bionic natural language parser (BNLP) based on AC and integrates two new biologically rational structures, Recurrent Circuit and Stack Circuit which are inspired by RNN and short-term memory mechanism. In contrast to the original parser, the BNLP can fully handle all regular languages and Dyck languages. Therefore, leveraging the Chomsky-Sch \H{u}tzenberger theorem, the BNLP which can parse all Context-Free Languages can be constructed. We also formally prove that for any PDA, a Parser Automaton corresponding to BNLP can always be formed, ensuring that BNLP has a description ability equal to that of PDA and addressing the deficiencies of the original parser.