A Pipeline For Discourse Circuits From CCG

TL;DR

This paper presents a software pipeline that converts English text into DisCoCirc representations, bridging linguistic theory and NLP practice, and enabling quantum-compatible semantic modeling.

Contribution

It introduces a pipeline that transforms English text into DisCoCirc circuits using CCG parsing and coreference resolution, facilitating neuro-symbolic and quantum NLP applications.

Findings

Achieves broad coverage of English language fragments.

Successfully converts text into semantic circuits.

Supports implementation on near-term quantum computers.

Abstract

There is a significant disconnect between linguistic theory and modern NLP practice, which relies heavily on inscrutable black-box architectures. DisCoCirc is a newly proposed model for meaning that aims to bridge this divide, by providing neuro-symbolic models that incorporate linguistic structure. DisCoCirc represents natural language text as a `circuit' that captures the core semantic information of the text. These circuits can then be interpreted as modular machine learning models. Additionally, DisCoCirc fulfils another major aim of providing an NLP model that can be implemented on near-term quantum computers. In this paper we describe a software pipeline that converts English text to its DisCoCirc representation. The pipeline achieves coverage over a large fragment of the English language. It relies on Combinatory Categorial Grammar (CCG) parses of the input text as well as coreference resolution information. This semantic and syntactic information is used in several steps to convert the text into a simply-typed $\lambda$-calculus term, and then into a circuit diagram. This pipeline will enable the application of the DisCoCirc framework to NLP tasks, using both classical and quantum approaches.