Quantum Text Encoding for Classification Tasks

TL;DR

This paper demonstrates a quantum approach to sentiment analysis that improves accuracy on real-world data using amplitude encoding and quantum SVMs, marking progress in quantum NLP.

Contribution

It introduces a scalable quantum text encoding method combined with quantum SVMs for sentiment classification on real datasets, surpassing previous quantum NLP results.

Findings

Achieved 62% average sentiment prediction accuracy on movie reviews.

Used amplitude encoding with quantum support vector machines.

Improved over prior quantum NLP results with larger, real-world datasets.

Abstract

This paper explores text classification on quantum computers. Previous results have achieved perfect accuracy on an artificial dataset of 100 short sentences, but at the unscalable cost of using a qubit for each word. This paper demonstrates that an amplitude encoded feature map combined with a quantum support vector machine can achieve 62% average accuracy predicting sentiment using a dataset of 50 actual movie reviews. This is still small, but considerably larger than previously-reported results in quantum NLP.