Kehuan Yan


2024

pdf bib
Quantum-inspired Language Model with Lindblad Master Equation and Interference Measurement for Sentiment Analysis
Kehuan Yan | Peichao Lai | Yilei Wang
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)

Quantum-inspired models have demonstrated superior performance in many downstream language tasks, such as question answering and sentiment analysis. However, recent models primarily focus on embedding and measurement operations, overlooking the significance of the quantum evolution process. In this work, we present a novel quantum-inspired neural network, LI-QiLM, which integrates the Lindblad Master Equation (LME) to model the evolution process and the interferometry to the measurement process, providing more physical meaning to strengthen the interpretability. We conduct comprehensive experiments on six sentiment analysis datasets. Compared to the traditional neural networks, transformer-based pre-trained models and quantum-inspired models, such as CICWE-QNN and ComplexQNN, the proposed method demonstrates superior performance in accuracy and F1-score on six commonly used datasets for sentiment analysis. Additional ablation tests verify the effectiveness of LME and interferometry.