Comparative study of the ans\"atze in quantum language models

TL;DR

This paper systematically compares various ansätze in quantum language models for text classification, analyzing how their complexity and hyperparameters influence performance, and provides insights for developing improved QNLP algorithms.

Contribution

It offers the first comprehensive comparison of different ansätze in quantum language models, highlighting their impact on model performance and guiding future improvements.

Findings

Performance varies with ansatz complexity and hyperparameters.

Optimized hyperparameters improve classification accuracy.

Balance between simplicity and expressivity is crucial.

Abstract

Quantum language models are the alternative to classical language models, which borrow concepts and methods from quantum machine learning and computational linguistics. While several quantum natural language processing (QNLP) methods and frameworks exist for text classification and generation, there is a lack of systematic study to compare the performance across various ans\"atze, in terms of their hyperparameters and classical and quantum methods to implement them. Here, we evaluate the performance of quantum natural language processing models based on these ans\"atze at different levels in text classification tasks. We perform a comparative study and optimize the QNLP models by fine-tuning several critical hyperparameters. Our results demonstrate how the balance between simplification and expressivity affects model performance. This study provides extensive data to improve our understanding of QNLP models and opens the possibility of developing better QNLP algorithms.