Application of Quantum Recurrent Neural Network in Low-Resource Language Text Classification
Text sentiment analysis is an important task in natural language processing and has always been a hot research topic. However, in low-resource regions such as South Asia, where languages like Bengali are widely used, the research interest is relatively low compared to high-resource regions due to li...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Transactions on Quantum Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10461108/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832586865641783296 |
|---|---|
| author | Wenbin Yu Lei Yin Chengjun Zhang Yadang Chen Alex X. Liu |
| author_facet | Wenbin Yu Lei Yin Chengjun Zhang Yadang Chen Alex X. Liu |
| author_sort | Wenbin Yu |
| collection | DOAJ |
| description | Text sentiment analysis is an important task in natural language processing and has always been a hot research topic. However, in low-resource regions such as South Asia, where languages like Bengali are widely used, the research interest is relatively low compared to high-resource regions due to limited computational resources, flexible word order, and high inflectional nature of the language. With the development of quantum technology, quantum machine learning models leverage the superposition property of qubits to enhance model expressiveness and achieve faster computation compared to classical systems. To promote the development of quantum machine learning in low-resource language domains, we propose a quantum–classical hybrid architecture. This architecture utilizes a pretrained multilingual bidirectional encoder representations from transformer (BERT) model to obtain vector representations of words and combines the proposed batch upload quantum recurrent neural network (BUQRNN) and parameter nonshared batch upload quantum recurrent neural network (PN-BUQRNN) as feature extraction models for sentiment analysis in Bengali. Our numerical results demonstrate that the proposed BUQRNN structure achieves a maximum accuracy improvement of 0.993% in Bengali text classification tasks while reducing average model complexity by 12%. The PN-BUQRNN structure surpasses the BUQRNN structure once again and outperforms classical architectures in certain tasks. |
| format | Article |
| id | doaj-art-742eb2f0e7ba4468ab35fe3fb84d4cf3 |
| institution | Kabale University |
| issn | 2689-1808 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Quantum Engineering |
| spelling | doaj-art-742eb2f0e7ba4468ab35fe3fb84d4cf32025-01-25T00:03:29ZengIEEEIEEE Transactions on Quantum Engineering2689-18082024-01-01511310.1109/TQE.2024.337390310461108Application of Quantum Recurrent Neural Network in Low-Resource Language Text ClassificationWenbin Yu0https://orcid.org/0000-0003-4786-4036Lei Yin1https://orcid.org/0009-0003-7905-4959Chengjun Zhang2https://orcid.org/0000-0002-4458-5843Yadang Chen3https://orcid.org/0000-0002-4448-2617Alex X. Liu4https://orcid.org/0000-0002-6916-1326School of Software, Nanjing University of Information Science and Technology, Nanjing, ChinaSchool of Software, Nanjing University of Information Science and Technology, Nanjing, ChinaNanjing University of Information Science and Technology, Wuxi Institute of Technology, Wuxi, ChinaSchool of Computer Science, Nanjing University of Information Science and Technology, Nanjing, ChinaShandong Provincial Key Laboratory of Computer Networks, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan, ChinaText sentiment analysis is an important task in natural language processing and has always been a hot research topic. However, in low-resource regions such as South Asia, where languages like Bengali are widely used, the research interest is relatively low compared to high-resource regions due to limited computational resources, flexible word order, and high inflectional nature of the language. With the development of quantum technology, quantum machine learning models leverage the superposition property of qubits to enhance model expressiveness and achieve faster computation compared to classical systems. To promote the development of quantum machine learning in low-resource language domains, we propose a quantum–classical hybrid architecture. This architecture utilizes a pretrained multilingual bidirectional encoder representations from transformer (BERT) model to obtain vector representations of words and combines the proposed batch upload quantum recurrent neural network (BUQRNN) and parameter nonshared batch upload quantum recurrent neural network (PN-BUQRNN) as feature extraction models for sentiment analysis in Bengali. Our numerical results demonstrate that the proposed BUQRNN structure achieves a maximum accuracy improvement of 0.993% in Bengali text classification tasks while reducing average model complexity by 12%. The PN-BUQRNN structure surpasses the BUQRNN structure once again and outperforms classical architectures in certain tasks.https://ieeexplore.ieee.org/document/10461108/Natural language processing (NLP)quantum machine learningquantum recurrent neural network |
| spellingShingle | Wenbin Yu Lei Yin Chengjun Zhang Yadang Chen Alex X. Liu Application of Quantum Recurrent Neural Network in Low-Resource Language Text Classification IEEE Transactions on Quantum Engineering Natural language processing (NLP) quantum machine learning quantum recurrent neural network |
| title | Application of Quantum Recurrent Neural Network in Low-Resource Language Text Classification |
| title_full | Application of Quantum Recurrent Neural Network in Low-Resource Language Text Classification |
| title_fullStr | Application of Quantum Recurrent Neural Network in Low-Resource Language Text Classification |
| title_full_unstemmed | Application of Quantum Recurrent Neural Network in Low-Resource Language Text Classification |
| title_short | Application of Quantum Recurrent Neural Network in Low-Resource Language Text Classification |
| title_sort | application of quantum recurrent neural network in low resource language text classification |
| topic | Natural language processing (NLP) quantum machine learning quantum recurrent neural network |
| url | https://ieeexplore.ieee.org/document/10461108/ |
| work_keys_str_mv | AT wenbinyu applicationofquantumrecurrentneuralnetworkinlowresourcelanguagetextclassification AT leiyin applicationofquantumrecurrentneuralnetworkinlowresourcelanguagetextclassification AT chengjunzhang applicationofquantumrecurrentneuralnetworkinlowresourcelanguagetextclassification AT yadangchen applicationofquantumrecurrentneuralnetworkinlowresourcelanguagetextclassification AT alexxliu applicationofquantumrecurrentneuralnetworkinlowresourcelanguagetextclassification |