检索结果-内蒙古大学图书馆

17th Chinese intelligent Systems Conference, CISC 2021

作者： Ouyang, Suyu Du, Junping Shao, Yingxia Li, Ang Xu, Xin Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia School of Computer Science Beijing University of Posts and Telecommunications Beijing100876 China

ISBN: (纸本)9789811663192

Knowledge representation learning can realize the representation of entity and relation semantic information by projecting the triple entity or relation in knowledge graph into vector space, and can effectively calculate entity, relation and their complex semantic association. However, most of the existing models only use the structure information of triples, ignoring the semantic rich entity description. In addition, knowledge representation learning methods usually use negative sampling method. Through random sampling, the negative samples generated by this method are easy to be recognized by the model, and with the iteration of training, the contribution to the improvement of the model performance becomes smaller and smaller. Therefore, we propose a Knowledge Representation learning method based on Generative adversarial network and Pre-training language model (KRGP). Specifically, it uses the idea of generative adversarial network, semantic matching model and translation distance model to generate high-quality negative samples. We combine descriptions of head and tail entities and relations corresponding to negative sample triples into text sequences, and then use next sentence prediciton task of BERT to transform text sequences into a binary classification problem. Experimental results show that this method can improve the performance of link prediction and triple classification on multiple data sets. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Relational Triple Extraction Method Based on Feature Reasoning for Technological Patents 8

A Relational Triple Extraction Method Based on Feature Reaso...

引用

8th IEEE International Conference on Cloud Computing and Intelligence Systems, CCIS 2022

作者： Fang, Runze Du, Junping Shao, Yingxia Guan, Zeli Beijing University of Posts and Telecommunications School of Computer Science Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia Beijing100876 China

ISBN: (纸本)9781665477352

The relation triples extraction method based on table filling can address the issues of relation overlap and bias propagation. However, most of them only establish separate table features for each relationship, which ignores the implicit relationship between different entity pairs and different relationship features. Therefore, a feature reasoning relational triple extraction method based on table filling for technological patents is proposed to explore the integration of entity recognition and entity relationship, and to extract entity relationship triples from multi-source scientific and technological patents data. Compared with the previous methods, the method we proposed for relational triple extraction has the following advantages: 1) The table filling method that saves more running space enhances the speed and efficiency of the model. 2) Based on the features of existing token pairs and table relations, reasoning the implicit relationship features, and improve the accuracy of triple extraction. On three benchmark datasets, we evaluated the model we suggested. The result suggest that our model is advanced and effective, and it performed well on most of these datasets. © 2022 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Beyond Fine-Tuning: Efficient and Effective Fed-Tuning for Mobile/Web Users 23

Beyond Fine-Tuning: Efficient and Effective Fed-Tuning for M...

引用

2023 World Wide Web Conference, WWW 2023

作者： Liu, Bingyan Cai, Yifeng Bi, Hongzhe Zhang, Ziqi Li, Ding Guo, Yao Chen, Xiangqun Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia School of Computer Science Beijing University of Posts and Telecommunications Beijing China Moe Key Lab of Hcst School of Computer Science Peking University Beijing China School of Computer Science Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781450394161

Fine-tuning is a typical mechanism to achieve model adaptation for mobile/web users, where a model trained by the cloud is further retrained to fit the target user task. While traditional fine-tuning has been proved effective, it only utilizes local data to achieve adaptation, failing to take advantage of the valuable knowledge from other mobile/web users. In this paper, we attempt to extend the local-user fine-tuning to multi-user fed-tuning with the help of Federated Learning (FL). Following the new paradigm, we propose EEFT, a framework aiming to achieve Efficient and Effective Fed-Tuning for mobile/web users. The key idea is to introduce lightweight but effective adaptation modules to the pre-trained model, such that we can freeze the pre-trained model and just focus on optimizing the modules to achieve cost reduction and selective task cooperation. Extensive experiments on our constructed benchmark demonstrate the effectiveness and efficiency of the proposed framework. © 2023 ACM.

关键词： Cost reduction

来源：评论

学校读者我要写书评

暂无评论

CDM: Content Diffusion Model for Information-Centric Networks

引用

Journal of computer Science & technology 2021年第6期36卷 1431-1451页

作者： Bo Chen Liang Liu Hua-Dong Ma Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia Beijing University of Posts and TelecommunicationsBeijing 100876China School of Computer Science Beijing University of Posts and TelecommunicationsBeijing 100876China

This paper proposes the Content Diffusion Model(CDM)for modeling the content diffusion process in information-centric networking(ICN).CDM is inspired by the epidemic model and it provides a method of theoretical quantitative analysis for the content diffusion process in ***,CDM introduces the key functions to formalize the key factors that influence the content diffusion process,and thus it can construct the model via a simple but efficient ***,we derive CDM by using different combinations of those key factors and put them into several typical ICN scenarios,to analyze the characteristics during the diffusion process such as diffusion speed,diffusion scope,average fetching hops,changing and final state,which can greatly help to analyze the network performance and application design.A series of experiments are conducted to evaluate the efficacy and accuracy of *** results show that CDM can accurately illustrate and model the content diffusion process in ICN.

关键词： information-centric networking content diffusion modeling

来源：评论

学校读者我要写书评

暂无评论

Brain-inspired artificial intelligence research: A review

引用

Science China(Technological Sciences) 2024年第8期67卷 2282-2296页

作者： WANG GuoYin BAO HuaNan LIU Qun ZHOU TianGang WU Si HUANG TieJun YU ZhaoFei LU CeWu GONG YiHong ZHANG ZhaoXiang HE Sheng Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and TelecommunicationsChongqing 400065China Key Laboratory of Cyberspace Big Data Intelligent Security Chongqing University of Posts and TelecommunicationsChongqing 400065China College of Computer and Information Science Chongqing Normal UniversityChongqing 401331China State Key Laboratory of Brain and Cognitive Science Institute of BiophysicsChinese Academy of SciencesBeijing 100101China School of Psychological and Cognitive Sciences Peking UniversityBeijing 100871China State Key Laboratory of Multimedia Information Processing School of Computer SciencePeking UniversityBeijing 100871China Department of Computer Science School of ElectronicsInformation and Electrical EngineeringShanghai Jiao Tong UniversityShanghai 200240China Faculty of Electronic and Information Engineering Xi’an Jiaotong UniversityXi’an 710049China The Center for Research on Intelligent Perception and Computing Institute of AutomationChinese Academy of SciencesBeijing 100190China Institute of Biophysics Chinese Academy of SciencesBeijing 100101China

Artificial intelligence(AI) systems surpass certain human intelligence abilities in a statistical sense as a whole, but are not yet the true realization of these human intelligence abilities and behaviors. There are differences, and even contradictions, between the cognition and behavior of AI systems and humans. With the goal of achieving general AI, this study contains a review of the role of cognitive science in inspiring the development of the three mainstream academic branches of AI based on the three-layer framework proposed by David Marr, and the limitations of the current development of AI are explored and analyzed. The differences and inconsistencies between the cognition mechanisms of the human brain and the computation mechanisms of AI systems are analyzed. They are found to be the cause of the differences and contradictions between the cognition and behavior of AI systems and humans. Additionally, eight important research directions and their scientific issues that need to focus on braininspired AI research are proposed: highly imitated bionic information processing, a large-scale deep learning model that balances structure and function, multi-granularity joint problem solving bidirectionally driven by data and knowledge, AI models that simulate specific brain structures, a collaborative processing mechanism with the physical separation of perceptual processing and interpretive analysis, embodied intelligence that integrates the brain cognitive mechanism and AI computation mechanisms,intelligence simulation from individual intelligence to group intelligence(social intelligence), and AI-assisted brain cognitive intelligence.

关键词： artificial intelligence cognitive science brain science intelligence science large language model

来源：评论

学校读者我要写书评

暂无评论

Text-Image Scene Graph Fusion for Multimodal Named Entity Recognition

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 2828-2839页

作者： Cheng, Jian Long, Kaifang Zhang, Shuang Zhang, Tian Ma, Lianbo Cheng, Shi Guo, Yinan State Key Laboratory for Intelligent Coal Mining and Strata Control Research Institute of Mine Big Data Chinese Institute of Coal Science Beijing100013 China Northeastern University College of Software Shenyang110819 China Shaanxi Normal University College of Computer Science Xi'an710062 China China University of Mining and Technology Xuzhou221116 China

With the popularity and widespread use of social media platforms, such as Twitter and Facebook, massive amounts of text and image information posted by a variety of users have flooded these social media platforms. Thus, multimodal named entity recognition (MNER) has become a research hotspot for the task of extracting named entities from multimodal data. Empirically, the visual clues unrelated to text data may introduce uncertain or even negative impacts on the named entity recognition. The considerations of the relevance of multimodal data have been ignored in the previous studies. In this article, to effectively measure the relationship between text data and visual cues for improving the accuracy of named entities, we propose a text-image scene graph fusion (TISGF) approach with a text-image similarity assessment module (TISA) and a text-image fusion module (TIF) for MNER. Specifically, we first construct two (visual and textual) scene graphs to exploit the joint features of objects and relations in text and image and encode the two scene graphs separately using a specific encoder pair. In this way, we can obtain both object-level and relationship-level cross-modal features. Subsequently, TISA is used to compute the similarity of the image and text data and to determine the proportion of visual information that will be retained for fusion. Finally, we use TIF to achieve a unified multimodal representation of each word and predict the entity type using conditional random fields. Extensive experiment results on two public datasets demonstrate the effectiveness and competitiveness of our proposed method for the MNER task. © 2020 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Novel Ontology-Based Semantic Retrieval Model for Food Safety Domain

引用

Chinese Journal of Electronics 2023年第2期22卷 247-252页

作者： Yuehua Yang Junping Du Bowei He Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia School of Computer Science Beijing University of Posts and Telecommunications Beijing China

Recently, serious food safety events have emerged frequently and food safety issues have caused wide public concern all over the world. To find the needed food safety information for users from the growing information over the Internet, this paper presents an ontology-based semantic retrieval model used in food safety domain information retrieval. Firstly, food safety domain ontology is constructed to represent food safety domain knowledge, which has many advantages, such as sharable, reusable, and scalable. So it is very appropriately to describe the semantic relationships between food safety domain concepts. Then the lexicon for words segmentation is expanded based on the food safety domain ontology to return more accurate preprocessing results of queries. Finally semantic query expansion and sorting algorithm of search results based on concepts similarity computation model are implemented so that more relevant results can come before irrelevant retrieval results. The experiments show that the precision of the retrieval method with the proposed model is higher 25.2% averagely than that of the traditional retrieval method.

关键词： Vocabulary Computational modeling Knowledge acquisition Semantics Ontologies Safety Internet

来源：评论

学校读者我要写书评

暂无评论

Adversarial Guided Gradient Estimation Hashing for Cross-modal Retrieval 8

Adversarial Guided Gradient Estimation Hashing for Cross-mod...

引用

8th IEEE International Conference on Cloud Computing and Intelligence Systems, CCIS 2022

作者： Lu, Kangkang Liang, Meiyu Xue, Zhe Cao, Xiaowen Yin, Mengran Zhao, Zehua Beijing University of Posts and Telecommunications Beijing Key Laboratory of Intelligent Communication Software and Multimedia School of Computer Science National Pilot Software Engineering School Beijing100876 China

ISBN: (纸本)9781665477352

Due to low storage cost and fast query speed, deep hashing methods are widely used in cross-modal retrieval. However, the 'heterogeneous gap' between multi-modal data is still a challenge. Moreover, a major difficulty in deep hashing lies in the discrete constraints imposed on the network output. Existing solutions usually use relaxation techniques, but this inevitably produces quantization error, leading to sub-optimal hash code. In this paper, we propose Adversarial Guided Gradient Estimation Hashing (AGEH). Firstly, in order to bridge the heterogeneous gap between different modal data, a cross-modal adversarial feature learning network is constructed to learn cross-modal semantic associations. Secondly, to solve the discrete optimization problem of hash code, we propose a hashing optimization strategy based on gradient estimation for sign function, which strictly uses sign function to maintain discrete constraints in forward propagation, while in back propagation, the gradient is directly transmitted to the previous layer and thus avoid quantization error. Extensive experiments conducted on two cross-modal benchmark datasets show that our proposed AGEH outperforms several state-of-the-art methods. © 2022 IEEE.

关键词： Backpropagation

来源：评论

学校读者我要写书评

暂无评论

Research on the Robust Image Representation Scheme for Natural Scene Categorization

引用

Chinese Journal of Electronics 2023年第2期22卷 341-346页

作者： Jie Liu Junping Du Xiaoru Wang Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia School of Computer Science Beijing University of Posts and Telecommunications Beijing China

Natural scene categorization is a challenging pattern classification problem and the image representation has deep impact on the classification performance. To improve the robustness and effectiveness of the image representation, a novel integrated scheme is proposed. Firstly, a feature combination method is adopted to generate a compound feature which contains the local texture and the spatial structure information for each image. Then an optimized dimensionality reduction algorithm is applied on the compound features to get lower dimensional and compressed feature representations. In the following, the dimensionality reduced features are clustered by a $k$ -means based adaptive clustering algorithm to form a proper visual codebook, and each image is represented by the codebook histogram. Finally, the support vector machine is exploited to do the scene categorization tasks using the robust image representations. The proposed scheme is sufficiently evaluated on three well-known scene datasets. The experimental results show that our proposed method effectively enhances the image representation and outperforms the state-of-the-art approaches.

关键词： Dimensionality reduction Support vector machines Visualization Histograms Scene classification Clustering algorithms Image representation

来源：评论

学校读者我要写书评

暂无评论

Cross-modal Search Method of technology Video based on Adversarial Learning and Feature Fusion 8

Cross-modal Search Method of Technology Video based on Adver...

引用

8th IEEE International Conference on Cloud Computing and Intelligence Systems, CCIS 2022

作者： Liu, Xiangbin Du, Junping Liang, Meiyu Li, Ang Beijing University of Posts and Telecommunications Beijing Key Laboratory of Intelligent Communication Software and Multimedia School of Computer Science National Pilot Software Engineering School Beijing100876 China

ISBN: (纸本)9781665477352

technology videos contain rich multi-modal information. In cross-modal information search, the data features of different modalities cannot be compared directly, so the semantic gap between different modalities is a key problem that needs to be solved. To address the above problems, this paper proposes a novel Feature Fusion based Adversarial Cross-modal Retrieval method (FFACR) to achieve text-to-video matching, ranking and searching. The proposed method uses the framework of adversarial learning to construct a video multimodal feature fusion network and a feature mapping network as generator, a modality discrimination network as discriminator. Generator and discriminator are trained alternately based on adversarial learning, so that the data obtained by the feature mapping network is semantically consistent with the original data and the modal features are eliminated. Experimental results demonstrate that the proposed method performs better in text-to-video search on the self-built datasets of technology videos. © 2022 IEEE.

关键词： Semantics

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：