Xiaoxin Sun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xiaoxin Sun has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Suhua Wang
Computer Department, Changchun Humanities and Sciences College, Changchun 130117, China
4 shared publications Suhua Wang
Computer Department, Changchun Humanities and Sciences College, Changchun 130117, China
2 shared publications- Xin Li
College of Optical Science and Engineering, Zhejiang University, Hangzhou, P. R. China
2 shared publications - Yun Zhang
College of Computer Science, Changchun Humanities and Sciences College, Changchun 130117, China
2 shared publications Zhen Huang
The University of Science and Technology of China, Department of Computer Science, Hefei 230026, China
2 shared publicationsBangzuo Zhang
Northeast Normal University, Changchun, China
1 shared publication
Latest Publications
- 14 July 2026
- Published by Springer Nature
- p. 51-61
ManchuTTS: Towards High-Quality Manchu Speech Synthesis via Flow Matching and Hierarchical Text Representation
- 14 July 2026
- Published by Springer Nature
- p. 51-61
ManchuTTS: Towards High-Quality Manchu Speech Synthesis via Flow Matching and Hierarchical Text Representation
- 9 May 2026
- Published by World Scientific Pub Co Pte Ltd in International Journal on Artificial Intelligence Tools
- Vol. 35 (03)
Transformer–Based Models for Low–Resource Language Processing in Specialized Technical Domains
Natural language processing encounters major difficulties when processing low-resource languages because technical fields require specialized terminology and lack sufficient annotated data. The performance of transformer-based multilingual models depends on their ability to operate in different domains and their available resources for training. The researchers developed a transformer-based framework that uses XLM-RoBERTa (XLM-R) to process languages that have limited resources for their needs. The proposed methodology includes systematic data preprocessing methods that create low-resource data through data augmentation and implement a two-stage domain adaptation approach that begins with pretraining on unlabeled technical text before moving to task-specific classification fine-tuning. The FLORES-200 multilingual dataset provides a structured benchmark assessment that tests low-resource conditions through its multiple testing methods. Model performance assessment uses standard evaluation metrics, which include accuracy and precision and recall and [ ]1-score, together with confusion matrix analysis and evaluation curve measurements. The experimental results show that the proposed approach achieved 0.98889 accuracy, 0.98925 precision, 0.98889 recall, and 0.98889 [ ]1-score, which demonstrates strong accurate classification abilities. The study shows that multilingual transformer models, which use domain adaptation and data augmentation methods, deliver effective solutions to data scarcity challenges while improving performance in technical fields.
- 9 May 2026
- Published by World Scientific Pub Co Pte Ltd in International Journal on Artificial Intelligence Tools
- Vol. 35 (03)
Transformer–Based Models for Low–Resource Language Processing in Specialized Technical Domains
Natural language processing encounters major difficulties when processing low-resource languages because technical fields require specialized terminology and lack sufficient annotated data. The performance of transformer-based multilingual models depends on their ability to operate in different domains and their available resources for training. The researchers developed a transformer-based framework that uses XLM-RoBERTa (XLM-R) to process languages that have limited resources for their needs. The proposed methodology includes systematic data preprocessing methods that create low-resource data through data augmentation and implement a two-stage domain adaptation approach that begins with pretraining on unlabeled technical text before moving to task-specific classification fine-tuning. The FLORES-200 multilingual dataset provides a structured benchmark assessment that tests low-resource conditions through its multiple testing methods. Model performance assessment uses standard evaluation metrics, which include accuracy and precision and recall and [ ]1-score, together with confusion matrix analysis and evaluation curve measurements. The experimental results show that the proposed approach achieved 0.98889 accuracy, 0.98925 precision, 0.98889 recall, and 0.98889 [ ]1-score, which demonstrates strong accurate classification abilities. The study shows that multilingual transformer models, which use domain adaptation and data augmentation methods, deliver effective solutions to data scarcity challenges while improving performance in technical fields.
- Open Access
- 1 January 2023
- Published by American Institute of Mathematical Sciences (AIMS) in Electronic Research Archive
- Vol. 31 (6) , 3169-3186
Plot-aware transformer for recommender systems
Plot text is very valuable supporting information in movie recommendations. It has several characteristics: 1) It is rich in content. Each movie often has a document of more than 200 words to describe it, which can give the movie a rich semantic meaning. 2) Objectivity. Plot texts are different from review information. A movie may have thousands of reviews with mixed and conflicting opinions. However, a film has only one plot text, which is fair in tone and does not take a position. Despite its appealing properties and potential for accurate movie portrayal, the lack of a building block for effectively mining plot semantics has led to the marginalization of plot text in the design of movie recommendation algorithms. Therefore, in this paper, we explore the application of the Transformer, currently the best natural language processing module, to learning movie plot texts to help achieve more accurate rating prediction. We propose the "Plot-Aware Transformer" model (PAT) to model the process of "user-movie" rating interaction. We test the PAT model on several movie datasets and demonstrated that the model is competitive. In all tasks, PAT achieves state-of-the-art performance compared to baseline experiments.
- 1 January 2023
- Published by American Institute of Mathematical Sciences (AIMS) in Electronic Research Archive
- Vol. 31 (6) , 3169-3186
Open AccessPlot-aware transformer for recommender systems
Plot text is very valuable supporting information in movie recommendations. It has several characteristics: 1) It is rich in content. Each movie often has a document of more than 200 words to describe it, which can give the movie a rich semantic meaning. 2) Objectivity. Plot texts are different from review information. A movie may have thousands of reviews with mixed and conflicting opinions. However, a film has only one plot text, which is fair in tone and does not take a position. Despite its appealing properties and potential for accurate movie portrayal, the lack of a building block for effectively mining plot semantics has led to the marginalization of plot text in the design of movie recommendation algorithms. Therefore, in this paper, we explore the application of the Transformer, currently the best natural language processing module, to learning movie plot texts to help achieve more accurate rating prediction. We propose the "Plot-Aware Transformer" model (PAT) to model the process of "user-movie" rating interaction. We test the PAT model on several movie datasets and demonstrated that the model is competitive. In all tasks, PAT achieves state-of-the-art performance compared to baseline experiments.
- Open Access
- 1 January 2023
- Published by American Institute of Mathematical Sciences (AIMS) in Electronic Research Archive
- Vol. 31 (1) , 509-529
PM2.5 hourly concentration prediction based on graph capsule networks
In this paper, we use a graph capsule network to capture the spatial dependence of air quality data and meteorological data among cities, then use an LSTM network to model the temporal dependence of air pollution levels in specific cities and finally implement PM2.5 concentration prediction. We propose a graph-capsule-LSTM model based on a graph-capsule network and an LSTM network. The model uses a graph capsule network to model the neighboring feature information of the target city and then combines the local data of the target city to form the final feature vector. The feature mapping on the time axis is then used to obtain the temporal feature sequences of the target nodes, which are fed into the LSTM network for learning and prediction. Experiments show that the method achieves better results than the latest baseline model in the PM2.5 prediction task. While demonstrating that the capsule network outperforms the convolutional network, it also shows that this capsule network is very competent for the task of PM2.5 prediction.
- 1 January 2023
- Published by American Institute of Mathematical Sciences (AIMS) in Electronic Research Archive
- Vol. 31 (1) , 509-529
Open AccessPM2.5 hourly concentration prediction based on graph capsule networks
In this paper, we use a graph capsule network to capture the spatial dependence of air quality data and meteorological data among cities, then use an LSTM network to model the temporal dependence of air pollution levels in specific cities and finally implement PM2.5 concentration prediction. We propose a graph-capsule-LSTM model based on a graph-capsule network and an LSTM network. The model uses a graph capsule network to model the neighboring feature information of the target city and then combines the local data of the target city to form the final feature vector. The feature mapping on the time axis is then used to obtain the temporal feature sequences of the target nodes, which are fed into the LSTM network for learning and prediction. Experiments show that the method achieves better results than the latest baseline model in the PM2.5 prediction task. While demonstrating that the capsule network outperforms the convolutional network, it also shows that this capsule network is very competent for the task of PM2.5 prediction.
- 20 June 2022
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 78 (17) , 19322-19345
Leveraging side information as adjusting embedding to improve user representation for recommendations
- 20 June 2022
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 78 (17) , 19322-19345
Leveraging side information as adjusting embedding to improve user representation for recommendations
- Open Access
- 4 February 2022
- Published by MDPI AG in Mathematics
- Vol. 10 (3) , 503
Neural Metric Factorization for Recommendation
All current recommendation algorithms, when modeling user–item interactions, basically use dot product. This dot product calculation is derived from matrix factorization. We argue that an inherent drawback of matrix factorization is that latent semantic vectors of users or items sometimes do not satisfy triangular inequalities, which may affect the performance of the recommendation. Recently, metric factorization was proposed to replace matrix factorization and has achieved some improvements in terms of recommendation accuracy. However, similar to matrix factorization, metric factorization still uses a simple, linear fashion. In this paper, we explore leveraging nonlinear deep neural networks to realize Euclidean distance interaction between users and items. We propose a generic Neural Metric Factorization Framework (NMetricF), which learns representations for users and items by incorporating Euclidean metric factorization into deep neural networks. Extensive experiments on six real-world datasets show that, compared to the previous recommendation algorithms based purely on rating data, NMetricF achieves the best performance.
- 4 February 2022
- Published by MDPI AG in Mathematics
- Vol. 10 (3) , 503
Open AccessNeural Metric Factorization for Recommendation
All current recommendation algorithms, when modeling user–item interactions, basically use dot product. This dot product calculation is derived from matrix factorization. We argue that an inherent drawback of matrix factorization is that latent semantic vectors of users or items sometimes do not satisfy triangular inequalities, which may affect the performance of the recommendation. Recently, metric factorization was proposed to replace matrix factorization and has achieved some improvements in terms of recommendation accuracy. However, similar to matrix factorization, metric factorization still uses a simple, linear fashion. In this paper, we explore leveraging nonlinear deep neural networks to realize Euclidean distance interaction between users and items. We propose a generic Neural Metric Factorization Framework (NMetricF), which learns representations for users and items by incorporating Euclidean metric factorization into deep neural networks. Extensive experiments on six real-world datasets show that, compared to the previous recommendation algorithms based purely on rating data, NMetricF achieves the best performance.
- 9 November 2020
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 77 (6) , 5510-5527
Attribute-aware deep attentive recommendation
- 9 November 2020
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 77 (6) , 5510-5527
Attribute-aware deep attentive recommendation
- 14 August 2020
- Published by Springer Nature in Neural Processing Letters
- Vol. 52 (3) , 1983-1995
Deep Plot-Aware Generalized Matrix Factorization for Collaborative Filtering
- 14 August 2020
- Published by Springer Nature in Neural Processing Letters
- Vol. 52 (3) , 1983-1995
Deep Plot-Aware Generalized Matrix Factorization for Collaborative Filtering
- 2 June 2020
- Published by Springer Nature in Evolutionary Intelligence
- Vol. 15 (4) , 2385-2393
Neural multi-task collaborative filtering
- 2 June 2020
- Published by Springer Nature in Evolutionary Intelligence
- Vol. 15 (4) , 2385-2393
Neural multi-task collaborative filtering