Adapting Pre-trained Language Models for Quantum Natural Language Processing
This work addresses the performance limitations of quantum NLP models for researchers in quantum computing and natural language processing, representing an incremental advancement in the classical-quantum transfer learning paradigm.
The paper tackled the problem of adapting pre-trained language models for quantum natural language processing, achieving a 50% to 60% increase in capacity for end-to-end quantum models in sentence classification tasks.
The emerging classical-quantum transfer learning paradigm has brought a decent performance to quantum computational models in many tasks, such as computer vision, by enabling a combination of quantum models and classical pre-trained neural networks. However, using quantum computing with pre-trained models has yet to be explored in natural language processing (NLP). Due to the high linearity constraints of the underlying quantum computing infrastructures, existing Quantum NLP models are limited in performance on real tasks. We fill this gap by pre-training a sentence state with complex-valued BERT-like architecture, and adapting it to the classical-quantum transfer learning scheme for sentence classification. On quantum simulation experiments, the pre-trained representation can bring 50\% to 60\% increases to the capacity of end-to-end quantum models.