检索结果-内蒙古大学图书馆

3rd International Conference on Natural Language Processing, ICNLP 2021

作者： Wang, Yuhui Zhou, Feng Li, Xiaoyong Beijing University of Posts and Telecommunications Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia School of Computer Science Beijing China Beijing University of Posts and Telecommunications School of Cyberspace Security Beijing China

ISBN: (纸本)9781665414111

Enormous volume of data on social media platforms such as Weibo and Twitter is being generated every day. Microblogs collected from Weibo on a certain topic may consist of numerous conversation threads about relevant subtopics. However, it is difficult to distinguish these subtopics if the data is visualized as a single WordCloud because there's no contextual information around the words in WordCloud. To help identify subtopics under a broader topic, we introduce VoronoiTopicCloud, a novel technique for visualizing the opinions in a large social media text collection. In order to overcome the problem of semantic sparseness and improve the performance of text clustering, we propose a novel corpus-based enrichment approach for short text. In the expansion procedure, new words which may not appear in the original short text document are added to the document with a virtual weight and the virtual weight is obtained from the posterior probabilities of new words given all the words in that document. At last, VoronoiTopicCloud is implemented as a lightweight application that runs in the browser. © 2021 IEEE.

关键词： Semantics

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

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

引用

IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS)

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

ISBN: (纸本)9781665456579

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.

关键词： Cloud computing Semantics Search problems Adversarial machine learning Generators intelligent systems Videos

来源：评论

学校读者我要写书评

暂无评论

Efficient Partitioning Method of Large-Scale Public Safety Spatio-Temporal Data based on Information Loss Constraints

arXiv

引用

arXiv 2023年

作者： Gao, Jie Li, Yawen Xue, Zhe Guan, Zeli Beijing Key Laboratory of Intelligent Communication Software and Multimedia School of Computer Science National Pilot Software Engineering School Beijing University of Posts and Telecommunications Beijing100876 China School of Economics and Management Beijing University of Posts and Telecommunications Beijing100876 China

The storage, management, and application of massive spatio-temporal data are widely applied in various practical scenarios, including public safety. However, due to the unique spatio-temporal distribution characteristics of real-world data, most existing methods have limitations in terms of the spatio-temporal proximity of data and load balancing in distributed storage. Therefore, this paper proposes an efficient partitioning method of large-scale public safety spatio-temporal data based on information loss constraints (IFL-LSTP). The IFL-LSTP model specifically targets large-scale spatio-temporal point data by combining the spatio-temporal partitioning module (STPM) with the graph partitioning module (GPM). This approach can significantly reduce the scale of data while maintaining the model’s accuracy, in order to improve the partitioning efficiency. It can also ensure the load balancing of distributed storage while maintaining spatio-temporal proximity of the data partitioning results. This method provides a new solution for distributed storage of massive spatio-temporal data. The experimental results on multiple real-world datasets demonstrate the effectiveness and superiority of IFL-LSTP. Copyright © 2023, The Authors. All rights reserved.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Entity Alignment Method of Science and technology Patent based on Graph Convolution Network and Information Fusion

arXiv

引用

arXiv 2023年

作者： Fang, Runze Li, Yawen Shao, Yingxia Guan, Zeli Xue, Zhe Beijing Key Laboratory of Intelligent Communication Software and Multimedia School of Computer Science National Pilot Software Engineering School Beijing University of Posts and Telecommunications Beijing100876 China School of Economics and Management Beijing University of Posts and Telecommunications Beijing100876 China

The entity alignment of science and technology patents aims to link the equivalent entities in the knowledge graph of different science and technology patent data sources. Most entity alignment methods only use graph neural network to obtain the embedding of graph structure or use attribute text description to obtain semantic representation, ignoring the process of multi-information fusion in science and technology patents. In order to make use of the graphic structure and auxiliary information such as the name, description and attribute of the patent entity, this paper proposes an entity alignment method based on the graph convolution network for science and technology patent information fusion. Through the graph convolution network and BERT model, the structure information and entity attribute information of the science and technology patent knowledge graph are embedded and represented to achieve multi-information fusion, thus improving the performance of entity alignment. Experiments on three benchmark data sets show that the proposed method Hit@K The evaluation indicators are better than the existing methods. © 2023, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Semantic Representation Learning of Scientific Literature based on Adaptive Feature and Graph Neural Network

arXiv

引用

arXiv 2023年

作者： Gao, Hongrui Li, Yawen Liang, Meiyu Guan, Zeli Xue, Zhe Beijing Key Laboratory of Intelligent Communication Software and Multimedia School of Computer Science National Pilot Software Engineering School Beijing University of Posts and Telecommunications Beijing100876 China School of Economics and Management Beijing University of Posts and Telecommunications Beijing100876 China

Because most of the scientific literature data is unmarked, it makes semantic representation learning based on unsupervised graph become crucial. At the same time, in order to enrich the features of scientific literature, a learning method of semantic representation of scientific literature based on adaptive features and graph neural network is proposed. By introducing the adaptive feature method, the features of scientific literature are considered globally and locally. The graph attention mechanism is used to sum the features of scientific literature with citation relationship, and give each scientific literature different feature weights, so as to better express the correlation between the features of different scientific literature. In addition, an unsupervised graph neural network semantic representation learning method is proposed. By comparing the mutual information between the positive and negative local semantic representation of scientific literature and the global graph semantic representation in the potential space, the graph neural network can capture the local and global information, thus improving the learning ability of the semantic representation of scientific literature. The experimental results show that the proposed learning method of semantic representation of scientific literature based on adaptive feature and graph neural network is competitive on the basis of scientific literature classification, and has achieved good results. © 2023, CC BY.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

BRCEA: Bootstrapping Relation-Aware Cross-Lingual Entity Alignment 10th

BRCEA: Bootstrapping Relation-Aware Cross-Lingual Entity Ali...

引用

10th CCF Conference on Natural Language Processing and Chinese Computing, NLPCC 2021

作者： Zhang, Yujing Zhou, Feng Li, Xiaoyong Y. Key Laboratory of Intelligent Telecommunications Software and Multimedia Beijing China School of Computer Science Beijing University of Posts and Telecommunications Beijing China School of Cyberspace Security Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9783030884796

Entity alignment aims to align entities referring to the same identity in the real world across different Knowledge Graphs (KGs), which is a fundamental task of KG construction and KG fusion. Recent works focus on embedding-based approaches. With the pre-aligned entity pairs, these approaches mainly embed entities based on relation triples to capture structural information and then try to refine the entity embeddings by self-characteristics contained in attribute triples. However, insufficient training data, diverse expressions of attributes, and different importance between self-characteristics and structural information in different KGs are three obstacles to entity embedding. In order to tackle these problems, we propose a novel Bootstrapping Relation-aware model for Cross-lingual Entity Alignment using both relation triples and attribute triples of KGs (BRCEA). Firstly, given the base prior alignments, it separately embeds entities from two aspects, namely self-characteristics and structural information. Then, bootstrapping component discovers two sets of new alignments. Finally, the two sets will be used to construct new training data for the next iteration to overcome the sparsity of training data. We performed our model on several real-world datasets, and the results show that our model outperforms the state-of-art models for cross-lingual entity alignment. © 2021, Springer Nature Switzerland AG.

关键词： Knowledge graph

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

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

引用

IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS)

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

ISBN: (纸本)9781665456579

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.

关键词： Representation learning Bridges Backpropagation Training Codes Quantization (signal) Semantics

来源：评论

学校读者我要写书评

暂无评论

Dynamic Radio Map Construction With Minimal Manual Intervention: A State Space Model-Based Approach With Imitation Learning

引用

IEEE Transactions on Big Data 2024年

作者： Zhu, Xiaoqiang Qiu, Tie Qu, Wenyu Zhou, Xiaobo Shi, Tuo Xu, Tianyi Beijing Jiaotong University School of Cyberspace Science and Technology Beijing100044 China Beijing Jiaotong University Beijing Key Laboratory of Security and Privacy in Intelligent Transportation Beijing100044 China Tianjin University School of Computer Science and Technology College of Intelligence and Computing Tianjin300350 China Tianjin Key Laboratory of Advanced Networking Tianjin300350 China

Fingerprint localization methods typically require a substantial amount of manual effort to collect fingerprint data from various scenarios to construct an accurate radio map. While some existing research has attempted to use path planning strategies to save on labor costs, these approaches often suffer from being time-consuming and prone to locally optimal solutions. To address these shortcomings, our paper proposes a novel approach that utilizes imitation learning to construct and update a highly accurate radio map with minimal manual intervention in dynamic environments. Specifically, we employ a multivariate Gaussian process model to fit a rough standby fingerprint database with only a few pilot data points. We then utilize a state space model to calculate the variation range of the pilot data, which forms the CSI error band used to filter the rough radio map. Imitation learning and a confidence coefficient are utilized to predict and calibrate the global CSI data distribution. And we utilize the K-nearest neighbor algorithm to achieve the real-time localization function. Experimental results show that our proposed algorithm outperforms several state-of-the-art approaches in most test cases, exhibiting low computation complexity, lower localization error, and saving 73.3% of the manual workload. © 2015 IEEE.

关键词： Wages

来源：评论

学校读者我要写书评

暂无评论

Robust Student Expression Recognition Model with Self-Adaptive Multi-View Attention Fusion Network

SSRN

引用

SSRN 2022年

作者： Wanying, Yu Meiyu, Liang Mengran, Yin Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia School of Computer Science Beijing China Beijing University of Posts and Telecommunications Beijing100876 China

In order to solve the problem of occlusion in student expression recognition under complex classroom scenes, and make full use of deep learning in the field of intelligent teaching evaluation, so as to realize the mapping of student expressions to intelligent teaching evaluation, this paper proposes a student expression recognition model based on adaptive fusion of multi-view deep attention features. In this paper, a teaching video library and a student expression library are constructed. Firstly, a branch convolutional neural network is used to learn the global features of the face region. Then, the face is divided into different local areas by the clipping strategy, and some areas of the face are blocked by the occlusion strategy to simulate the possible occlusion in the real scene, and the local features of the clipping area and the occlusion area are respectively learned based on the same branch convolutional neural network. We also propose a multi-branch convolutional network weighted fusion strategy based on self-attention mechanism and construct a multi-branch deep attention network for facial expression feature learning. In addition, we propose to impose a weight constraint loss function in the multi-branch convolutional network to adaptively adjust the weight distribution of each path, and by multiplying the feature of each branch by the sum of the attention weights divided by the sum of the attention weights of all the branches, the adaptive fusion of the global and local features of the face is realized, and the multi-view feature representation of the face area is obtained. Finally, the classification of students’ facial expressions in class is achieved based on the learned multi-view facial features, realizing the recognition of student facial expressions under occlusion. Extensive experiments on the benchmark FERplus dataset and self-built teaching video dataset demonstrate that the proposed model outperforms the state-of-the-art methods. © 2022, The A

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

keywords Extraction Algorithm of Financial Review Based on Dirichlet Multinomial Model

Keywords Extraction Algorithm of Financial Review Based on D...

引用

Chinese intelligent Systems Conference, CISC 2020

作者： Li, Jinxuan Li, Yawen Xue, Zhe Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia School of Computer Science Beijing University of Posts and Telecommunications Beijing100876 China School of Economics and Management Beijing University of Posts and Telecommunications Beijing100876 China

ISBN: (纸本)9789811584572

At present, the main method of keyword extraction is usually based on topical discovery model, and the most popular model is LDA (Latent Dirichlet Allocation) topical model. However, LDA model has poor performance in dealing with short texts, which is the imperfection of the current topical discovery model. This paper propose a keywords extraction model SDMM (Statistical Dirichlet Multinomial model) to extract the keywords of short financial review. This keywords extraction model use DMM (Dirichlet Multinomial Model) for topic discovery, and calculate the similarity between the words and keywords, thus improve the performance of keyword extraction for short texts. Experimental results on several financial review datasets show that the proposed model is better than the existing models in evaluation indicator Precision, Recall and F-measure. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Finance

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：