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

IEEE International Conference on Acoustics Speech and Signal Processing

The Dawn of Quantum Natural Language Processing

R. Di Sipio, Jia-Hong Huang, Samuel Yen-Chi Chen, Stefano Mangini, Marcel Worring

Published Apr 27, 2022• 124 citations
Publisher

Abstract

In this paper, we discuss the initial attempts at boosting understanding human language based on deep-learning models with quantum computing. We successfully train a quantum-enhanced Long Short-Term Memory network to perform the parts-of-speech tagging task via numerical simulations. Moreover, a quantum-enhanced Transformer is proposed to perform the sentiment analysis based on the existing dataset.

DOI
10.1109/icassp43922.2022.9747675

Related papers

The Dawn of Quantum Natural Language Processing

R. Di Sipio, Jia-Hong Huang, Samuel Yen-Chi Chen +2 more

In this paper, we discuss the initial attempts at boosting understanding human language based on deep-learning models with quantum computing. We successfully train a quantum-enhanced Long Short-Term Memory network to perform the parts-of-speech tagging task via numerical simulations. Moreover, a quantum-enhanced Transformer is proposed to perform the sentiment analysis based on the existing dataset.

arXiv:2110.06510•Oct 13, 2021•7 citations

Parts of speech tagging towards classical to quantum computing

Shyambabu Pandey, Pankaj Dadure, Morrel V. L. Nunsanga +1 more

Quantum computing is a fast-emerging field that follows the laws of quantum mechanics to solve complex problems for classical systems. In the last few years, several researchers have emerged in quantum computing in accordance with the artificial intelligence field. Natural language processing is one of the prominent subfields of artificial intelligence. Quantum computing can be applied to the applications of natural language processing for better performance. One of the vital applications of natural language processing is Parts-Of-Speech (POS) tagging. It is prerequired for many natural language processing applications. In this paper, we have performed POS tagging of the Mizo language using classical Long short-term memory (LSTM). Subsequently, quantum-enhanced long short-term memory (QLSTM) has also been used to perform POS tagging of the Mizo language. The approaches mentioned above have been tested on the Mizo-tagged corpus, and experimental results have shown that quantum computing approaches such as QLSTM need the inclusion of new technologies to achieve significant results.

IEEE Silchar Subsection Conference (SILCON)•Nov 4, 2022•8 citations

Integrating Quantum Computing with Deep Learning for Enhanced Natural Language Processing

Anand Singh Rajawat, Hussein Mohammed Breesam, Shruti Goyal

Quantum computing with its capacity to compute multiple possibilities at once, and perform some kinds of calculations almost instantly is one leading edge. The integration of QCs and DL undoubtedly represent one such transformative means for improving Natural Language Processing (NLP). By combining the two, this uses quantum principles of superposition and entanglement to make computation faster regarding human language comprehension limitations in classical computing. Deep learning models, specifically neural networks have already made significant improvements over NLP tasks like language translations, sentiment analysis and text generation. Nevertheless, these models also face scalability and computational efficiency issues with huge volumes of data. Quantum computing offers a solution to all this by reducing the time exponentially that it takes to fetch large amounts of language data and running deep learning algorithms. This paper investigates the opportunities that integrating quantum computing and deep learning into NLP practices might unlock. We drafted the fundamentals of quantum computing and why it is a need over classical computing, where we discussed on how quantum beneficial for data processing & optimization of an algorithm. We then explore applications of quantum enhanced deep learning for NLP, with a focus on the impact that training and inference can have on model performance. We demonstrate the utility of this integration by integrating our four SQDs to showcase improvements on diverse NLP tasks through a series of experiments and case studies. We also demonstrate that hybrid quantum-classical approaches allow the combination of traditional ML and quantum-enhanced models, achieving state-of-the-art performance with respect to effectiveness, scalability and precision

International Conference on Augmented Reality, Intelligent Systems, and Industrial Automation (ARIIA)•Dec 20, 2024•0 citations

Integrating Quantum Model Computing With Machine Learning: Quantum Algorithms For Accelerating Ai Model Training

Ponnarasan Krishnan

Quantum computing is a rapidly growing discipline that uses properties of quantum mechanics to compute problems that are challenging for traditional computational means. On the other hand, machine learning is a subset of artificial intelligence that enhances a computer's ability to learn patterns from experience. Massive data will get bigger with time; machine learning may sometimes be up to the task of big data, while quantum computing can perform fast computing. The crossbreed of quantum computing and machine learning brought about another field: quantum ML, or quantum machine learning. Applying the quantum learning algorithm includes benefiting from the fast processing in quantum computing and demonstrative speedup over the classical algorithm. Another subfield of artificial intelligence includes natural language processing, through which the computer can understand human languages. The chasers seek to apply quantum machine speedup in natural language processing. In this paper, firstly, we explain how from quantum computing to quantum machine learning. We then discuss the current trends regarding quantum machine learning for natural language processing. We also offer classic and quantum-based long short-term memory for POS tagging of code-mixed language and social media code mixed language. According to the above experiment, it is clear that the quantum-based long short-term memory works better than the classical long short-term memory for POS tagging for code-mixed datasets. Quantum computing is a rapidly developing field that uses the properties of quantum mechanics to solve problems challenging for classical computations.

Well Testing Journal•Sep 30, 2023•0 citations

Quantum Natural Language Processing: Challenges and Opportunities

Raffaele Guarasci, Giuseppe De Pietro, Massimo Esposito

The meeting between Natural Language Processing (NLP) and Quantum Computing has been very successful in recent years, leading to the development of several approaches of the so-called Quantum Natural Language Processing (QNLP). This is a hybrid field in which the potential of quantum mechanics is exploited and applied to critical aspects of language processing, involving different NLP tasks. Approaches developed so far span from those that demonstrate the quantum advantage only at the theoretical level to the ones implementing algorithms on quantum hardware. This paper aims to list the approaches developed so far, categorizing them by type, i.e., theoretical work and those implemented on classical or quantum hardware; by task, i.e., general purpose such as syntax-semantic representation or specific NLP tasks, like sentiment analysis or question answering; and by the resource used in the evaluation phase, i.e., whether a benchmark dataset or a custom one has been used. The advantages offered by QNLP are discussed, both in terms of performance and methodology, and some considerations about the possible usage QNLP approaches in the place of state-of-the-art deep learning-based ones are given.

Applied Sciences•Jun 2, 2022•85 citations

Quantum Classifier for Natural Language Processing Applications

Shyambabu Pandey, Partha Pakray, Riyanka Manna

A deep neural network is a branch of machinelearning that is capable of learning and representingcomplex patterns from a dataset through interconnectedmultiple layers of neurons. This capability makes itapplicable in various fields, such as natural languageprocessing, image processing, and computer vision.Deep learning models show effective performance butface challenges such as complexity and resourcedemands. On the other hand, quantum machine learningalgorithms offer an alternative with potential efficiencycompared to their classical counterparts. This paperproposes a Quantum Recurrent Neural Network (QRNN)for natural language processing tasks, which classify textdata such as parts of speech, named entity recognition,and sentiment analysis. The proposed method utilizesparameterized quantum circuits that contain the tunableparameters. Our approach uses amplitude encodingto represent classical data into quantum states, partialmeasurement for label determination, and ancilla qubitsto transfer the information from the current state to thenext.

Computación y Sistemas•Jun 29, 2024•5 citations
In this paper, we discuss the initial attempts at boosting understanding human language based on deep-learning models with quantum computing. We successfully train a quantum-enhanced Long Short-Term Memory network to perform the parts-of-speech tagging task via numerical simulations. Moreover, a quantum-enhanced Transformer is proposed to perform the sentiment analysis based on the existing dataset.
Quantum computing is a fast-emerging field that follows the laws of quantum mechanics to solve complex problems for classical systems. In the last few years, several researchers have emerged in quantum computing in accordance with the artificial intelligence field. Natural language processing is one of the prominent subfields of artificial intelligence. Quantum computing can be applied to the applications of natural language processing for better performance. One of the vital applications of natural language processing is Parts-Of-Speech (POS) tagging. It is prerequired for many natural language processing applications. In this paper, we have performed POS tagging of the Mizo language using classical Long short-term memory (LSTM). Subsequently, quantum-enhanced long short-term memory (QLSTM) has also been used to perform POS tagging of the Mizo language. The approaches mentioned above have been tested on the Mizo-tagged corpus, and experimental results have shown that quantum computing approaches such as QLSTM need the inclusion of new technologies to achieve significant results.
Quantum computing with its capacity to compute multiple possibilities at once, and perform some kinds of calculations almost instantly is one leading edge. The integration of QCs and DL undoubtedly represent one such transformative means for improving Natural Language Processing (NLP). By combining the two, this uses quantum principles of superposition and entanglement to make computation faster regarding human language comprehension limitations in classical computing. Deep learning models, specifically neural networks have already made significant improvements over NLP tasks like language translations, sentiment analysis and text generation. Nevertheless, these models also face scalability and computational efficiency issues with huge volumes of data. Quantum computing offers a solution to all this by reducing the time exponentially that it takes to fetch large amounts of language data and running deep learning algorithms. This paper investigates the opportunities that integrating quantum computing and deep learning into NLP practices might unlock. We drafted the fundamentals of quantum computing and why it is a need over classical computing, where we discussed on how quantum beneficial for data processing & optimization of an algorithm. We then explore applications of quantum enhanced deep learning for NLP, with a focus on the impact that training and inference can have on model performance. We demonstrate the utility of this integration by integrating our four SQDs to showcase improvements on diverse NLP tasks through a series of experiments and case studies. We also demonstrate that hybrid quantum-classical approaches allow the combination of traditional ML and quantum-enhanced models, achieving state-of-the-art performance with respect to effectiveness, scalability and precision
Quantum computing is a rapidly growing discipline that uses properties of quantum mechanics to compute problems that are challenging for traditional computational means. On the other hand, machine learning is a subset of artificial intelligence that enhances a computer's ability to learn patterns from experience. Massive data will get bigger with time; machine learning may sometimes be up to the task of big data, while quantum computing can perform fast computing. The crossbreed of quantum computing and machine learning brought about another field: quantum ML, or quantum machine learning. Applying the quantum learning algorithm includes benefiting from the fast processing in quantum computing and demonstrative speedup over the classical algorithm. Another subfield of artificial intelligence includes natural language processing, through which the computer can understand human languages. The chasers seek to apply quantum machine speedup in natural language processing. In this paper, firstly, we explain how from quantum computing to quantum machine learning. We then discuss the current trends regarding quantum machine learning for natural language processing. We also offer classic and quantum-based long short-term memory for POS tagging of code-mixed language and social media code mixed language. According to the above experiment, it is clear that the quantum-based long short-term memory works better than the classical long short-term memory for POS tagging for code-mixed datasets. Quantum computing is a rapidly developing field that uses the properties of quantum mechanics to solve problems challenging for classical computations.
The meeting between Natural Language Processing (NLP) and Quantum Computing has been very successful in recent years, leading to the development of several approaches of the so-called Quantum Natural Language Processing (QNLP). This is a hybrid field in which the potential of quantum mechanics is exploited and applied to critical aspects of language processing, involving different NLP tasks. Approaches developed so far span from those that demonstrate the quantum advantage only at the theoretical level to the ones implementing algorithms on quantum hardware. This paper aims to list the approaches developed so far, categorizing them by type, i.e., theoretical work and those implemented on classical or quantum hardware; by task, i.e., general purpose such as syntax-semantic representation or specific NLP tasks, like sentiment analysis or question answering; and by the resource used in the evaluation phase, i.e., whether a benchmark dataset or a custom one has been used. The advantages offered by QNLP are discussed, both in terms of performance and methodology, and some considerations about the possible usage QNLP approaches in the place of state-of-the-art deep learning-based ones are given.
A deep neural network is a branch of machinelearning that is capable of learning and representingcomplex patterns from a dataset through interconnectedmultiple layers of neurons. This capability makes itapplicable in various fields, such as natural languageprocessing, image processing, and computer vision.Deep learning models show effective performance butface challenges such as complexity and resourcedemands. On the other hand, quantum machine learningalgorithms offer an alternative with potential efficiencycompared to their classical counterparts. This paperproposes a Quantum Recurrent Neural Network (QRNN)for natural language processing tasks, which classify textdata such as parts of speech, named entity recognition,and sentiment analysis. The proposed method utilizesparameterized quantum circuits that contain the tunableparameters. Our approach uses amplitude encodingto represent classical data into quantum states, partialmeasurement for label determination, and ancilla qubitsto transfer the information from the current state to thenext.