检索结果-内蒙古大学图书馆

2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017

作者： Li, Bofang Liu, Tao Zhao, Zhe Tang, Buzhou Drozd, Aleksandr Rogers, Anna Du, Xiaoyong School of Information Renmin University of China China Key Laboratory of Data Engineering and Knowledge Engineering MOE China Shenzhen Graduate School Harbin Institute of Technology China Global Scientific Information and Computing Center Tokyo Institute of Technology China Department of Computer Science University of Massachusetts Lowell United States

ISBN: (纸本)9781945626838

The number of word embedding models is growing every year. Most of them are based on the co-occurrence information of words and their contexts. However, it is still an open question what is the best definition of context. We provide a systematical investigation of 4 different syntactic context types and context representations for learning word embeddings. Comprehensive experiments are conducted to evaluate their effectiveness on 6 extrinsic and intrinsic tasks. We hope that this paper, along with the published code, would be helpful for choosing the best context type and representation for a given task. © 2017 Association for Computational Linguistics.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Personalized Clustering via Targeted Representation Learning

arXiv

引用

arXiv 2024年

作者： Geng, Xiwen Zhao, Suyun Yu, Yixin Peng, Borui Du, Pan Chen, Hong Li, Cuiping Wang, Mengdie Key Lab of Data Engineering and Knowledge Engineering MOE Renmin University of China China School of Information Renmin University of China China School of Statistics Remin University of China China

Clustering traditionally aims to reveal a natural grouping structure within unlabeled data. However, this structure may not always align with users’ preferences. In this paper, we propose a personalized clustering method that explicitly performs targeted representation learning by interacting with users via modicum task information (e.g., must-link or cannot-link pairs) to guide the clustering direction. We query users with the most informative pairs, i.e., those pairs most hard to cluster and those most easy to miscluster, to facilitate the representation learning in terms of the clustering preference. Moreover, by exploiting attention mechanism, the targeted representation is learned and augmented. By leveraging the targeted representation and constrained contrastive loss as well, personalized clustering is obtained. Theoretically, we verify that the risk of personalized clustering is tightly bounded, guaranteeing that active queries to users do mitigate the clustering risk. Experimentally, extensive results show that our method performs well across different clustering tasks and datasets, even when only a limited number of queries are available. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Web Technologies Research and Development - APWeb 2005 1

引用

丛书名： Lecture Notes in Computer Science

1000年

作者： Yanchun Zhang Katsumi Tanaka Jeffrey Xu Yu Shan Wang Minglu Li

ISBN: (数字)9783540318491

ISBN: (纸本)9783540252078

This volume contains papers selected for presentation at the 7th Asia Pacific Conference on Web Technology (APWeb 2005), which was held in Shanghai, china during March 29–April 1, 2005. APWeb is an international conference series on WWW technologies and is the primary forum for researchers and practitioners from both academia and industry to exchange knowledge on WWW-related technologies and new advanced applications. APWeb 2005 received 420 submissions from 21 countries and regions worldwide, including china, Korea, Australia, Japan, Taiwan, France, UK, Canada, USA, India, Hong Kong, Brazil, Germany, Thailand, Singapore, Turkey, Spain, Greece, Belgium, New Zealand, and UAE. After a thorough review process for each submission by the Program Committee members and expert reviewers recommended by PC members, APWeb 2005 accepted 71 regular research papers (acceptance ratio 16.9%) and 22 short papers (acceptance ratio 5.2%). This volume also includes 6 keynote papers and 11 invited demo papers. The keynote lectures were given by six leading experts: Prof. Ah Chung Tsoi (Australia Research Council), Prof. Zhiyong Liu (National Nature Science Foundation of china), Prof. John Mylopoulos (university of Toronto), Prof. Ramamohanarao (Rao) Kotagiri (university of Melbourne), Prof. Calton Pu (Georgia Tech), and Prof. Zhiwei Xu (Chinese Academy of Sciences).

关键词： Information Storage and Retrieval Information Systems Applications (incl. Internet) Multimedia Information Systems User Interfaces and Human Computer Interaction Computer Communication Networks Computers and Society

来源：评论

学校读者我要写书评

暂无评论

Deep Text Classification Can be Fooled

arXiv

引用

arXiv 2017年

作者： Liang, Bin Li, Hongcheng Su, Miaoqiang Bian, Pan Li, Xirong Shi, Wenchang School of Information Renmin University of China Beijing China Key laboratory of Data Engineering and Knowledge Engineering MOE Beijing China

In this paper, we present an effective method to craft text adversarial samples, revealing one important yet underestimated fact that DNN-based text classifiers are also prone to adversarial sample attack. Specifically, confronted with different adversarial scenarios, the text items that are important for classification are identified by computing the cost gradients of the input (white-box attack) or generating a series of occluded test samples (black-box attack). Based on these items, we design three perturbation strategies, namely insertion, modification, and removal, to generate adversarial samples. The experiment results show that the adversarial samples generated by our method can successfully fool both state-of-the-art character-level and word-level DNN-based text classifiers. The adversarial samples can be perturbed to any desirable classes without compromising their utilities. At the same time, the introduced perturbation is difficult to be perceived. Copyright © 2017, The Authors. 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

What matters for ad-hoc video search? A large-scale evaluation on TRECVID

arXiv

引用

arXiv 2021年

作者： Chen, Aozhu Hu, Fan Wang, Zihan Zhou, Fangming Li, Xirong AIMC Lab. School of Information Renmin University of China Key Lab of Data Engineering and Knowledge Engineering Renmin University of China

For quantifying progress in Ad-hoc Video Search (AVS), the annual TRECVID AVS task is an important international evaluation. Solutions submitted by the task participants vary in terms of their choices of cross-modal matching models, visual features and training data. As such, what one may conclude from the evaluation is at a high level that is insufficient to reveal the influence of the individual components. In order to bridge the gap between the current solution-level comparison and the desired component-wise comparison, we propose in this paper a large-scale and systematic evaluation on TRECVID. By selected combinations of state-of-the-art matching models, visual features and (pre-)training data, we construct a set of 25 different solutions and evaluate them on the TRECVID AVS tasks 2016–2020. The presented evaluation helps answer the key question of what matters for AVS. The resultant observations and learned lessons are also instructive for developing novel AVS solutions. Copyright © 2021, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reverse Nearest Neighbor Heat Maps: A Tool for Influence Exploration

Reverse Nearest Neighbor Heat Maps: A Tool for Influence Exp...

引用

IEEE International Conference on data engineering

作者： Yu Sun Rui Zhang Andy Yuan Xue Jianzhong Qi Xiaoyong Du Department of Computing and Information Systems University of Melbourne Renmin University of China and Key Laboratory of Data Engineering and Knowledge Engineering MOE

ISBN: (纸本)9781509020218

We study the problem of constructing a reverse nearest neighbor (RNN) heat map by finding the RNN set of every point in a two-dimensional space. Based on the RNN set of a point, we obtain a quantitative influence (i.e., heat) for the point. The heat map provides a global view on the influence distribution in the space, and hence supports exploratory analyses in many applications such as marketing and resource management. To construct such a heat map, we first reduce it to a problem called Region Coloring (RC), which divides the space into disjoint regions within which all the points have the same RNN set. We then propose a novel algorithm named CREST that efficiently solves the RC problem by labeling each region with the heat value of its containing points. In CREST, we propose innovative techniques to avoid processing expensive RNN queries and greatly reduce the number of region labeling operations. We perform detailed analyses on the complexity of CREST and lower bounds of the RC problem, and prove that CREST is asymptotically optimal in the worst case. Extensive experiments with both real and synthetic data sets demonstrate that CREST outperforms alternative algorithms by several orders of magnitude.

关键词： Heating Radio frequency Indexes

来源：评论

学校读者我要写书评

暂无评论

Generalized domain prompt learning for accessible scientific vision-language models

引用

Nexus 2025年第2期2卷

作者： Qinglong Cao Yuntian Chen Lu Lu Hao Sun Zhengzhong Zeng Xiaokang Yang Dongxiao Zhang MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai 200240 China Ningbo Institute of Digital Twin Eastern Institute of Technology Ningbo 315200 China Department of Statistics and Data Science Yale University New Haven CT 06511 USA Gaoling School of Artificial Intelligence Renmin University of China Beijing 100872 China School of Environmental Science and Engineering Southern University of Science and Technology Shenzhen 518055 China Institute for Advanced Study Lingnan University Tuen Mun Hong Kong 100872 China

Large-scale vision-language models have shown remarkable success in general vision tasks, inspiring the development of domain-specific models. However, creating these models requires substantial investments in annotated data, computational resources, and energy, making such endeavors largely accessible to industrial giants. This resource-intensive nature of model development inadvertently stifles academic research, particularly for smaller research groups, and limits the diversity and growth of the field. To address these challenges and promote more sustainable and equitable research, we introduce the generalized domain prompt learning framework. This framework enables the efficient transfer of robust recognition capabilities from natural vision to specialized domains without the need for large datasets or heavy computational overhead. By leveraging small-scale domain-specific foundation models and minimal prompt samples, the framework enriches the language component with domain-specific knowledge through quaternion networks, revealing cross-modal relationships between specialized vision features and natural vision-based contextual embeddings. Simultaneously, it drives the vision component toward domain-specific tasks via hierarchical propagation of vision prompts, grounded in well-matched vision-language relationships. To maximize the domain adaptation potential of these models, we also propose a novel low-rank adaptation technique. Extensive experiments across diverse domains—including remote sensing, medical imaging, geology, synthetic aperture radar, and fluid dynamics—demonstrate the effectiveness of the framework, achieving state-of-the-art domain recognition performance within a prompt learning structure. Our work presents a pathway for inclusive and sustainable research that bridges the gap between academia and industry, empowering smaller research groups and promoting broader access to cutting-edge advancements in the context of future sustainable developme

关键词： vision-language models domain adaptation generalized domain prompt learning sustainable AI research AI for science

来源：评论

学校读者我要写书评

暂无评论

Malicious Web Pages Detection Based on Abnormal Visibility Recognition

Malicious Web Pages Detection Based on Abnormal Visibility R...

引用

International Conference on E-Business and Information System Security, EBISS

作者： Bin Liang Jianjun Huang Fang Liu Dawei Wang Daxiang Dong Zhaohui Liang Key Laboratory of Data Engineering and Knowledge Engineering MOE Renmin University of China Beijing China School of Information Renmin University of China Beijing China Renmin University of China Beijing CN

In recent years, Web sites have already become the attackers' main target. When attackers embed malicious code in the Web pages, they generally change the display mode of the corresponding HTML tags to make the display effect of malicious code invisible or almost invisible to the browser users. In this paper, the concept of abnormal visibility is proposed to describe the display feature setting of malicious code embedded. According to the concept, a malicious code detection method based on abnormal visibility recognition is designed and a prototype system is implemented. Compared to traditional methods and systems, the method has higher efficiency and less maintenance cost. Besides, a special-purpose JavaScript interpreter is implemented to get the execution output of browser-end scripts that are often used to generate malicious code dynamically by attackers. Experiments show that this system can detect most of the malicious Web pages efficiently and at the same time locate the malicious code in the source code accurately.

关键词： Web pages Displays Java Prototypes HTML Costs Invasive software Fingerprint recognition laboratories data engineering

来源：评论

学校读者我要写书评

暂无评论

The tradeoff of delta table merging and re-writing algorithms in what-if analysis application

The tradeoff of delta table merging and re-writing algorithm...

引用

Joint International Conference on Advances in data and Web Management, APWeb/WAIM 2009

作者： Zhang, Yansong Zhang, Yu Xiao, Yanqin Wang, Shan Chen, Hong Key Laboratory of the Ministry of Education for Data Engineering and Knowledge Engineering Renmin University of China Beijing 100872 China School of Information Renmin University of China Beijing 100872 China Department of Computer Science Harbin Finance College Harbin 150030 China Computer Center Hebei University Baoding Hebei 071002 China

ISBN: (纸本)9783642006715

What-if analysis can provide more meaningful information than classical OLAP. Multi-scenario hypothesis based on historical data needs efficient what-if data view support. In general, delta table for what-if analysis is more general than other solutions such as query re-writing prototype of Sesame. Delta table is independent of base table and is more suitable to represent complex hypothetical updates and multi-version hypothetical updates. Due to low efficiency of traditional delta table merging algorithm which is based on set operation, there are few researches focus on delta table merging algorithm but on query re-writing algorithm. By analyzing the difference between what-if query and what-if analysis and improving the delta table merging algorithm, we propose novel algorithms without set operation of difference. Considering the feature of aggregate operations in OLAP analysis, pre-merge algorithm is presented without the generation of what if data view before group-bys in the scenario of SUM, AVERAGE and COUNT function OLAP queries. In our experiments, the pre-merge algorithm greatly improved the efficiency of delta table merging procedure which is close to base group-by statement and superior to the re-writing algorithm. A complete comparison between all candidate delta table merging algorithms and re-writing algorithm with different what-if update conditions of update, deletion, insertion and mixed what-if updates is exhibited in our experiments, the policy of what-if analysis among different types is also discussed. © Springer-Verlag Berlin Heidelberg 2009.

关键词： Merging

来源：评论

学校读者我要写书评

暂无评论

Measuring Semantic Associaiton in Domain Ontology

Measuring Semantic Associaiton in Domain Ontology

引用

International Conference on Semantics, knowledge and Grid (SKG)

作者： Xuan Tian Haihua Li Xiaoyong Du School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering MOESchool of Information Renmin University of China Beijing China

In domain ontology, semantic association (SA) is used to depict the correlation between two concepts. In this paper, we define semantic association degree (SAD) for measuring SA in the domain ontology. We first present a method to measure SAD of two direct related concepts by evaluating the semantic relationship between them, and then give another method to measure SAD of two indirect related concepts though SAD of two directed neighboring concepts. A set of comparison experiments show the benefit of our approaches.

关键词： Ontologies Psychology data mining Diseases Information retrieval laboratories data engineering knowledge engineering Text categorization History

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：