检索结果-内蒙古大学图书馆

29th International Conference on Computational Linguistics, COLING 2022

作者： Yang, Zeng Zhang, Linhai Zhou, Deyu School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China

Few-shot named entity recognition (NER) aims at identifying named entities based on only few labeled instances. Current few-shot NER methods focus on leveraging existing datasets in the rich-resource domains which might fail in a training-from-scratch setting where no source-domain data is used. To tackle training-from-scratch setting, it is crucial to make full use of the annotation information (the boundaries and entity types). Therefore, in this paper, we propose a novel multi-task (Seed, Expand and Entail) learning framework, SEE-Few, for Few-shot NER without using source domain data. The seeding and expanding modules are responsible for providing as accurate candidate spans as possible for the entailing module. The entailing module reformulates span classification as a textual entailment task, leveraging both the contextual clues and entity type information. All the three modules share the same text encoder and are jointly learned. Experimental results on four benchmark datasets under the training-from-scratch setting show that the proposed method outperformed state-of-the-art few-shot NER methods with a large margin. Our code is available at https://***/unveiled-the-red-hat/SEE-Few. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Complicate then Simplify: A Novel Way to Explore Pre-trained Models for Text Classification 29

Complicate then Simplify: A Novel Way to Explore Pre-trained...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Zhang, Xu Liu, Zejie Xiang, Yanzheng Zhou, Deyu School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China

In the developing context of pre-trained models (PTMs), the performance of text classification has been continuously improved by directly employing the features generated by PTMs. However, such a way might not fully explore the knowledge in PTMs as it is constrained by the difficulty of the task. Compared to a difficult task, the learning algorithms tend to saturate early on the simple task. Moreover, the native sentence representations derived from BERT are prone to be collapsed and directly employing such representation for text classification might fail to fully capture discriminative features. In order to address these issues, in this paper we propose a novel framework for text classification which implements a two-stage training strategy. In the pre-training stage, auxiliary labels are introduced to increase the task difficulties and to fully exploit the knowledge in the pre-trained model. In the fine-tuning stage, the textual representation learned in the pre-training stage is employed and the classifier is fine-tuned to obtain better classification performance. Experiments were conducted on six text classification corpora and the results showed that the proposed framework outperformed several state-of-the-art baselines. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Temporal Knowledge Graph Completion with Approximated Gaussian Process Embedding 29

Temporal Knowledge Graph Completion with Approximated Gaussi...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Zhang, Linhai Zhou, Deyu School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China

Knowledge Graphs (KGs) stores world knowledge that benefits various reasoning-based applications. Due to their incompleteness, a fundamental task for KGs, which is known as Knowledge Graph Completion (KGC), is to perform link prediction and infer new facts based on the known facts. Recently, link prediction on the temporal KGs becomes an active research topic. Numerous Temporal Knowledge Graph Completion (TKGC) methods have been proposed by mapping the entities and relations in TKG to the high-dimensional representations. However, most existing TKGC methods are mainly based on deterministic vector embeddings, which are not flexible and expressive enough. In this paper, we propose a novel TKGC method, TKGC-AGP, by mapping the entities and relations in TKG to the approximations of multivariate Gaussian processes (MGPs). Equipped with the flexibility and capacity of MGP, the global trends as well as the local fluctuations in the TKGs can be simultaneously modeled. Moreover, the temporal uncertainties can be also captured with the kernel function and the covariance matrix of MGP. Moreover, a first-order Markov assumption-based training algorithm is proposed to effective optimize the proposed method. Experimental results show the effectiveness of the proposed approach on two real-world benchmark datasets compared with some state-of-the-art TKGC methods. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Cooperative Caching Strategy Based on Two-Layer Caching Model for Remote Sensing Satellite networks

引用

computers, Materials & Continua 2023年第5期75卷 3903-3922页

作者： Rui Xu Xiaoqiang Di Hao Luo Hui Qi Xiongwen He Wenping Lei School of Computer Science and Technology Changchun University of Science and TechnologyChangchun130022China School of Information Engineering Henan Institute of Science and TechnologyXinxiang453003China Jilin Province Key Laboratory of Network and Information Security Changchun University of Science and TechnologyChangchun130022China Information Center Changchun University of Science and TechnologyChangchun130022China Beijing Institute of Spacecraft System Engineering Beijing100094China Beijing Institute of Space Mechanic and Electricity Beijing100094China

In information Centric networking(ICN)where content is the object of exchange,in-network caching is a unique functional feature with the ability to handle data storage and distribution in remote sensing satellite *** up cache space at any node enables users to access data nearby,thus relieving the processing pressure on the ***,the existing caching strategies still suffer from the lack of global planning of cache contents and low utilization of cache resources due to the lack of fine-grained division of cache *** address the issues mentioned,a cooperative caching strategy(CSTL)for remote sensing satellite networks based on a two-layer caching model is *** two-layer caching model is constructed by setting up separate cache spaces in the satellite network and the ground *** caching of popular contents in the region at the ground station to reduce the access delay of users.A content classification method based on hierarchical division is proposed in the satellite network,and differential probabilistic caching is employed for different levels of *** cached content is also dynamically adjusted by analyzing the subsequent changes in the popularity of the cached *** the two-layer caching model,ground stations and satellite networks collaboratively cache to achieve global planning of cache contents,rationalize the utilization of cache resources,and reduce the propagation delay of remote sensing *** results show that the CSTL strategy not only has a high cache hit ratio compared with other caching strategies but also effectively reduces user request delay and server load,which satisfies the timeliness requirement of remote sensing data transmission.

关键词： information centric networking caching strategy two-layer caching model hierarchical division

来源：评论

学校读者我要写书评

暂无评论

FTGraph: A Flexible Tree-Based Graph Store on Persistent Memory for Large-Scale Dynamic Graphs

FTGraph: A Flexible Tree-Based Graph Store on Persistent Mem...

引用

2024 IEEE International Conference on Cluster Computing, CLUSTER 2024

作者： Sun, Gan Zhou, Jiang Li, Bo Gu, Xiaoyan Wang, Weiping He, Shuibing Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Cyberspace Security Defense Beijing China College of Computer Science and Technology Zhejiang University Hangzhou China

ISBN: (纸本)9798350358711

Traditional in-memory graph systems often suffer from scalability due to the limited capacity and volatility of DRAM. Emerging non-volatile memory (NVM) provides an opportunity to achieve highly scalable and high-performance graph stores for its large capacity and persistence characteristics. However, directly deploying current in-memory graph storage systems on NVM would cause significant inefficiencies in NVM access, as their graph organization designed for DRAM may incur higher write amplification, crash inconsistency and costly concurrency control overhead in NVM for write-intensive work-loads. In this paper, we propose FTGraph, a Flexible Tree-based Graph storage system, for both efficient dynamical graph updates and analysis. To achieve this goal, we introduce a novel degree-aware suffix bit tree to effectively manage vertices and edges of the graph, enabling adaptability to real-world power-law degree distributions while significantly reducing NVM writes. Based on it, we adopt two optimization methods, logical vertex ID translation and sequential storage, for vertices with very high degrees within the tree to enhance graph analysis operations. We further integrate 8B NVM atomic writes with optimistic version-based concurrency control through a dual bitmap design to ensure low-overhead, log-free crash consistency and reduce read-writer contention. Experimental results show that FTGraph achieves up to 21.2× higher update performance and up to 85.4 × higher analysis performance, compared with state-of-the-art dynamic graph systems implemented on NVMs. © 2024 IEEE.

关键词： Concurrency control

来源：评论

学校读者我要写书评

暂无评论

A State Synchronization Method of Mimic Architecture Device 8

A State Synchronization Method of Mimic Architecture Device

引用

8th International Symposium on Advances in Electrical, Electronics, and computer Engineering, ISAEECE 2023

作者： Shao, ZhiPeng Zhang, Bo Xi, ZeSheng State Grid Smart Grid Research Institute co. Ltd. Nanjing210003 China State Grid Key Laboratory of Information & Network Security Nanjing210003 China

ISBN: (纸本)9781510666290

In mimic architecture devices, programs with equivalent functions are usually implemented on heterogeneous executors. However, due to the differences in the scheduling order of threads among executors, the outputs of programs are also different. Usually, the scheduler in the mimic device needs to compare the outputs of different executors to decide the final output. The difference between the outputs will have a significant impact on the arbitration of the scheduler, causing executor's output cannot pass the arbitration, and the program cannot function normally. In order to solve this problem, some researchers proposed a state synchronization method based on relative time. This method can effectively solve the problem of program state synchronization in multiple heterogeneous executors, but it can be improved in completeness and running efficiency. Based on this method, this paper proposes an improved program synchronization method based on targeted reply, which considers the synchronization problem in more scenarios, saves the communication overhead caused by synchronization, and improves the operation efficiency of the system. The experimental results show that the method is effective to some extent. © 2023 SPIE. All rights reserved.

关键词： Synchronization

来源：评论

学校读者我要写书评

暂无评论

Table-based fact verification with self-labeled keypoint alignment 29

Table-based fact verification with self-labeled keypoint ali...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Zhao, Guangzhen Yang, Peng School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China

Table-based fact verification aims to verify whether a statement sentence is trusted or fake. Most existing methods rely on graph feature or data augmentation but fail to investigate evidence correlation between the statement and table effectively. In this paper, we propose a self-Labeled keypoint Alignment model, named LKA, to explore the correlation between the two. Specifically, a dual-view alignment module based on the statement and table views is designed to discriminate the salient words through multiple interactions, where one regular and one adversarial alignment network cooperatively character the alignment discrepancy. Considering the interaction characteristic inherent in the alignment module, we introduce a novel mixture-of-experts block to elaborately integrate the interacted information for supporting the alignment and final classification. Furthermore, a contrastive learning loss is utilized to learn the precise representation of the structure-involved words, encouraging the words closer to words with the same table attribute and farther from the words with the unrelated attribute. Experimental results on three widely-studied datasets show that our model can outperform the state-of-the-art baselines and capture interpretable evidence words. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Brillouin Frequency Shift Extraction for BOTDA Based on Gramian Angular Fields 4

Brillouin Frequency Shift Extraction for BOTDA Based on Gram...

引用

4th International Computational Imaging Conference, CITA 2024

作者： Zhu, Borong Zhang, Zhihao Qian, Yuhao Ma, Xiaole Wang, Liang Yu, Kuanglu Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China Institute of Information Science School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China National Engineering Laboratory for Next Generation Internet Access System School of Optics and Electronic Information Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9781510688834

To accurately extract Brillouin frequency shift of BOTDA with large sweeping step sizes, a novel structure of GAFCNN is proposed, combining time series coding with convolutional neural networks. The experimental data validation results demonstrate that the GAFCNN is capable of obtaining more accurate results under large sweep steps and low signal-to-noise ratios (SNRs) than other current methods. © 2025 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Efficient Module-Lattice-based Certificateless Online/Offline Signcryption Scheme for Internet of Medical Things

引用

IEEE Internet of Things Journal 2025年

作者： Bai, Ye He, Debiao Yang, Zhichao Luo, Min Peng, Cong Wuhan University Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan430072 China Wuhan University School of Cyber Science and Engineering Wuhan430072 China Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan250014 China Naval University of Engineering Department of Information Security Wuhan430000 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Industrial Network and Information System Security Jinan250014 China

The Internet of Medical Things (IoMT) has achieved remote diagnosis and real-time health monitoring through intelligent sensor devices and Internet of Things (IoT) technology, providing great convenience for analyzing medical conditions between doctors and patients. However, sensitive information such as patient medical data may face security challenges such as data leakage and abuse during transmission in the IoMT. To ensure the confidentiality and unforgeability of medical data transmission, scholars have proposed many cryptographic schemes. With the development of quantum computers, schemes based on traditional cryptographic primitives have become insecure. Existing cryptographic schemes for IoMT cannot simultaneously meet the security requirements of high communication performance, low computational overhead, and resistance to quantum attacks. Therefore, we propose an efficient module-lattice-based certificateless online/offline signcryption (MLCLOOSC) scheme resistant to quantum attacks while meeting the confidentiality and unforgeability requirements under Type I and Type II attacks. Compared with five recent CLOOSC schemes, theoretical analysis, and experimental test results show that the proposed scheme outperforms the other five schemes regarding computational and communication costs and security. Therefore, our scheme is more suitable for application in IoMT scenarios. © 2014 IEEE.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Resource Cooperative Scheduling Optimization Considering security in Edge Mobile networks 19th

Resource Cooperative Scheduling Optimization Considering Sec...

引用

19th EAI International Conference on Collaborative Computing: networking, Applications and Worksharing, CollaborateCom 2023

作者： Fang, Cheng Yang, Peng Yi, Meng Du, Miao Li, Bing Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing China School of Computer Science and Engineering Southeast University Nanjing China School of Cyber Science and Engineering Southeast University Nanjing China

ISBN: (纸本)9783031545207

With the rapid development of technologies such as the Internet of Things and artificial intelligence, the contradiction between limited user computing resources and real-time, fast, and safe processing of large amounts of data has become an urgent issue. The emergence of edge computing provides IoT applications with a low-latency, high-bandwidth, and high-performance computing service. Due to the complexity and dynamics of the edge computing environment itself, and the limited resources of the terminal, the security issue of resource collaborative scheduling in the edge mobile network has become an important research topic. Different from existing work, this paper proposes an efficient and secure multi-user resource cooperative scheduling model, which comprehensively considers resource allocation, task offloading, QoE requirements, and data security. In the model, ChaCha20 encryption technology is introduced as a security mechanism to prevent data from being maliciously stolen by attackers during the offloading process, and computing speed is used as an indicator to quantify QoE requirements. A resource collaborative scheduling algorithm that integrates security mechanisms and computing acceleration is also proposed to minimize the total cost of optimizing the edge computing system. Finally, the effectiveness and superiority of the model and algorithm are verified by simulation experiments. © ICST Institute for computer Sciences, Social Informatics and Telecommunications Engineering 2024.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：