检索结果-内蒙古大学图书馆

11th ACM SIGIR International Conference on Theory of Information Retrieval, ICTIR 2021

作者： Cai, Yinqiong Fan, Yixing Guo, Jiafeng Zhang, Ruqing Lan, Yanyan Cheng, Xueqi University of Chinese Academy of Sciences Beijing China Cas Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China Institute for Ai Industry Research Tsinghua University Beijing China

ISBN: (纸本)9781450386111

Similar question retrieval is a core task in community-based question answering (CQA) services. To balance the effectiveness and efficiency, the question retrieval system is typically implemented as multi-stage rankers: The first-stage ranker aims to recall potentially relevant questions from a large repository, and the latter stages attempt to re-rank the retrieved results. Most existing works on question retrieval mainly focused on the re-ranking stages, leaving the first-stage ranker to some traditional term-based methods. However, term-based methods often suffer from the vocabulary mismatch problem, especially on short texts, which may block the re-rankers from relevant questions at the very beginning. An alternative is to employ embedding-based methods for the first-stage ranker, which compress texts into dense vectors to enhance the semantic matching. However, these methods often lose the discriminative power as term-based methods, thus introduce noise during retrieval and hurt the recall performance. In this work, we aim to tackle the dilemma of the first-stage ranker, and propose a discriminative semantic ranker, namely DenseTrans, for high-recall retrieval. Specifically, DenseTrans is a densely connected Transformer, which learns semantic embeddings for texts based on Transformer layers. Meanwhile, DenseTrans promotes low-level features through dense connections to keep the discriminative power of the learned representations. DenseTrans is inspired by DenseNet in computer vision (CV), but poses a new way to use the dense connectivity which is totally different from its original design purpose. Experimental results over two question retrieval benchmark datasets show that our model can obtain significant gain on recall against strong term-based methods as well as state-of-the-art embedding-based methods. © 2021 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

HGTA: News Recommendation Based on Hierarchical Granular Semantic Embeddings and Threshold Attention

HGTA: News Recommendation Based on Hierarchical Granular Sem...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Yiwen Li Zhenyu Yang Zhijun Li Xiaoyang Li Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Personalized news recommendation helps users find interesting content among much news information. Most existing news recommendation techniques densely interact a user’s historical clicked news with candidate news to capture their reading interest. However, during this process, even if certain historical clicked news is weakly correlated with the candidate news, the model still interacts with it, generating more noise information when constructing user interests. Simultaneously, the news representation learning process using neural networks is a fine-grained to coarse-grained learning process; i.e., as the network deepens, the fine-grained original news information is easily lost. Therefore, to solve the above problems, this paper proposes a news recommendation model based on hierarchical granular semantic embeddings and threshold attention (HGTA). In HGTA, we propose a threshold attention module to filter unimportant historical clicked news by setting an attention score threshold, i.e., interacting only with historical clicked news that is strongly correlated with the candidate news when capturing user interests. Thus, the model attention is focused, and the noisy interaction information is reduced. Furthermore, when training the neural network, to prevent the loss of fine-grained information, we design a hierarchical granular information extraction module to capture both coarse- and fine-grained news features to better enrich the news semantics. Experiments conducted on the large real-world Microsoft News dataset (MIND) show that our model achieves highly competitive results in terms of popular metrics. Our code is published at the following URL: https://***/liyiweneven/HGTA.

关键词： Uniform resource locators Training Representation learning Federated learning Semantics Neural networks Noise

来源：评论

学校读者我要写书评

暂无评论

LESaET: Low-Dimensional Embedding Method for Link Prediction Combining Self-Attention and Enhanced-TuckER

LESaET: Low-Dimensional Embedding Method for Link Prediction...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Lichao Ding Jing Zhao Kai Lu Zenghao Hao Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Knowledge graphs (KGs) provide a structured representation of the real world through entity-relation triples. However, current KGs are often incomplete, typically containing only a small fraction of all possible facts. This involves inferring missing content from existing information, a task known as link prediction. Existing methods in the field of link prediction struggle with controlling the dimensionality of embedding vectors or suffer from overly complex models. In order to tackle these challenges, we introduce a method in this paper, named Low-Dimensional Embedding Method for Link Prediction Combining Self-Attention and Enhanced-TuckER (LESaET). LESaET leverages both self-attention mechanisms and tensor factorization to learn expressive contextual-enhanced representations of KGs. Specifically, LESaET employs the multi-head self-attention mechanism of Transformer as an encoder to capture the mutual information between entities and relationships, and utilizes Enhanced-TuckER as a decoder, ultimately achieving expressive low-dimensional embeddings for link prediction tasks. LESaET demonstrates competitive performance compared to advanced methods on standard datasets.

关键词： Tensors Stacking Knowledge graphs Predictive models Transformers Vectors Decoding Standards Mutual information Periodic structures

来源：评论

学校读者我要写书评

暂无评论

TSFE: Research on Transformer and Feature Enhancement Methods for Image-Text Retrieval

TSFE: Research on Transformer and Feature Enhancement Method...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Jinxiao Yang Xingang Wang Qingao Wang Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

In recent years, cross-modal retrieval has a wide range of applications in fields such as information retrieval and multimedia processing, where the key is to find relevant data in another modality through one modal query. In cross-modal graphic retrieval, mutual attention mechanisms are commonly used to interact image and text features. However, this interaction mechanism makes it difficult to extract separate visual and textual features for subsequent indexing steps, especially in large-scale retrieval tasks. Furthermore, in image representation, non-semantic information in image features can lead to inaccuracies in the alignment of image and text features. Therefore this paper proposes a Transformer and Feature Enhancement Method (TSFE) for Image-Text Retrieval. The method better fuses the underlying features and the higher level features by using a hierarchical Transformer coding structure on two separate branches, image and text, to proofread and localise the final output features. The Feature Enhanced Attention (FEA) module is designed in order to infer non-semantic information in the image and enhance the features of salient regions. Channel-space attention and max pooling is introduced on top of Transformer encoder self-attention to filter redundant and interfering information from channel and spatial dimensions. Experiments on Flickr30k dataset and MS-COCO dataset in this paper show improved performance in cross-modal retrieval, thus validating the effectiveness and sophistication of the proposed method.

关键词： Visualization Semantics Pipelines Noise Image representation Transformers Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Opinion-Tree-guided Contrastive Learning for Aspect Sentiment Quadruple Prediction

Opinion-Tree-guided Contrastive Learning for Aspect Sentimen...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Zhijun Li Zhenyu Yang Yiwen Li Xiaoyang Li Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

In recent years, aspect sentiment quadruple prediction (ASQP) has become a popular task in the field of aspect-based sentiment analysis. When modeling comment statements, it is often necessary to consider structural information between sentiment labels. Existing approaches categorize these labels by encoding text and dependency tree structures separately and then incorporating their representations, but this approach fails to effectively capture the structural information between sentiment labels. To address this problem, we propose a method for ASQP called Opinion-Tree-guided Contrastive Learning (OTCL), which embeds structural information directly into the text instead of modeling it separately. Specifically, OTCL utilizes the opinion tree structure to guide the construction of positive samples of the input text during training. By associating the input text with its positive samples, the text encoder can learn to generate textual representations associated with the opinion tree structure. We validate the effectiveness of our method on two commonly used datasets.

关键词： Training Sentiment analysis Federated learning Contrastive learning Predictive models Encoding Task analysis

来源：评论

学校读者我要写书评

暂无评论

JTEA: Implementing Semi-Supervised Entity Alignment Using Joint Teaching Strategies

JTEA: Implementing Semi-Supervised Entity Alignment Using Jo...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Kai Lu Jing Zhao Lichao Ding Zenghao Hao Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Faculty of Computer Science and Technology Shandong Engineering Research Center of Big Data Applied Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Entity alignment(EA) aims to identify equivalent entities in different knowledge graphs or data sources and establish correspondences between them. In recent years, embedding-based methods have made significant progress in the field of entity alignment, yet the shortage of adequate training data (i.e., seed entity pairs) continues to be a primary challenge. Traditional semi-supervised methods typically address this issue by generating potential mappings (i.e., pseudo-mappings) for unlabeled entities. However, these methods often suffer from the influence of erroneous potential mappings or overlook the uncertainty of potential mappings. Therefore, we propose a novel semi-supervised entity alignment method called JTEA. This method combines seed entity pairs with potential mappings through end-to-end joint training, providing strong guidance for model training. In constructing potential mappings, we propose a bidirectional matching strategy (BMS), which generates more detailed potential mappings by jointly adjusting decisions in different directions and uses a joint matching confidence score to characterize its uncertainty. Furthermore, we also introduce a method of matching diversity alignment selection, aiming to screen out more reliable entity alignments to further improve the performance and stability of the model. We conducted a large number of experiments on the benchmark dataset to fully validate the effectiveness of the JTEA method.

关键词： Training Uncertainty Soft sensors Noise Training data Knowledge graphs data models Stability analysis Reliability Thermal stability

来源：评论

学校读者我要写书评

暂无评论

The Security and Privacy of Mobile Edge Computing: An Artificial Intelligence Perspective

arXiv

引用

arXiv 2024年

作者： Wang, Cheng Yuan, Zenghui Zhou, Pan Xu, Zichuan Li, Ruixuan Wu, Dapeng Oliver Hubei Engineering Research Center on Big Data Security Key Laboratory of Distributed System Security of Hubei Province School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China School of Software The Key Laboratory for Ubiquitous Network Service Software of Liaoning Province Dalian University of Technology Dalian116024 China Intelligent and Distributed Computing Laboratory School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Department of Computer Science City University of Hong Kong Kowloon999077 Hong Kong

Mobile Edge Computing (MEC) is a new computing paradigm that enables cloud computing and information technology (IT) services to be delivered at the network’s edge. By shifting the load of cloud computing to individual local servers, MEC helps meet the requirements of ultralow latency, localized data processing, and extends the potential of Internet of Things (IoT) for end-users. However, the crosscutting nature of MEC and the multidisciplinary components necessary for its deployment have presented additional security and privacy concerns. Fortunately, Artificial Intelligence (AI) algorithms can cope with excessively unpredictable and complex data, which offers a distinct advantage in dealing with sophisticated and developing adversaries in the security industry. Hence, in this paper we comprehensively provide a survey of security and privacy in MEC from the perspective of AI. On the one hand, we use European Telecommunications Standards Institute (ETSI) MEC reference architecture as our based framework while merging the Software Defined network (SDN) and network Function Virtualization (NFV) to better illustrate a serviceable platform of MEC. On the other hand, we focus on new security and privacy issues, as well as potential solutions from the viewpoints of AI. Finally, we comprehensively discuss the opportunities and challenges associated with applying AI to MEC security and privacy as possible future research directions. Copyright © 2024, The Authors. All rights reserved.

关键词： network security

来源：评论

学校读者我要写书评

暂无评论

Evaluating natural language generation via unbalanced optimal transport 29

Evaluating natural language generation via unbalanced optima...

引用

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Chen, Yimeng Lan, Yanyan Xiong, Ruibin Pang, Liang Ma, Zhiming Cheng, Xueqi University of Chinese Academy of Sciences China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology CAS China Academy of Mathematics and Systems Science CAS China

ISBN: (纸本)9780999241165

Embedding-based evaluation measures have shown promising improvements on the correlation with human judgments in natural language generation. In these measures, various intrinsic metrics are used in the computation, including generalized precision, recall, F-score and the earth mover's distance. However, the relations between these metrics are unclear, making it difficult to determine which measure to use in real applications. In this paper, we provide an in-depth study on the relations between these metrics. Inspired by the optimal transportation theory, we prove that these metrics correspond to the optimal transport problem with different hard marginal constraints. However, these hard marginal constraints may cause the problem of incomplete and noisy matching in the evaluation process. Therefore we propose a family of new evaluation metrics, namely Lazy Earth Mover's Distances, based on the more general unbalanced optimal transport problem. Experimental results on WMT18 and WMT19 show that our proposed metrics have the ability to produce more consistent evaluation results with human judgements, as compared with existing intrinsic metrics. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Computation theory

来源：评论

学校读者我要写书评

暂无评论

A Dual-Channel Framework for Sarcasm Recognition by Detecting Sentiment Conflict

A Dual-Channel Framework for Sarcasm Recognition by Detectin...

引用

2022 Findings of the Association for Computational Linguistics: NAACL 2022

作者： Liu, Yiyi Wang, Yequan Sun, Aixin Meng, Xuying Li, Jing Guo, Jiafeng CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Beijing Academy of Artificial Intelligence Beijing China School of Computer Science and Engineering Nanyang Technological University Singapore Singapore Institute of Computing Technology Chinese Academy of Sciences Beijing China Inception Institute of Artificial Intelligence Abu Dhabi United Arab Emirates

ISBN: (纸本)9781955917766

Sarcasm employs ambivalence, where one says something positive but actually means negative, and vice versa. The essence of sarcasm, which is also a sufficient and necessary condition, is the conflict between literal and implied sentiments expressed in one sentence. However, it is difficult to recognize such sentiment conflict because the sentiments are mixed or even implicit. As a result, the recognition of sophisticated and obscure sentiment brings in a great challenge to sarcasm detection. In this paper, we propose a Dual-Channel Framework by modeling both literal and implied sentiments separately. Based on this dual-channel framework, we design the Dual-Channel network (DC-Net) to recognize sentiment conflict. Experiments on political debates (i.e., IAC-V1 and IAC-V2) and Twitter datasets show that our proposed DC-Net achieves state-of-the-art performance on sarcasm recognition. Our code is released to support research. © Findings of the Association for Computational Linguistics: NAACL 2022 - Findings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Effect of the Mixing Structure Parameters of a Self-reflux Burner on Combustion Characteristics and NO_(x)Emission

引用

Journal of Thermal science 2021年第4期30卷 1224-1236页

作者： XU Qian SHEN Meng SHI Kejian LIU Zhihui AKKURT Nevzat XIONG Yaxuan LIU Lin FENG Junxiao WANG Jiulong School of energy and environmental engineering Shunde Graduate SchoolUniversity of Science and Technology BeijingBeijing 100083China Beijing Key Laboratory of Energy Conservation and Emission Reduction for Metallurgical Industry Beijing 100083China Department of Mechanical Engineering Munzur UniversityTunceli 62000Turkey Key Laboratory of HVAC Beijing University of Civil Engineering and ArchitectureBeijing 100044China School of Mathematics and Physics University of Science and Technology BeijingBeijing 100083China Department of Big Data Technology and Application Development Computer Network Information CenterChinese Academy of SciencesBeijing 100190China

To solve the problem of low efficiency of NO_(x)emission reduction in self-reflux burners,this study is based on the concept of coordinated control of self-reflux burner structural and thermal *** completing the structural design and optimization of thermal parameters,we continue to adjust the two key structural parameters:the nozzle axis distance and the length of the cylindrical section,to minimize NO_(x)*** are the two parameters that chiefly affect the mixing of flue gas and fuel *** results show that increasing nozzle axis distance can delay the mixing of gas and air and create a more uniform oxygen concentration field for the combustion *** maximum combustion temperature is reduced from 1973.65 K to 1935.88 K and the volume fraction of NO_(x)in the flue gas is reduced from 188.08×10^(–6)to 143.47×10^(–6).However,compared with the nozzle axis distance,the length of the cylindrical section of the burner has little effect on the mixing of the flow *** different cylindrical section lengths,the maximum combustion temperature does not change more than 3 K,and the volume fraction of NO_(x)in the flue gas changes within 5×10~(–6).

关键词： self-reflux structure structural parameter control thermal parameter combustion characteristic NO_(x)emission

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：