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 Silchar Subsection Conference (SILCON)

Parts of speech tagging towards classical to quantum computing

Shyambabu Pandey, Pankaj Dadure, Morrel V. L. Nunsanga, Partha Pakray

Published Nov 4, 2022• 8 citations
Publisher

Abstract

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.

DOI
10.1109/silcon55242.2022.10028796

Related papers

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

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.

IEEE International Conference on Acoustics Speech and Signal Processing•Apr 27, 2022•124 citations

Quantum-Enhanced Gated Recurrent Units for Part-of-Speech Tagging

Ashutosh Rai, Shyambabu Pandey, Partha Pakray

Deep learning models for Natural Language Processing (NLP) tasks, such as Part-of-Speech (POS) tagging, usually have significant parameter counts that make them costly to train and deploy.Quantum Machine Learning (QML) offers a potential approach for building more parameter-efficient models.This paper proposes a hybrid quantum-classical gated recurrent unit model for POS tagging in code-mixed social media text.By integrating a quantum layer into the recurrent framework, our model achieved an accuracy comparable to the baseline classical model, while needing fewer parameters.Although the cut-off point in the parameters is modest in our setup, the approach is promising when scaled to deeper architectures.These results suggest that hybrid models can offer a resource-efficient alternative for NLP tasks.

•Jan 1, 2025•0 citations

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

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•3 citations

Toward Quantum-Enhanced Natural Language Understanding: Sarcasm and Claim Detection with QLSTM

Pritam Pal, Dipankar Das

Traditional machine learning (ML) and deep learning (DL) models have shown effectiveness in natural language processing (NLP) tasks, such as sentiment analysis.However, they often struggle with complex linguistic structures, such as sarcasm and implicit claims.This paper introduces a Quantum Long Short-Term Memory (QLSTM) framework for detecting sarcasm and identifying claims in text, aiming to enhance the analysis of complex sentences.We evaluate four approaches: (1) classical LSTM, (2) quantum framework using QLSTM, (3) voting ensemble combining classical and quantum LSTMs, and (4) hybrid framework integrating both types.The experimental results indicate that the QLSTM approach excels in sarcasm detection, while the voting framework performs best in claim identification.

International conference Recent advances in natural language processing•Jan 1, 2025•2 citations
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 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.
Deep learning models for Natural Language Processing (NLP) tasks, such as Part-of-Speech (POS) tagging, usually have significant parameter counts that make them costly to train and deploy.Quantum Machine Learning (QML) offers a potential approach for building more parameter-efficient models.This paper proposes a hybrid quantum-classical gated recurrent unit model for POS tagging in code-mixed social media text.By integrating a quantum layer into the recurrent framework, our model achieved an accuracy comparable to the baseline classical model, while needing fewer parameters.Although the cut-off point in the parameters is modest in our setup, the approach is promising when scaled to deeper architectures.These results suggest that hybrid models can offer a resource-efficient alternative for NLP tasks.
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.
Traditional machine learning (ML) and deep learning (DL) models have shown effectiveness in natural language processing (NLP) tasks, such as sentiment analysis.However, they often struggle with complex linguistic structures, such as sarcasm and implicit claims.This paper introduces a Quantum Long Short-Term Memory (QLSTM) framework for detecting sarcasm and identifying claims in text, aiming to enhance the analysis of complex sentences.We evaluate four approaches: (1) classical LSTM, (2) quantum framework using QLSTM, (3) voting ensemble combining classical and quantum LSTMs, and (4) hybrid framework integrating both types.The experimental results indicate that the QLSTM approach excels in sarcasm detection, while the voting framework performs best in claim identification.