检索结果-内蒙古大学图书馆

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Chen, Zhijun Wang, Huimin Sun, Hailong Chen, Pengpeng Han, Tao Liu, Xudong Yang, Jie SKLSDE Lab School of Computer Science and Engineering Beihang University China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University China Web Information Systems Delft University of Technology Netherlands

ISBN: (纸本)9780999241165

End-to-end learning from crowds has recently been introduced as an EM-free approach to training deep neural networks directly from noisy crowdsourced annotations. It models the relationship between true labels and annotations with a specific type of neural layer, termed as the crowd layer, which can be trained using pure backpropagation. Parameters of the crowd layer, however, can hardly be interpreted as annotator reliability, as compared with the more principled probabilistic approach. The lack of probabilistic interpretation further prevents extensions of the approach to account for important factors of annotation processes, e.g., instance difficulty. This paper presents SpeeLFC, a structured probabilistic model that incorporates the constraints of probability axioms for parameters of the crowd layer, which allows to explicitly model annotator reliability while benefiting from the end-to-end training of neural networks. Moreover, we propose SpeeLFC-D, which further takes into account instance difficulty. Extensive validation on real-world datasets shows that our methods improve the state-of-the-art. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Semantic networks for engineering design: A survey: A preprint

arXiv

引用

arXiv 2020年

作者： Han, Ji Sarica, Serhad Shi, Feng Luo, Jianxi School of Engineering University of Liverpool United Kingdom Data-Driven Innovation Lab Singapore University of Technology and Design 487372 Singapore Amazon Web Services United Kingdom

There have been growing uses of semantic networks in the past decade, such as leveraging large-scale pre-trained graph knowledge databases for various natural language processing (NLP) tasks in engineering design research. Therefore, the paper provides a survey of the research that has employed semantic networks in the engineering design research community. The survey reveals that engineering design researchers have primarily relied on WordNet, ConceptNet, and other commonsense semantic network databases trained on non-engineering data sources to develop methods or tools for engineering design. Meanwhile, there are emerging efforts to mine large scale technical publication and patent databases to construct engineering-contextualized semantic network databases, e.g., B-Link and TechNet, to support NLP in engineering design. On this basis, we recommend future research directions for the construction and applications of engineering-related semantic networks in engineering design research and practice. © 2020, CC BY.

关键词： Knowledge management

来源：评论

学校读者我要写书评

暂无评论

Dowe really need fully unsupervised cross-lingual embeddings?

arXiv

引用

arXiv 2019年

作者： Vulić, Ivan Glavaš, Goran Reichart, Roi Korhonen, Anna Language Technology Lab University of Cambridge Data and Web Science Group University of Mannheim Faculty of Industrial Engineering and Management Technion IIT

Recent efforts in cross-lingual word embedding (CLWE) learning have predominantly focused on fully unsupervised approaches that project monolingual embeddings into a shared cross-lingual space without any cross-lingual signal. The lack of any supervision makes such approaches conceptually attractive. Yet, their only core difference from (weakly) supervised projection-based CLWE methods is in the way they obtain a seed dictionary used to initialize an iterative self-learning procedure. The fully unsupervised methods have arguably become more robust, and their primary use case is CLWE induction for pairs of resourcepoor and distant languages. In this paper, we question the ability of even the most robust unsupervised CLWE approaches to induce meaningful CLWEs in these more challenging settings. A series of bilingual lexicon induction (BLI) experiments with 15 diverse languages (210 language pairs) show that fully unsupervised CLWE methods still fail for a large number of language pairs (e.g., they yield zero BLI performance for 87/210 pairs). Even when they succeed, they never surpass the performance of weakly supervised methods (seeded with 500-1, 000 translation pairs) using the same self-learning procedure in any BLI setup, and the gaps are often substantial. These findings call for revisiting the main motivations behind fully unsupervised CLWE methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Zero-determinant Strategies for Three-player in Finitely Repeated Games

Zero-determinant Strategies for Three-player in Finitely Rep...

引用

第37届中国控制会议

作者： Jianzhang Chen Zhihai Rong College of Computer and Information Sciences Fujian Agriculture and Forestry University CompleX Lab Web Sciences CenterUniversity of Electronic Science and Technology of China Big Data Research Center University of Electronic Science and Technology of China School of Computer Science and Engineering University of Electronic Science and Technology of China

Zero-determinant strategies are a new class of probabilistic and conditional strategies, where a player can use a linear relationship between his own payoff and the opponents payoff to determine his opponents expected payoff or extort his opponents unilaterally. This paper will analysis a model of zero-determinant strategies for three players in the finitely repeated public goods game（with a discount factor δ satisfying 0 ＜ δ ＜ 1）. Via analyzing these strategies for three players in the game, including equalizer strategies, extortion strategies and generous strategies, it finds that a player also has an ability to pin the expected total payoff of all other players in a unilateral way as the two-player model by equalizer strategies and can set a ratio between his payoff and the total payoff of all other players by the extortion strategies, and the expected payoffs of three players can obtain the same payoff when they cooperate in the first round by using generous strategies. This provides potential clues to design efficient cooperation protocol in multi-agent systems.

关键词： Zero-determinant Strategies Finitely Repeated Games Direct reciprocity Discount factor

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to “Promotion and resignation in employee networks” [Physica A 444 (2016) 442–447]

引用

Physica A: Statistical Mechanics and its Applications 2020年 555卷

作者： Jia Yuan Qian-Ming Zhang Jian Gao Linyan Zhang Xue-Song Wan Xiao-Jun Yu Tao Zhou Chengdu Institute of Public Administration Chengdu 610110 People’s Republic of China School of Management and Economics University of Electronic Science and Technology of China Chengdu 611731 People’s Republic of China CompleX Lab Web Sciences Center School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu 611731 People’s Republic of China Center for Polymer Studies Department of Physics Boston University Boston 02215 United States Hire Big Data (Chengdu) LTD. Chengdu 611731 People’s Republic of China Beijing Strong Union Technology Co. Ltd. Beijing 100086 People’s Republic of China Big Data Research Center University of Electronic Science and Technology of China Chengdu 611731 People’s Republic of China

来源：评论

学校读者我要写书评

暂无评论

Extortion provides alternative routes to the evolution of cooperation in structured populations

引用

Physical Review E 2017年第5期95卷 052302-052302页

作者： Xiongrui Xu Zhihai Rong Zhi-Xi Wu Tao Zhou Chi Kong Tse CompleX Lab Web Sciences Center University of Electronic Science and Technology of China Chengdu 611731 China Big Data Research Center University of Electronic Science and Technology of China Chengdu 611731 China Department of Electronic and Information Engineering The Hong Kong Polytechnic University Hung Hom Kowloon Hong Kong Institute of Computational Physics and Complex Systems Lanzhou University Lanzhou Gansu 730000 People's Republic of China

In this paper, we study the evolution of cooperation in structured populations (individuals are located on either a regular lattice or a scale-free network) in the context of repeated games by involving three types of strategies, namely, unconditional cooperation, unconditional defection, and extortion. The strategy updating of the players is ruled by the replicator-like dynamics. We find that extortion strategies can act as catalysts to promote the emergence of cooperation in structured populations via different mechanisms. Specifically, on regular lattice, extortioners behave as both a shield, which can enwrap cooperators inside and keep them away from defectors, and a spear, which can defeat those surrounding defectors with the help of the neighboring cooperators. Particularly, the enhancement of cooperation displays a resonance-like behavior, suggesting the existence of optimal extortion strength mostly favoring the evolution of cooperation, which is in good agreement with the predictions from the generalized mean-field approximation theory. On scale-free network, the hubs, who are likely occupied by extortioners or defectors at the very beginning, are then prone to be conquered by cooperators on small-degree nodes as time elapses, thus establishing a bottom-up mechanism for the emergence and maintenance of cooperation.

关键词： Population dynamics Self-organized systems Social systems

来源：评论

学校读者我要写书评

暂无评论

Event-based clustering for reducing labeling costs of incident-related microposts 2

Event-based clustering for reducing labeling costs of incide...

引用

2nd International Workshop on Mining Urban data, MUD 2015 - co-located with 32nd International Conference on Machine Learning, ICML 2015

作者： Schulz, Axel Ristoski, Petar Fürnkranz, Johannes Janssen, Frederik DB Mobility Logistics AG Telecooperation Lab Technische Universität Darmstadt Germany Data and Web Science Group University of Mannheim Germany Knowledge Engineering Group Technische Universität Darmstadt Germany

Automatically identifying the event type of event-related information in the sheer amount of social media data makes machine learning inevitable. However, this is highly dependent on (1) the number of correctly labeled instances and (2) labeling costs. Active learning has been proposed to reduce the number of instances to label. Though, current approaches focus on the thematic dimension, i.e., the event type, for selecting instances to label;other metadata such as spatial and temporal information that is helpful for achieving a more fine-grained clustering is currently not taken into account. Also, labeling quality is always assumed to be perfect as currently no qualitative information is present for manual event type labeling. In this paper, we present a novel event-based clustering strategy that makes use of temporal, spatial, and thematic metadata to determine instances to label. Furthermore, we also inspect the quality of the manual labeling in a crowdsourcing study by comparing experts and non-experts. An evaluation on incident-related tweets shows that (i) labels provided by crowdsourcing are of acceptable quality and (ii) our selection strategy for active learning outperforms current state-of-theart approaches even with few labeled instances. Copyright © 2015 for this paper by its authors.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

Event-based clustering for reducing labeling costs of event-related microposts 9

Event-based clustering for reducing labeling costs of event-...

引用

9th International Conference on web and Social Media, ICWSM 2015

作者： Schulz, Axel Janssen, Frederik Ristoski, Petar Fürnkranz, Johannes DB Mobility Logistics AG Germany Telecooperation Lab Technische Universität Darmstadt Germany Data and Web Science Group University of Mannheim Germany Knowledge Engineering Group Technische Universität Darmstadt Germany

ISBN: (纸本)9781577357339

Automatically identifying the event type of event-related information in the sheer amount of social media data makes machine learning inevitable. However, this is highly dependent on (1) the number of correctly labeled instances and (2) labeling costs. Active learning has been proposed to reduce the number of instances to label. Albeit the thematic dimension is already used, other metadata such as spatial and temporal information that is helpful for achieving a more fine-grained clustering is currently not taken into account. In this paper, we present a novel event-based clustering strategy that makes use of temporal, spatial, and thematic metadata to determine instances to label. An evaluation on incident-related tweets shows that our selection strategy for active learning outperforms current state-of-the-art approaches even with few labeled instances. © Copyright 2015, Association for the Advancement of Artificial Intelligence. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

WaSABi 2014: Breakout brainstorming session summary 2

WaSABi 2014: Breakout brainstorming session summary

引用

Joint 2nd International Workshop on Semantic web Enterprise Adoption and Best Practice, WaSABi 2014 and 2nd International Workshop on Finance and Economics on the Semantic web, FEOSW 2014 - Co-located with 11th European Semantic web Conference, ESWC 2014

作者： Coppens, Sam Hammar, Karl Knuth, Magnus Neumann, Marco Ritze, Dominique Sande, Miel Vander Ireland Information Engineering Group Jönköping University Sweden Hasso Plattner Institute University of Potsdam Germany KONA LLC NY United States Research Group Data and Web Science University of Mannheim Germany IMinds -Multimedia Lab Ghent University Belgium

来源：评论

学校读者我要写书评

暂无评论

Updating in XML Using Semantic Constraints

International Journal of Database Theory and Application

引用

International Journal of database Theory and Application 2011年第2期4卷 1-12页

作者： Shahriar, Md. Sumon Liu, Jixue Tasmanian ICT Centre CSIRO Hobart 7001 Tasmania Australia Data and Web Engineering Lab School of Computer and Information Science University of South Australia Adelaide SA-5095 Australia

A novel technique for updating in XML using semantic constraints is proposed. In the proposed technique for XML updating, we consider close value pair semantics in ordered XML documents. Further, how semantic constraints can be incorporated with integrity constraints for XML updat-ing and how to update XML views using semantic constraints are discussed.

关键词： XML

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：