Fei Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Fei Chen has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Yijia Zhang
School of Information Science and Technology, Dalian Maritime University, Dalian, China
3 shared publications - Jinyu Li
Dalian Maritime University
2 shared publications - Longmei Xu
Dalian Maritime University
2 shared publications - Wenchi Zhou
Information Science and Technology College, Dalian Maritime University, Dalian 116026, China
2 shared publications - Ai Zhou
College of Information Science and Technology, Dalian Maritime University, Dalian, People’s Republic of China
1 shared publication - Bo Ning
Dalian Maritime University, Dalian, China
1 shared publication
Latest Publications
- Open Access
- 1 August 2025
- Published by MDPI AG in Electronics
- Vol. 14 (15) , 3092
Quality over Quantity: An Effective Large-Scale Data Reduction Strategy Based on Pointwise V-Information
In order to increase the effectiveness of model training, data reduction is essential to data-centric Artificial Intelligence (AI). It achieves this by locating the most instructive examples in massive datasets. To increase data quality and training efficiency, the main difficulty is choosing the best examples rather than the complete datasets. In this paper, we propose an effective data reduction strategy based on Pointwise -Information (PVI). To enable a static method, we first use PVI to quantify instance difficulty and remove instances with low difficulty. Experiments show that classifier performance is maintained with only a 0.0001% to 0.76% decline in accuracy when 10–30% of the data is removed. Second, we train the classifiers using a progressive learning strategy on examples sorted by increasing PVI, accelerating convergence and achieving a 0.8% accuracy gain over conventional training. Our findings imply that training a classifier on the chosen optimal subset may improve model performance and increase training efficiency when combined with an efficient data reduction strategy. Furthermore, we have adapted the PVI framework, which was previously limited to English datasets, to a variety of Chinese Natural Language Processing (NLP) tasks and base models, yielding insightful results for faster training and cross-lingual data reduction.- 1 August 2025
- Published by MDPI AG in Electronics
- Vol. 14 (15) , 3092
Open AccessQuality over Quantity: An Effective Large-Scale Data Reduction Strategy Based on Pointwise V-Information
In order to increase the effectiveness of model training, data reduction is essential to data-centric Artificial Intelligence (AI). It achieves this by locating the most instructive examples in massive datasets. To increase data quality and training efficiency, the main difficulty is choosing the best examples rather than the complete datasets. In this paper, we propose an effective data reduction strategy based on Pointwise -Information (PVI). To enable a static method, we first use PVI to quantify instance difficulty and remove instances with low difficulty. Experiments show that classifier performance is maintained with only a 0.0001% to 0.76% decline in accuracy when 10–30% of the data is removed. Second, we train the classifiers using a progressive learning strategy on examples sorted by increasing PVI, accelerating convergence and achieving a 0.8% accuracy gain over conventional training. Our findings imply that training a classifier on the chosen optimal subset may improve model performance and increase training efficiency when combined with an efficient data reduction strategy. Furthermore, we have adapted the PVI framework, which was previously limited to English datasets, to a variety of Chinese Natural Language Processing (NLP) tasks and base models, yielding insightful results for faster training and cross-lingual data reduction. - 15 February 2025
- Published by Springer Nature
- p. 16-33
A Recommender System for Mining Personalized User Preferences
- 15 February 2025
- Published by Springer Nature
- p. 16-33
A Recommender System for Mining Personalized User Preferences
- 15 February 2025
- Published by Springer Nature
- p. 135-151
Ordinal and Position Enhance the Framework of the Multimodal Dialogue System
- 15 February 2025
- Published by Springer Nature
- p. 135-151
Ordinal and Position Enhance the Framework of the Multimodal Dialogue System
- 15 February 2025
- Published by Springer Nature
- p. 34-52
An Automatic Hyperparameter Optimization Method for an Improved DQN
- 15 February 2025
- Published by Springer Nature
- p. 34-52
An Automatic Hyperparameter Optimization Method for an Improved DQN
- 15 February 2025
- Published by Springer Nature
- p. 152-166
A Two-Stage Approach for Multimodal Emotion Cause Pair Extraction that is Based on Large Language Models
- 15 February 2025
- Published by Springer Nature
- p. 152-166
A Two-Stage Approach for Multimodal Emotion Cause Pair Extraction that is Based on Large Language Models
- 8 December 2024
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 81 (1)
CRKG: combining retrieval knowledge with generative language models
- 8 December 2024
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 81 (1)
CRKG: combining retrieval knowledge with generative language models
- 20 September 2023
- Published by Springer Nature
- p. 419-433
Adversarial Network with External Knowledge for Zero-Shot Stance Detection
- 20 September 2023
- Published by Springer Nature
- p. 419-433
Adversarial Network with External Knowledge for Zero-Shot Stance Detection
- 1 February 2022
- Published by Elsevier in Knowledge-Based Systems
- Vol. 238
Heterogeneous graph neural networks with denoising for graph embeddings
- 1 February 2022
- Published by Elsevier in Knowledge-Based Systems
- Vol. 238
Heterogeneous graph neural networks with denoising for graph embeddings
- Open Access
- 1 January 2021
- Published by Wiley in Complexity
- Vol. 2021 (1)
Automatic Integrated Scoring Model for English Composition Oriented to Part‐Of‐Speech Tagging
Part‐of‐speech tagging for English composition is the basis for automatic correction of English composition. The performance of the part‐of‐speech tagging system directly affects the performance of the marking and analysis of the correction system. Therefore, this paper proposes an automatic scoring model for English composition based on article part‐of‐speech tagging. First, use the convolutional neural network to extract the word information from the character level and use this part of the information in the coarse‐grained learning layer. Secondly, the word‐level vector is introduced, and the residual network is used to establish an information path to integrate the coarse‐grained annotation and word vector information. Then, the model relies on the recurrent neural network to extract the overall information of the sequence data to obtain accurate annotation results. Then, the features of the text content are extracted, and the automatic scoring model of English composition is constructed by means of model fusion. Finally, this paper uses the English composition scoring competition data set on the international data mining competition platform Kaggle to verify the effect of the model.
- 1 January 2021
- Published by Wiley in Complexity
- Vol. 2021 (1)
Open AccessAutomatic Integrated Scoring Model for English Composition Oriented to Part‐Of‐Speech Tagging
Part‐of‐speech tagging for English composition is the basis for automatic correction of English composition. The performance of the part‐of‐speech tagging system directly affects the performance of the marking and analysis of the correction system. Therefore, this paper proposes an automatic scoring model for English composition based on article part‐of‐speech tagging. First, use the convolutional neural network to extract the word information from the character level and use this part of the information in the coarse‐grained learning layer. Secondly, the word‐level vector is introduced, and the residual network is used to establish an information path to integrate the coarse‐grained annotation and word vector information. Then, the model relies on the recurrent neural network to extract the overall information of the sequence data to obtain accurate annotation results. Then, the features of the text content are extracted, and the automatic scoring model of English composition is constructed by means of model fusion. Finally, this paper uses the English composition scoring competition data set on the international data mining competition platform Kaggle to verify the effect of the model.
- Open Access
- 10 August 2020
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2020, 1-13
A Multichannel Biomedical Named Entity Recognition Model Based on Multitask Learning and Contextualized Word Representations
As the biomedical literature increases exponentially, biomedical named entity recognition (BNER) has become an important task in biomedical information extraction. In the previous studies based on deep learning, pretrained word embedding becomes an indispensable part of the neural network models, effectively improving their performance. However, the biomedical literature typically contains numerous polysemous and ambiguous words. Using fixed pretrained word representations is not appropriate. Therefore, this paper adopts the pretrained embeddings from language models (ELMo) to generate dynamic word embeddings according to context. In addition, in order to avoid the problem of insufficient training data in specific fields and introduce richer input representations, we propose a multitask learning multichannel bidirectional gated recurrent unit (BiGRU) model. Multiple feature representations (e.g., word-level, contextualized word-level, character-level) are, respectively, or collectively fed into the different channels. Manual participation and feature engineering can be avoided through automatic capturing features in BiGRU. In merge layer, multiple methods are designed to integrate the outputs of multichannel BiGRU. We combine BiGRU with the conditional random field (CRF) to address labels’ dependence in sequence labeling. Moreover, we introduce the auxiliary corpora with same entity types for the main corpora to be evaluated in multitask learning framework, then train our model on these separate corpora and share parameters with each other. Our model obtains promising results on the JNLPBA and NCBI-disease corpora, with F1-scores of 76.0% and 88.7%, respectively. The latter achieves the best performance among reported existing feature-based models.
- 10 August 2020
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2020, 1-13
Open AccessA Multichannel Biomedical Named Entity Recognition Model Based on Multitask Learning and Contextualized Word Representations
As the biomedical literature increases exponentially, biomedical named entity recognition (BNER) has become an important task in biomedical information extraction. In the previous studies based on deep learning, pretrained word embedding becomes an indispensable part of the neural network models, effectively improving their performance. However, the biomedical literature typically contains numerous polysemous and ambiguous words. Using fixed pretrained word representations is not appropriate. Therefore, this paper adopts the pretrained embeddings from language models (ELMo) to generate dynamic word embeddings according to context. In addition, in order to avoid the problem of insufficient training data in specific fields and introduce richer input representations, we propose a multitask learning multichannel bidirectional gated recurrent unit (BiGRU) model. Multiple feature representations (e.g., word-level, contextualized word-level, character-level) are, respectively, or collectively fed into the different channels. Manual participation and feature engineering can be avoided through automatic capturing features in BiGRU. In merge layer, multiple methods are designed to integrate the outputs of multichannel BiGRU. We combine BiGRU with the conditional random field (CRF) to address labels’ dependence in sequence labeling. Moreover, we introduce the auxiliary corpora with same entity types for the main corpora to be evaluated in multitask learning framework, then train our model on these separate corpora and share parameters with each other. Our model obtains promising results on the JNLPBA and NCBI-disease corpora, with F1-scores of 76.0% and 88.7%, respectively. The latter achieves the best performance among reported existing feature-based models.