Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

International Conference on Evolutionary Computing and Mobile Sustainable Networks (ICECMSN)

QESAN: A Quantum-Enhanced Semantic Attention Network for Accurate Text Classification

S.Amsaveni, P. Lalithamani, S. Punithadevi, J.Dhivya

Published Nov 24, 2025• 1 citation
Publisher

Abstract

Text classification remains among the most significant tasks in natural language processing and the field has been used in healthcare, law, social media analysis, and economic literature. Classical attention networks existing machine learning approaches and deep learning approaches, including LSTM, BiLSTM, Transformers, and classical attention networks, are susceptible to such problems as long-range dependencies and semantic ambiguity, as well as sparse or underrepresented text. To deal with these deficiencies, this research presents a proposed a Quantum-Enhanced Semantic Attention Network (QESAN), a quantum computing concept integrated into semantic attention-based deep learning paradigm. The proposed QESAN coded textual features using amplitude encoding, quantum superposition, and entanglement-like transformations, such that the model is able to learn not only complex relations between interdependencies, but also fairly subtle semantic relations which are generally hard to learn on classical models. The result of these quantum-enhanced representations is then sent through an attention mechanism which acts on the most semantically significant aspects to produce results that are context-sensitive and can be interpreted. The Kaggle Quantum Programming experimental results indicate that QESAN is effective with accuracy of 98.7 which is far superior than the LSTM, BiLSTM, Transformer, and classical attention networks. The results indicate the ability of QESAN to solve the conventional issues of the text classification process particularly in the assignment of dealing with the long-range dependencies, semantic ambiguity, and sparse data. Overall, the integration of the concept of quantum computing with the attention-based deep learning provides the scalable and resilient solution to the issue of the modern text classification problems of the high-performance.

DOI
10.1109/icecmsn68058.2025.11382896

Related papers

Advancing Textual Semantic Understanding with Quantum LSTM Networks

Muhammad Mustafa Umar Gondel, Kyung Min Byun, Hyundong Shin

Long Short-Term Memory (LSTM) networks are adept at managing long-term dependencies in sequential data, making them particularly effective for understanding semantics in context. However, challenges such as language complexity and data limitations persist in natural language processing (NLP). Quantum computing utilizes quantum mechanics to tackle complex language structures with limited data. By integrating quantum computing with LSTM, we can address the issues of linguistic complexity and data scarcity. In this paper, we present a Quantum Long Short-Term Memory (QLSTM) network that comprehends the semantics of textual data. Our simulations demonstrate superior capability of QLSTM in capturing textual semantics.

International Conference on Information and Communication Technology Convergence (ICTC)•Oct 16, 2024•2 citations

Enhancing Text Classification Through Quantum Transfer Learning: A Hybrid Quantum-Classical Approach With Complex Kernel Self-Attention Networks

Xiaoxiao Chen, Xiaoping Lou

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.

IEEE Access•Jan 1, 2025•5 citations

Q-EntangleFormer: A Quantum-Entanglement Transformer Framework for Contextual Semantic Disambiguation

Dalydas Karanath, Udai Shankar

Word Sense Disambiguation (WSD) is one of the unresolved issues in natural language processing because polysemous words are inherently ambiguous and require semantic interpretation based on the context. Transformerbased models have made considerable progress in contextual modelling still, they cannot address fine-grained sense distinctions, long-range dependencies, and sentences containing multiple ambiguous words interacting with each other. At the same time quantum-inspired methods also take advantage of superposition and interference to model ambiguity, although generally only at the word level, and do not do contextual propagation. This paper presents Q-EntangleFormer, a new hybrid quantum-classical Transformer based on a unified quantum multi-sense superposition encoding, contextual entanglement of words, and quantum-enhanced attention of deep contextual WSD. The unclear word is represented as a quantum superposition of the possible meanings, the dependence between the context and sense is represented by entanglement networks and the hybrid attention model can combine classical and quantum signals with a fusion gate. Empirical testing of standard WSD metrics indicates that QEntangleFormer has significantly better accuracy than both classical Transformer models and current quantum WSD approaches. The framework also shows that it is parameterefficiently scalable and that it is better understood through amplitude-based semantic reasoning. It therefore connects quantum representation theory and contextual semantic modelling and points to a new direction of quantum-augmented natural language understanding.

International Conference on Communication, Computing and Electronics Systems (ICCCES)•Jan 21, 2026•0 citations

Quantum-Enhanced Attention Mechanism in NLP: A Hybrid Classical-Quantum Approach

S. M. Yousuf Iqbal Tomal, Abdullah Al Shafin, Bhattacharjee, Debojit +2 more

Recent advances in quantum computing have opened new pathways for enhancing deep learning architectures, particularly in domains characterized by high-dimensional and context-rich data such as natural language processing (NLP). In this work, we present a hybrid classical-quantum Transformer model that integrates a quantum-enhanced attention mechanism into the standard classical architecture. By embedding token representations into a quantum Hilbert space via parameterized variational circuits and exploiting entanglement-aware kernel similarities, the model captures complex semantic relationships beyond the reach of conventional dot-product attention. We demonstrate the effectiveness of this approach across diverse NLP benchmarks, showing improvements in both efficiency and representational capacity. The results section reveal that the quantum attention layer yields globally coherent attention maps and more separable latent features, while requiring comparatively fewer parameters than classical counterparts. These findings highlight the potential of quantum-classical hybrid models to serve as a powerful and resource-efficient alternative to existing attention mechanisms in NLP.

arXiv:2501.15630•Jan 26, 2025•3 citations

Hybrid Encoding-based Quantum Self Attention for Financial Time Series Analysis

S Lokes, Suresh Reddy, Samuel Yen Chi Chen

Self-attention mechanisms, central to Transformer architectures, have become foundational in the development of large language models (LLMs) and various advanced machine learning systems. These mechanisms are pivotal for effectively capturing complex data dependencies and relationships, which is crucial for tasks such as natural language understanding and generation. However, as dimensionality increases, self-attention mechanisms face significant challenges related to computational efficiency and scalability. This paper introduces an encoding-based quantum self-attention mechanism designed to address these issues by embedding classical data into quantum states. This approach facilitates more efficient computation and reduces model complexity. To further enhance performance for real-world applications, particularly in financial time series forecasting, we propose a hybrid model that integrates Long Short-Term Memory (LSTM) networks with quantum self-attention mechanism. Given the constraints of the Noisy Intermediate-Scale Quantum (NISQ) era, this hybrid approach represents a plausible solution, leveraging the strengths of both classical and quantum methods and focusing on achieving faster convergence. Experimental results demonstrate that our approach converges significantly quicker than traditional models, showcasing the advantages of integrating quantum techniques with classical machine learning for practical applications.

IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)•Apr 6, 2025•1 citation

Classification of texts based on classical and quantum features

Nilufar A’loxanovna Niyozmatova, N. M. Turgunova, Нигора Нурмахамадовна Абдурахманова +1 more

This article proposes classical and quantum vectorization methods for text data classification, along with corresponding neural network architectures for classification based on these representations. The study applies classical and quantum variants of one-hot encoding, bag-of-words, TF-IDF, and word2vec vectorization techniques, which are respectively integrated with CNN, LSTM, MLP, and BiLSTM neural network models for text classification. All models are trained on the same dataset under identical experimental conditions, with classification accuracy and computational efficiency adopted as the primary evaluation metrics. Classical vectorization methods represent semantic and contextual properties of text in a limited manner, whereas quantum vectorization overcomes these limitations. When neural networks are trained using quantum-based representations, higher classification accuracy and significantly reduced computation time are achieved compared to classical approaches. The combined use of quantum word2vec and the BiLSTM architecture yields the highest performance among all evaluated models. The obtained results demonstrate that this approach is the most effective for text data classification, as it accurately captures semantic relationships and leverages deep neural network architectures. This study may serve as a scientific foundation for future research aimed at developing more advanced neural architectures based on quantum computing paradigms.

InterConf•Feb 23, 2026•0 citations
Text classification remains among the most significant tasks in natural language processing and the field has been used in healthcare, law, social media analysis, and economic literature. Classical attention networks existing machine learning approaches and deep learning approaches, including LSTM, BiLSTM, Transformers, and classical attention networks, are susceptible to such problems as long-range dependencies and semantic ambiguity, as well as sparse or underrepresented text. To deal with these deficiencies, this research presents a proposed a Quantum-Enhanced Semantic Attention Network (QESAN), a quantum computing concept integrated into semantic attention-based deep learning paradigm. The proposed QESAN coded textual features using amplitude encoding, quantum superposition, and entanglement-like transformations, such that the model is able to learn not only complex relations between interdependencies, but also fairly subtle semantic relations which are generally hard to learn on classical models. The result of these quantum-enhanced representations is then sent through an attention mechanism which acts on the most semantically significant aspects to produce results that are context-sensitive and can be interpreted. The Kaggle Quantum Programming experimental results indicate that QESAN is effective with accuracy of 98.7 which is far superior than the LSTM, BiLSTM, Transformer, and classical attention networks. The results indicate the ability of QESAN to solve the conventional issues of the text classification process particularly in the assignment of dealing with the long-range dependencies, semantic ambiguity, and sparse data. Overall, the integration of the concept of quantum computing with the attention-based deep learning provides the scalable and resilient solution to the issue of the modern text classification problems of the high-performance.
Long Short-Term Memory (LSTM) networks are adept at managing long-term dependencies in sequential data, making them particularly effective for understanding semantics in context. However, challenges such as language complexity and data limitations persist in natural language processing (NLP). Quantum computing utilizes quantum mechanics to tackle complex language structures with limited data. By integrating quantum computing with LSTM, we can address the issues of linguistic complexity and data scarcity. In this paper, we present a Quantum Long Short-Term Memory (QLSTM) network that comprehends the semantics of textual data. Our simulations demonstrate superior capability of QLSTM in capturing textual semantics.
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.
Word Sense Disambiguation (WSD) is one of the unresolved issues in natural language processing because polysemous words are inherently ambiguous and require semantic interpretation based on the context. Transformerbased models have made considerable progress in contextual modelling still, they cannot address fine-grained sense distinctions, long-range dependencies, and sentences containing multiple ambiguous words interacting with each other. At the same time quantum-inspired methods also take advantage of superposition and interference to model ambiguity, although generally only at the word level, and do not do contextual propagation. This paper presents Q-EntangleFormer, a new hybrid quantum-classical Transformer based on a unified quantum multi-sense superposition encoding, contextual entanglement of words, and quantum-enhanced attention of deep contextual WSD. The unclear word is represented as a quantum superposition of the possible meanings, the dependence between the context and sense is represented by entanglement networks and the hybrid attention model can combine classical and quantum signals with a fusion gate. Empirical testing of standard WSD metrics indicates that QEntangleFormer has significantly better accuracy than both classical Transformer models and current quantum WSD approaches. The framework also shows that it is parameterefficiently scalable and that it is better understood through amplitude-based semantic reasoning. It therefore connects quantum representation theory and contextual semantic modelling and points to a new direction of quantum-augmented natural language understanding.
Recent advances in quantum computing have opened new pathways for enhancing deep learning architectures, particularly in domains characterized by high-dimensional and context-rich data such as natural language processing (NLP). In this work, we present a hybrid classical-quantum Transformer model that integrates a quantum-enhanced attention mechanism into the standard classical architecture. By embedding token representations into a quantum Hilbert space via parameterized variational circuits and exploiting entanglement-aware kernel similarities, the model captures complex semantic relationships beyond the reach of conventional dot-product attention. We demonstrate the effectiveness of this approach across diverse NLP benchmarks, showing improvements in both efficiency and representational capacity. The results section reveal that the quantum attention layer yields globally coherent attention maps and more separable latent features, while requiring comparatively fewer parameters than classical counterparts. These findings highlight the potential of quantum-classical hybrid models to serve as a powerful and resource-efficient alternative to existing attention mechanisms in NLP.
Self-attention mechanisms, central to Transformer architectures, have become foundational in the development of large language models (LLMs) and various advanced machine learning systems. These mechanisms are pivotal for effectively capturing complex data dependencies and relationships, which is crucial for tasks such as natural language understanding and generation. However, as dimensionality increases, self-attention mechanisms face significant challenges related to computational efficiency and scalability. This paper introduces an encoding-based quantum self-attention mechanism designed to address these issues by embedding classical data into quantum states. This approach facilitates more efficient computation and reduces model complexity. To further enhance performance for real-world applications, particularly in financial time series forecasting, we propose a hybrid model that integrates Long Short-Term Memory (LSTM) networks with quantum self-attention mechanism. Given the constraints of the Noisy Intermediate-Scale Quantum (NISQ) era, this hybrid approach represents a plausible solution, leveraging the strengths of both classical and quantum methods and focusing on achieving faster convergence. Experimental results demonstrate that our approach converges significantly quicker than traditional models, showcasing the advantages of integrating quantum techniques with classical machine learning for practical applications.
This article proposes classical and quantum vectorization methods for text data classification, along with corresponding neural network architectures for classification based on these representations. The study applies classical and quantum variants of one-hot encoding, bag-of-words, TF-IDF, and word2vec vectorization techniques, which are respectively integrated with CNN, LSTM, MLP, and BiLSTM neural network models for text classification. All models are trained on the same dataset under identical experimental conditions, with classification accuracy and computational efficiency adopted as the primary evaluation metrics. Classical vectorization methods represent semantic and contextual properties of text in a limited manner, whereas quantum vectorization overcomes these limitations. When neural networks are trained using quantum-based representations, higher classification accuracy and significantly reduced computation time are achieved compared to classical approaches. The combined use of quantum word2vec and the BiLSTM architecture yields the highest performance among all evaluated models. The obtained results demonstrate that this approach is the most effective for text data classification, as it accurately captures semantic relationships and leverages deep neural network architectures. This study may serve as a scientific foundation for future research aimed at developing more advanced neural architectures based on quantum computing paradigms.