A5034606659- Semantic Web and Ontologies
- Topic Modeling
- Natural Language Processing Techniques
- Advanced Graph Neural Networks
- Service-Oriented Architecture and Web Services
- Logic, Reasoning, and Knowledge
- Multimodal Machine Learning Applications
- Biomedical Text Mining and Ontologies
- Domain Adaptation and Few-Shot Learning
- Advanced Database Systems and Queries
- Data Quality and Management
- Advanced Text Analysis Techniques
- Rough Sets and Fuzzy Logic
- Artificial Intelligence in Law
- Text and Document Classification Technologies
- Speech and dialogue systems
- AI-based Problem Solving and Planning
- Cognitive Computing and Networks
- Multi-Agent Systems and Negotiation
- Sentiment Analysis and Opinion Mining
- Data Management and Algorithms
- Oil and Gas Production Techniques
- Recommender Systems and Techniques
- Imbalanced Data Classification Techniques
- Bayesian Modeling and Causal Inference
Southeast University
2016-2025
Changchun University of Technology
2025
Yangtze University
2022-2024
Zunyi Medical University
2024
Southeast University
2009-2023
Ministry of Education of the People's Republic of China
2023
Hubei University of Medicine
2022
Computer Network Information Center
2019-2021
Henan University
2021
Wuhan University
2021
Hydrogels with adhesive properties have the potential for rapid haemostasis and wound healing in uncontrolled non-pressurized surface bleeding. Herein, a typical hydrogen bond-crosslinked hydrogel above functions was constructed by directly mixing solutions of humic acid (HA) polyvinylpyrrolidone (PVP), which HA worked as crosslinking agent to form bonds PVP. By altering concentration HA, cluster stable uniform hydrogels were prepared within 10 s. The dynamic reversible nature gave HA/PVP...
Continual relation extraction is an important task that focuses on extracting new facts incrementally from unstructured text. Given the sequential arrival order of relations, this prone to two serious challenges, namely catastrophic forgetting and order-sensitivity. We propose a novel curriculum-meta learning method tackle above challenges in continual extraction. combine meta curriculum quickly adapt model parameters reduce interference previously seen tasks current task. design...
Visual modality recently has aroused extensive attention in the fields of knowledge graph and multimedia because a lot real-world is multi-modal nature. However, it currently unclear to what extent visual can improve performance tasks over unimodal models, equally treating structural features may encode too much irrelevant information from images. In this paper, we probe utility auxiliary context representation learning perspective by designing Relation Sensitive Multi-modal Embedding model,...
Possibilistic logic provides a convenient tool for dealing with uncertainty and handling inconsistency. In this paper, we propose possibilistic description logics as an extension of logics, which are family well-known ontology languages. We first give the syntax semantics define several inference services in logics. show that these serviced can be reduced to task computing inconsistency degree knowledge base Since suffer from drowning problem, is, axioms whose confidence degrees less than or...
With the continuous development of intelligent technologies, knowledge graph, backbone artificial intelligence, has attracted much attention from both academic and industrial communities due to its powerful capability representation reasoning. In recent years, graph been widely applied in different kinds applications, such as semantic search, question answering, management so on. Techniques for building Chinese graphs are also developing rapidly have constructed support various applications....
ChatGPT is a powerful large language model (LLM) that covers knowledge resources such as Wikipedia and supports natural question answering using its own knowledge. Therefore, there growing interest in exploring whether can replace traditional knowledge-based (KBQA) models. Although have been some works analyzing the performance of ChatGPT, still lack large-scale, comprehensive testing various types complex questions to analyze limitations model. In this paper, we present framework follows...
This paper investigates a challenging problem,which is known as fine-grained image classification(FGIC). Different from conventional computer visionproblems, FGIC suffers the large intraclassdiversities and subtle inter-class differences.Existing approaches are limited to exploreonly visual information embedded in images.In this paper, we present novel approachwhich can use handy prior knowledge eitherstructured bases or unstructured text tofacilitate FGIC. Specifically, propose...
Event detection (ED) aims at detecting event trigger words in sentences and classifying them into specific types.In real-world applications, ED typically does not have sufficient labelled data, thus can be formulated as a few-shot learning problem.To tackle the issue of low sample diversity ED, we propose novel knowledge-based fewshot method which uses definition-based encoder to introduce external knowledge prior types.Furthermore, provides limited imperfect coverage types, an adaptive...