A5101812281- Topic Modeling
- Network Security and Intrusion Detection
- Natural Language Processing Techniques
- Text and Document Classification Technologies
- Infrastructure Resilience and Vulnerability Analysis
- Sentiment Analysis and Opinion Mining
- Multimodal Machine Learning Applications
- Software System Performance and Reliability
- Advanced Computational Techniques and Applications
- Information and Cyber Security
- Geoscience and Mining Technology
- Expert finding and Q&A systems
- Quantum-Dot Cellular Automata
- Power Systems and Technologies
- Security and Verification in Computing
- Software-Defined Networks and 5G
- Anomaly Detection Techniques and Applications
- Advanced Text Analysis Techniques
- Machine Learning and Data Classification
Changchun University of Science and Technology
2015-2024
Institute of Information Engineering
2021-2022
University of Chinese Academy of Sciences
2021-2022
Chinese Academy of Sciences
2020-2021
Fine-Grained Entity Typing (FGET) is a task that aims at classifying an entity mention into wide range of label types. Recent researches improve the performance by imposing label-relational inductive bias based on hierarchy labels or co-occurrence graph. However, they usually overlook explicit interactions between instances and which may limit capability representations. Therefore, we propose novel method two-phase graph network for FGET to enhance representations, via relational biases...
Sentence similarity learning is a vital task in Natural Language Processing (NLP) such as document summarization and question answering. In this paper, we propose method to compute semantic between sentences which based on the attention hybrid model. Our utilizes Bidirectional Long Short-Term Memory Networks (BLSTM) Convolutional Neural (CNN) extract features of sentence. And it learns representation each sentence with word-level attention. Then attentive representations are concatenated fed...
In the area of network development, especially cloud computing, security has been a long-standing issue. order to better utilize physical resources, service providers usually allocate different tenants on same machine, i.e., resources such as CPU, memory, and devices are shared among multiple host. Virtual machine (VM) co-resident attack, serious threat in this sharing methodology, includes malicious who tend steal private data. Currently, most solutions focus how eliminate known specific...
Resource allocation is the process of optimizing rare resources. In area security, how to allocate limited resources protect a massive number targets especially challenging. This paper addresses this resource issue by constructing game theoretic model. A defender and an attacker are players interaction formulated as trade-off between protecting consuming The action cost which necessary role resource, considered in proposed Additionally, bounded rational behavior model (Quantal Response, QR),...
Distantly supervised relation extraction suffers from the influence of noise data. Some works solved this issue with relation-aware attention based on multi-instance learning to reduce weights data in sentence bag, which achieved remarkable results. However, relationships label-label and label-sentence semantic space that can enhance label representation effectively was ignored. The enhanced keep does not contain corresponding away space. In view this, we propose a novel method capture two...