A Biologically Plausible Parser

TL;DR

This paper introduces a biologically plausible neural network-based parser for English, demonstrating its ability to parse complex sentences and discussing extensions to other languages and linguistic features.

Contribution

It presents a novel neural network parser based on the Assembly Calculus, bridging cognitive neuroscience and natural language processing.

Findings

Successfully parsed nontrivial English sentences

Demonstrated potential for multilingual extension

Discussed handling of recursion, embedding, and polysemy

Abstract

We describe a parser of English effectuated by biologically plausible neurons and synapses, and implemented through the Assembly Calculus, a recently proposed computational framework for cognitive function. We demonstrate that this device is capable of correctly parsing reasonably nontrivial sentences. While our experiments entail rather simple sentences in English, our results suggest that the parser can be extended beyond what we have implemented, to several directions encompassing much of language. For example, we present a simple Russian version of the parser, and discuss how to handle recursion, embedding, and polysemy.