Quantum Text Classifier -- A Synchronistic Approach Towards Classical and Quantum Machine Learning

TL;DR

This paper introduces a novel quantum text classification framework called Quantum Text Classifier (QTC), combining classical pre- and post-processing with quantum machine learning algorithms for end-to-end text classification.

Contribution

It presents the first end-to-end quantum text classification pipeline integrating classical and quantum components, with implementation using IBM Qiskit.

Findings

Successful implementation of QTC framework

Demonstration of quantum algorithms for text classification

Potential for quantum advantage in NLP tasks

Abstract

Although it will be a while before a practical quantum computer is available, there is no need to hold off. Methods and algorithms are being developed to demonstrate the feasibility of running machine learning (ML) pipelines in QC (Quantum Computing). There is a lot of ongoing work on general QML (Quantum Machine Learning) algorithms and applications. However, a working model or pipeline for a text classifier using quantum algorithms isn't available. This paper introduces quantum machine learning w.r.t text classification to readers of classical machine learning. It begins with a brief description of quantum computing and basic quantum algorithms, with an emphasis on building text classification pipelines. A new approach is introduced to implement an end-to-end text classification framework (Quantum Text Classifier - QTC), where pre- and post-processing of data is performed on a classical computer, and text classification is performed using the QML algorithm. This paper also presents an implementation of the QTC framework and available quantum ML algorithms for text classification using the IBM Qiskit library and IBM backends.