Weijian Ni
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Weijian Ni has a total of 43 co-authors. Here are the top co-authors by number of shared publications:
- Qingtian Zeng
Shandong University of Science and Technology, Qingdao, China
18 shared publications - Hua Duan
College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, China
9 shared publications - Shansong Wang
The University of Chicago
8 shared publications - Tong Liu
College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, China
5 shared publications Nengfu Xie
Agricultural Information Institute of CAAS, Beijing, China
4 shared publications- Cong Liu
Nova Information Management School, Universidade Nova de Lisboa, Lisbon, Portugal
3 shared publications
Latest Publications
- Open Access
- 10 June 2026
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 15 (6) , 258
A Refined Span Classification Model for Recognizing Nested Named Entity in Marine Meteorological Disaster Texts
Named entity recognition (NER) in marine meteorological disaster texts is essential for automated information extraction and disaster management. However, disaster-chain descriptions often contain nested entities that are difficult for conventional flat NER models to represent. This paper proposes PRSpan, a position-role-aware span classification model for nested NER. PRSpan incorporates Rotary Position Embedding (RoPE)-enhanced attention for relative position-aware boundary modeling and uses Conditional Layer Normalization (CLN) to generate role-specific Head, Mid, and Tail token features. A Positional Role Pooling strategy further aggregates these features into span representations to preserve boundary cues and internal semantic coherence. To support evaluation, we construct MMD-NER, a domain-specific dataset containing 1899 sentences, 17,017 entities in 11 categories, and 2978 nested entity pairs through a four-step LLM-assisted pipeline. Experimental results show that PRSpan achieves Micro-F1 and Macro-F1 scores of 94.58% and 93.47%, outperforming the strongest baseline by 3.61 and 3.93 percentage points, respectively. Additional analyses verify the effectiveness of RoPE-enhanced attention, role-specific feature generation, and Positional Role Pooling. Cross-domain transfer and LLM prompting comparisons further demonstrate the practical value of PRSpan for nested entity extraction in low-resource Earth science domains.
- 10 June 2026
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 15 (6) , 258
Open AccessA Refined Span Classification Model for Recognizing Nested Named Entity in Marine Meteorological Disaster Texts
Named entity recognition (NER) in marine meteorological disaster texts is essential for automated information extraction and disaster management. However, disaster-chain descriptions often contain nested entities that are difficult for conventional flat NER models to represent. This paper proposes PRSpan, a position-role-aware span classification model for nested NER. PRSpan incorporates Rotary Position Embedding (RoPE)-enhanced attention for relative position-aware boundary modeling and uses Conditional Layer Normalization (CLN) to generate role-specific Head, Mid, and Tail token features. A Positional Role Pooling strategy further aggregates these features into span representations to preserve boundary cues and internal semantic coherence. To support evaluation, we construct MMD-NER, a domain-specific dataset containing 1899 sentences, 17,017 entities in 11 categories, and 2978 nested entity pairs through a four-step LLM-assisted pipeline. Experimental results show that PRSpan achieves Micro-F1 and Macro-F1 scores of 94.58% and 93.47%, outperforming the strongest baseline by 3.61 and 3.93 percentage points, respectively. Additional analyses verify the effectiveness of RoPE-enhanced attention, role-specific feature generation, and Positional Role Pooling. Cross-domain transfer and LLM prompting comparisons further demonstrate the practical value of PRSpan for nested entity extraction in low-resource Earth science domains.
- 14 January 2026
- Published by Elsevier in Neural Networks
- Vol. 198, 108597
A novel movie scene detection method based on clue relationship and constrained shot description
- 14 January 2026
- Published by Elsevier in Neural Networks
- Vol. 198, 108597
A novel movie scene detection method based on clue relationship and constrained shot description
- 23 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Big Data
- Vol. 12 (2) , 430-446
Visual Question Answer Model Based on Crop Diseases External Knowledge for Smart Agriculture
Current crop disease VQA models primarily focus on object counting and detection. However, accurately identifying various disease stages and determining control measures require additional knowledge beyond images, including information about control methods and pathogen details. To address this, the VQA dataset relies on the images and questions to retrieve relevant external knowledge. To realize the VQA task of crop diseases external knowledge, we construct the Visual Question Answer Model Based on Crop Diseases External Knowledge for Smart Agriculture (CDEK). CDEK integrates two categories of external knowledge on 66 common dicotyledonous crop diseases by utilizing large language models and agricultural knowledge repositories to enhance knowledge retrieval. This integration enhances the richness of external knowledge repositories. Enhancing fine-grained image understanding in CDEK through the utilization of Stack Self-Attention (SSA), utilising Cross-Attention and contrastive learning of two external knowledge, with a focus on emphasizing image-related semantic information during training. Finally, an automatic patrol disease detection robot is constructed based on Tensor Processing Unit (TPU) devices and the CDEK model. CDEK achieves an accuracy of 61.7% on the publicly available dataset OK-VQA, surpassing the previous state-of-the-art by 5.1%. Furthermore, we construct the OKiCD-VQA dataset for crop diseases external knowledge and achieve an accuracy of 89.36% using CDEK. A series of ablation experiments are conducted on various modules, the effectiveness of CDEK is demonstrated through extensive experimentation. Contributing solutions to the sustainable development of smart agriculture.
- 23 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Big Data
- Vol. 12 (2) , 430-446
Visual Question Answer Model Based on Crop Diseases External Knowledge for Smart Agriculture
Current crop disease VQA models primarily focus on object counting and detection. However, accurately identifying various disease stages and determining control measures require additional knowledge beyond images, including information about control methods and pathogen details. To address this, the VQA dataset relies on the images and questions to retrieve relevant external knowledge. To realize the VQA task of crop diseases external knowledge, we construct the Visual Question Answer Model Based on Crop Diseases External Knowledge for Smart Agriculture (CDEK). CDEK integrates two categories of external knowledge on 66 common dicotyledonous crop diseases by utilizing large language models and agricultural knowledge repositories to enhance knowledge retrieval. This integration enhances the richness of external knowledge repositories. Enhancing fine-grained image understanding in CDEK through the utilization of Stack Self-Attention (SSA), utilising Cross-Attention and contrastive learning of two external knowledge, with a focus on emphasizing image-related semantic information during training. Finally, an automatic patrol disease detection robot is constructed based on Tensor Processing Unit (TPU) devices and the CDEK model. CDEK achieves an accuracy of 61.7% on the publicly available dataset OK-VQA, surpassing the previous state-of-the-art by 5.1%. Furthermore, we construct the OKiCD-VQA dataset for crop diseases external knowledge and achieve an accuracy of 89.36% using CDEK. A series of ablation experiments are conducted on various modules, the effectiveness of CDEK is demonstrated through extensive experimentation. Contributing solutions to the sustainable development of smart agriculture.
- Open Access
- 28 February 2025
- Published by MDPI AG in Electronics
- Vol. 14 (5)
Document-Level Causal Event Extraction Enhanced by Temporal Relations Using Dual-Channel Neural Network
Event–event causal relation extraction (ECRE) represents a critical yet challenging task in natural language processing. Existing studies primarily focus on extracting causal sentences and events, despite the use of joint extraction methods for both tasks. However, both pipeline methods and joint extraction approaches often overlook the impact of document-level event temporal sequences on causal relations. To address this limitation, we propose a model that incorporates document-level event temporal order information to enhance the extraction of implicit causal relations between events. The proposed model comprises two channels: an event–event causal relation extraction channel (ECC) and an event–event temporal relation extraction channel (ETC). Temporal features provide critical support for modeling node weights in the causal graph, thereby improving the accuracy of causal reasoning. An Association Link Network (ALN) is introduced to construct an Event Causality Graph (ECG), incorporating an innovative design that computes node weights using Kullback–Leibler divergence and Gaussian kernels. The experimental results indicate that our model significantly outperforms baseline models in terms of accuracy and weighted average F1 scores.
- 28 February 2025
- Published by MDPI AG in Electronics
- Vol. 14 (5)
Open AccessDocument-Level Causal Event Extraction Enhanced by Temporal Relations Using Dual-Channel Neural Network
Event–event causal relation extraction (ECRE) represents a critical yet challenging task in natural language processing. Existing studies primarily focus on extracting causal sentences and events, despite the use of joint extraction methods for both tasks. However, both pipeline methods and joint extraction approaches often overlook the impact of document-level event temporal sequences on causal relations. To address this limitation, we propose a model that incorporates document-level event temporal order information to enhance the extraction of implicit causal relations between events. The proposed model comprises two channels: an event–event causal relation extraction channel (ECC) and an event–event temporal relation extraction channel (ETC). Temporal features provide critical support for modeling node weights in the causal graph, thereby improving the accuracy of causal reasoning. An Association Link Network (ALN) is introduced to construct an Event Causality Graph (ECG), incorporating an innovative design that computes node weights using Kullback–Leibler divergence and Gaussian kernels. The experimental results indicate that our model significantly outperforms baseline models in terms of accuracy and weighted average F1 scores.
- Open Access
- 21 November 2024
- Published by Elsevier in Plant Phenomics
- Vol. 6
Informed-Learning-Guided Visual Question Answering Model of Crop Disease
In contemporary agriculture, experts develop preventative and remedial strategies for various disease stages in diverse crops. Decision-making regarding the stages of disease occurrence exceeds the capabilities of single-image tasks, such as image classification and object detection. Consequently, research now focuses on training visual question answering (VQA) models. However, existing studies concentrate on identifying disease species rather than formulating questions that encompass crucial multiattributes. Additionally, model performance is susceptible to the model structure and dataset biases. To address these challenges, we construct the informed-learning-guided VQA model of crop disease (ILCD). ILCD improves model performance by integrating coattention, a multimodal fusion model (MUTAN), and a bias-balancing (BiBa) strategy. To facilitate the investigation of various visual attributes of crop diseases and the determination of disease occurrence stages, we construct a new VQA dataset called the Crop Disease Multi-attribute VQA with Prior Knowledge (CDwPK-VQA). This dataset contains comprehensive information on various visual attributes such as shape, size, status, and color. We expand the dataset by integrating prior knowledge into CDwPK-VQA to address performance challenges. Comparative experiments are conducted by ILCD on the VQA-v2, VQA-CP v2, and CDwPK-VQA datasets, achieving accuracies of 68.90%, 49.75%, and 86.06%, respectively. Ablation experiments are conducted on CDwPK-VQA to evaluate the effectiveness of various modules, including coattention, MUTAN, and BiBa. These experiments demonstrate that ILCD exhibits the highest level of accuracy, performance, and value in the field of agriculture. The source codes can be accessed at https://github.com/SdustZYP/ILCD-master/tree/main.
- 21 November 2024
- Published by Elsevier in Plant Phenomics
- Vol. 6
Open AccessInformed-Learning-Guided Visual Question Answering Model of Crop Disease
In contemporary agriculture, experts develop preventative and remedial strategies for various disease stages in diverse crops. Decision-making regarding the stages of disease occurrence exceeds the capabilities of single-image tasks, such as image classification and object detection. Consequently, research now focuses on training visual question answering (VQA) models. However, existing studies concentrate on identifying disease species rather than formulating questions that encompass crucial multiattributes. Additionally, model performance is susceptible to the model structure and dataset biases. To address these challenges, we construct the informed-learning-guided VQA model of crop disease (ILCD). ILCD improves model performance by integrating coattention, a multimodal fusion model (MUTAN), and a bias-balancing (BiBa) strategy. To facilitate the investigation of various visual attributes of crop diseases and the determination of disease occurrence stages, we construct a new VQA dataset called the Crop Disease Multi-attribute VQA with Prior Knowledge (CDwPK-VQA). This dataset contains comprehensive information on various visual attributes such as shape, size, status, and color. We expand the dataset by integrating prior knowledge into CDwPK-VQA to address performance challenges. Comparative experiments are conducted by ILCD on the VQA-v2, VQA-CP v2, and CDwPK-VQA datasets, achieving accuracies of 68.90%, 49.75%, and 86.06%, respectively. Ablation experiments are conducted on CDwPK-VQA to evaluate the effectiveness of various modules, including coattention, MUTAN, and BiBa. These experiments demonstrate that ILCD exhibits the highest level of accuracy, performance, and value in the field of agriculture. The source codes can be accessed at https://github.com/SdustZYP/ILCD-master/tree/main.
- 21 September 2024
- Published by Springer Nature in Multimedia Systems
- Vol. 30 (5) , 1-17
Unsupervised deep metric learning algorithm for crop disease images based on knowledge distillation networks
- 21 September 2024
- Published by Springer Nature in Multimedia Systems
- Vol. 30 (5) , 1-17
Unsupervised deep metric learning algorithm for crop disease images based on knowledge distillation networks
- Open Access
- 16 August 2024
- Published by Springer Nature in Research Square
A Novel Approach to Extract Cross-Organization Collaborative Process Models from Emergency Plans of Natural Disaster
Emergency response of natural disaster is a complex process involving multiple response levels and cross-organization collaboration. Traditionally, cross-organization collaborative process models of emergency response are constructed based on the common experiences of domain experts and business process modelers. Textual emergency plans are not conducive to emergency performers quickly understanding response tasks and managers analyzing and evaluating the quality of emergency plans of natural disaster. In this paper, a novel approach is proposed to automatically extract cross-organization collaborative process models from emergency plans for supporting emergency response process modeling and the automation analysis of emergency plans. First, an attention mechanism is introduced into the Bi-directional Long Short-Term Memory network combined with a Conditional Random Field (BiLSTM-Attention-CRF), which is trained to identify process elements from sentences. Second, inter-organization relationships are extracted to generate a cross-organization collaborative network of emergency response. Then, response tasks and task relationships are extracted to generate emergency response sub-process models for all organizations. Finally, inter-organization relationships integrate all sub-process models into a global cross-organization collaborative process model of emergency response. A real-world dataset is collected for experimental evaluation and the results illustrate that the proposed approach is capable of extracting automatically cross-organization collaborative process models from emergency plans of natural disaster, and the automatically extracted models are highly consistent with the manually extracted models.
- 16 August 2024
- Published by Springer Nature in Research Square
Open AccessA Novel Approach to Extract Cross-Organization Collaborative Process Models from Emergency Plans of Natural Disaster
Emergency response of natural disaster is a complex process involving multiple response levels and cross-organization collaboration. Traditionally, cross-organization collaborative process models of emergency response are constructed based on the common experiences of domain experts and business process modelers. Textual emergency plans are not conducive to emergency performers quickly understanding response tasks and managers analyzing and evaluating the quality of emergency plans of natural disaster. In this paper, a novel approach is proposed to automatically extract cross-organization collaborative process models from emergency plans for supporting emergency response process modeling and the automation analysis of emergency plans. First, an attention mechanism is introduced into the Bi-directional Long Short-Term Memory network combined with a Conditional Random Field (BiLSTM-Attention-CRF), which is trained to identify process elements from sentences. Second, inter-organization relationships are extracted to generate a cross-organization collaborative network of emergency response. Then, response tasks and task relationships are extracted to generate emergency response sub-process models for all organizations. Finally, inter-organization relationships integrate all sub-process models into a global cross-organization collaborative process model of emergency response. A real-world dataset is collected for experimental evaluation and the results illustrate that the proposed approach is capable of extracting automatically cross-organization collaborative process models from emergency plans of natural disaster, and the automatically extracted models are highly consistent with the manually extracted models.
- 18 March 2024
- Published by Springer Nature in Applied Intelligence
- Vol. 54 (5) , 3990-4011
TV-ALP: A log dataset of television assembly line production under multi-person collaboration for process mining research
- 18 March 2024
- Published by Springer Nature in Applied Intelligence
- Vol. 54 (5) , 3990-4011
TV-ALP: A log dataset of television assembly line production under multi-person collaboration for process mining research
- 17 August 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (8) , 22189-22220
APD-229: a textual-visual database for agricultural pests and diseases
- 17 August 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (8) , 22189-22220
APD-229: a textual-visual database for agricultural pests and diseases