Abstract Hybrid quantum-classical classifiers promise to positively impact critical aspects of natural language processing tasks, particularly classification-related ones. Among the possibilities currently investigated, quantum transfer learning, i.e., using a quantum circuit for fine-tuning pre-trained classical models for a specific task, is attracting significant attention as a potential platform for proving quantum advantage. This work shows potential advantages, in terms of both performance and expressiveness, of quantum transfer learning algorithms trained on embedding vectors extracted from a large language model to perform classification on a classical linguistics task—acceptability judgements. Acceptability judgement is the ability to determine whether a sentence is considered natural and well-formed by a native speaker. The approach has been tested on sentences extracted from ItaCoLa, a corpus that collects Italian sentences labeled with their acceptability judgement. The evaluation phase shows results for the quantum transfer learning pipeline comparable to state-of-the-art classical transfer learning algorithms, proving current quantum computers’ capabilities to tackle NLP tasks for ready-to-use applications. Furthermore, a qualitative linguistic analysis, aided by explainable AI methods, reveals the capabilities of quantum transfer learning algorithms to correctly classify complex and more structured sentences, compared to their classical counterpart. This finding sets the ground for a quantifiable quantum advantage in NLP in the near future.
Abstract Hybrid quantum-classical classifiers promise to positively impact critical aspects of natural language processing tasks, particularly classification-related ones. Among the possibilities currently investigated, quantum transfer learning, i.e., using a quantum circuit for fine-tuning pre-trained classical models for a specific task, is attracting significant attention as a potential platform for proving quantum advantage. This work shows potential advantages, in terms of both performance and expressiveness, of quantum transfer learning algorithms trained on embedding vectors extracted from a large language model to perform classification on a classical linguistics task—acceptability judgements. Acceptability judgement is the ability to determine whether a sentence is considered natural and well-formed by a native speaker. The approach has been tested on sentences extracted from ItaCoLa, a corpus that collects Italian sentences labeled with their acceptability judgement. The evaluation phase shows results for the quantum transfer learning pipeline comparable to state-of-the-art classical transfer learning algorithms, proving current quantum computers’ capabilities to tackle NLP tasks for ready-to-use applications. Furthermore, a qualitative linguistic analysis, aided by explainable AI methods, reveals the capabilities of quantum transfer learning algorithms to correctly classify complex and more structured sentences, compared to their classical counterpart. This finding sets the ground for a quantifiable quantum advantage in NLP in the near future.
Abstract Hybrid quantum-classical algorithms have emerged as promising candidates for overcoming current limitations of deep learning techniques and recently have attracted a lot of attention for their application in natural language processing (NLP). Among the potential applications of quantum computing in this field, quantum transfer learning—using quantum circuits for fine-tuning pre-trained classical models specific to a task—is regarded as a potential avenue to exploit the potentiality of quantum computers. This study validates, both experimentally and with domain knowledge analysis, the efficacy of quantum transfer learning for two distinct NLP tasks—semantic and syntactic—and employ multilingual data encompassing both English and Italian. In particular is hereby demonstrated that embedded knowledge coming from pre-trained deep learning models can be effectively transferred into a quantum classifier, which shows good performances, either comparable or potentially better than their classical counterparts, with a further reduction of parameters compared to a purely classical classifier. Furthermore, a qualitative linguistic analysis of the results is presented, that elucidates two points: the lack of language dependence in the quantum models and the ability to discriminate with higher precision than standard classifiers, sub-types of linguistic structures.
Exploiting quantum properties to improve performance of different tasks in Natural Language Processing (NLP) and other domains has increasingly becoming a successful trend to deal complex language phenomena or to fill task or domain-specific gaps with an approach that needs less data and minor computational resources. The field that has, to date, yielded more quantum-based attention is the retrieval and classification of textual data. This work aims to replicate the excellent results of hybrid quantum approaches for syntactic tasks on semantic classification tasks. In detail, a quantum machine learning algorithm, namely, the Variational Quantum Classifier (VQC), is used to perform sentiment analysis classification tasks. This algorithm can deduce the relationships between input features and their corresponding class affiliations using a parametrized quantum circuit and an encoding layer that translates classical data into quantum states. The approach has been tested on a well-known benchmark annotated dataset used for the Italian language, and the results have been compared to existing baselines, pointing out state-of-the-art scores.
Abstract Quantum Machine Learning (QML) is a promising field that combines the power of quantum computing with machine learning. Variational quantum circuits, where parameters of circuits are learned classically, have been widely used in many recent applications of QML. This is an instance of a hybrid quantum-classical framework, where both classical and quantum components are present. However, applying these techniques to applications involving massive data is a challenging task. One way to overcome this, is using the concept of classical-quantum transfer learning with the help of dressed quantum circuit, introduced recently, where the underlying neural architecture is pre-trained classically, but at the final steps (decision layer), a quantum circuit is used, followed by quantum measurements and post-processing to classify images with high precision. In this paper, we applied hybrid classical-quantum transfer learning to another task of massive data processing, i.e. Natural Language Processing (NLP). We show how to (binary) classify short texts (e.g., SMS) with classical-quantum transfer learning, which was originally applied to image processing only. Our quantum network was pre-trained by Bidirectional Encoder Representations from the Transformers (BERT) model, and its variational quantum circuit is fine-tuned for text processing. We evaluated the performance of our hybrid neural architecture using the Receiver Operating Characteristic (ROC) curve, which is typically used in the evaluation of classification problems. The results indicate high precision as well as lower loss function. To our knowledge, our work is the first application of quantum transfer learning to the area of NLP. Finally a comparison with a tool that uses learning but in a different way than transfer learning is presented
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.
Abstract In the era of Large Language Models, there is still potential for improvement in current Natural Language Processing (NLP) methods in terms of verifiability and consistency. NLP classical approaches are computationally expensive due to their high-power consumption, computing power, and storage requirements. Another computationally efficient approach to NLP is categorical quantum mechanics, which combines grammatical structure and individual word meaning to deduce the sentence meaning. As both quantum theory and natural language use vector space to describe states which are more efficient on quantum hardware, QNLP models can achieve up to quadratic speedup over classical direct calculation methods. In recent years, there is significant progress in utilizing quantum features such as superposition and entanglement to represent linguistic meaning on quantum hardware. Earlier research work has already demonstrated QNLP’s potential quantum advantage in terms of speeding up search, enhancing classification tasks’ accuracy and providing an exponentially large quantum state space in which complex linguistic structures can be efficiently embedded. In this work, a QNLP model is used to determine if two sentences are related to the same topic or not. By comparing our QNLP model to a classical tensor network-based one, our model improved training accuracy by up to 45% and validation accuracy by 35%, respectively. The QNLP model convergence is also studied when varying: first, the problem size, second, parametrized quantum circuits used for model’s training, and last, the backend quantum simulator noise model. The experimental results show that strongly entangled ansatz designs result in fastest model convergence.
Quantum computing, with its unique principles such as superposition and entanglement, promises to transform various domains, including artificial intelligence. This study investigates the fusion of quantum computing with contemporary AI technologies through quantum transfer learning. We introduce the Complex Quantum Kernel Self-Attention Network (CQKSAN), a novel model that leverages quantum circuits and self-attention mechanisms to boost text classification performance. By applying quantum transfer learning, CQKSAN harnesses the strengths of pre-trained classical models and enhances them with quantum capabilities. Experimental results on multiple binary classification datasets demonstrate that CQKSAN achieves a more efficient learning process. Specifically, it improves training accuracy and validation accuracy by up to 24.31% and 28.35%, respectively, and increases the Matthews Correlation Coefficient by 113.10%. Moreover, CQKSAN consistently outperforms the BERT baseline in both training and validation accuracy across various datasets, showcasing its strong learning capability and generalization performance in handling tasks with diverse linguistic structures and complex semantics. Our findings underscore the potential of hybrid quantum-classical approaches, while also identifying the current limitations and paving the way for future research in fully quantum-based learning systems.