Quantum Text Classifier -- A Synchronistic Approach Towards Classical and Quantum Machine Learning
It addresses the problem of demonstrating quantum machine learning feasibility for text classification, but it is incremental as it builds on existing quantum algorithms without major breakthroughs.
The paper tackles the lack of a working quantum machine learning pipeline for text classification by introducing the Quantum Text Classifier (QTC), an end-to-end framework that combines classical pre- and post-processing with quantum algorithms, implemented using IBM Qiskit and backends.
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.