检索结果-内蒙古大学图书馆

Neural storyline extraction model for storyline generation from news articles

Neural storyline extraction model for storyline generation f...

2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018

作者： Zhou, Deyu Guo, Linsen He, Yulan School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Southeast University China School of Engineering and Applied Science Aston University United Kingdom

ISBN: (纸本)9781948087278

Storyline generation aims to extract events described on news articles under a certain topic and reveal how those events evolve over time. Most existing approaches first train supervised models to extract events from news articles published in different time periods and then link relevant events into coherent stories. They are domain dependent and cannot deal with unseen event types. To tackle this problem, approaches based on probabilistic graphic models jointly model the generations of events and storylines without annotated data. However, the parameter inference procedure is too complex and models often require long time to converge. In this paper, we propose a novel neural network based approach to extract structured representations and evolution patterns of storylines without using annotated data. In this model, title and main body of a news article are assumed to share the similar storyline distribution. Moreover, similar documents described in neighboring time periods are assumed to share similar storyline distributions. Based on these assumptions, structured representations and evolution patterns of storylines can be extracted. The proposed model has been evaluated on three news corpora and the experimental results show that it outperforms state-of-The-Art approaches accuracy and efficiency. © 2018 The Association for Computational Linguistics.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

SCRIPT: A Scalable Continual Reinforcement Learning Framework for Autonomous Penetration Testing

引用

Expert Systems with Applications 2025年 285卷

作者： Zhou, Shicheng Liu, Jingju Lu, Yuliang Yang, Jiahai Zhang, Yue Lin, Bo Zhong, Xiaofeng Hu, Shulong College of Electronic Engineering National University of Defense Technology Hefei230037 China Anhui Province Key Laboratory of Cyberspace Security Situation Awareness and Evaluation Hefei230037 China Institute for Network Sciences and Cyberspace and the Beijing National Research Center for Information Science and Technology Tsinghua University Beijing10084 China College of Computer Science and Technology National University of Defense Technology Changsha410073 China

Compared with manual-based penetration testing (pentesting), autonomous pentesting offers advantages in autonomy and efficiency, emerging as a trending research area. Reinforcement learning (RL) is a natural fit for studying this topic. However, the proliferation of interconnected devices and systems has expanded attack surfaces, coupled with the constant emergence of new vulnerabilities, making pentesting tasks and scenarios in the real world non-stationary. This non-stationarity presents a new challenge for RL-based autonomous pentesting, as it requires pentesting agents to possess strong generalization capabilities, thereby achieving continuous learn new tasks while mitigating catastrophic forgetting. Previous research in this field overlooked this real-world challenge. To this end, we present the first scalable continual RL framework for autonomous pentesting, namely SCRIPT. SCRIPT trains the agent to learn continually like humans in a large-scale task sequence, allowing it to realize positive forward transfer (leveraging previously learned knowledge to accelerate new task learning) and resist catastrophic forgetting. Inspired by humans’ lifelong learning process, we separate SCRIPT's learning process into new task learning and knowledge consolidation processes. Specifically, we introduce a scaffolded curriculum learning approach to bootstrap new task learning through rolling exploration and policy imitation. Besides, we propose a policy retention method that utilizes regularization-based weight importance constraints and progressive self-distillation-based policy retrospection to mitigate catastrophic forgetting. Experiments are conducted using Vulhub, a widely used repository of vulnerable Docker environments. Results demonstrate that SCRIPT effectively enables agents to achieve positive forward transfer and enhance their resistance to catastrophic forgetting, making it a feasible approach for pentesting agents to handle the real-world non-stationarity challen

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Graph-based single-copy routing in delay tolerant networks

引用

High Technology Letters 2011年第1期17卷 52-56页

作者：于海征 Ma Jianfeng Key Laboratory of Computer Network and Information Security Xidian University Xi＇ an 710071 P. R. China

This paper presents a new graph-based single-copy routmg method m delay tolerant networks （DTN）. With time goes on in the networks, a DTN connectivity graph is constituted with mobility of nodes and communication, and a corresponding greedy tree is obtained using a greedy algorithm in DTN connectivity graph. While there are some bad nodes such as disabled nodes or selfish nodes in delay tolerant networks, the nodes can choose the next p^oper intermediate node to transmit the mes- sage by comparing the location of neighboring nodes in the greedy tree. The single-copy routing method is very appropriate for energy-constrained, storage-constrained and bandwidth-constrained applications such as mobile wireless DTN networks. We show that delivery ratio is increased significantly by using the graph-based single-copy routing when bad nodes exist.

关键词： delay tolerant network （ DTN） message single-copy routing graph

来源：评论

学校读者我要写书评

暂无评论

MOAL: Multi-view Out-of-distribution Awareness Learning

引用

Neural networks 2025年 190卷

作者： Xuzheng Wang Zihan Fang Shide Du Wenzhong Guo Shiping Wang College of Computer and Data Science Fuzhou University Fuzhou 350108 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou 350108 China

Multi-view learning integrates data from multiple sources to enhance task performance by improving data quality. However, existing approaches primarily focus on intra-distribution data learning and consequently fail to identify out-of-distribution instances effectively. This paper introduces a method to improve the perception of out-of-distribution data in multi-view situations. First, we employ multi-view consistency and complementarity principles to develop sub-view complementarity representation learning and multi-view consistency fusion layers, thereby enhancing the model’s perception ability to typical intra-distribution features. Additionally, we introduce a specialized multi-view training loss and an agent mechanism tailored for out-of-distribution scenarios, facilitating the ability to differentiate between known and new or anomalous instances effectively. The proposed approach enhances the recognition of out-of-distribution data by improving intra-distribution feature representations and minimizing the entropy associated with out-of-distribution instances. Experimental results on multiple multi-view datasets simulating out-of-distribution scenarios confirm the effectiveness of MOLA, which consistently outperforms all baselines with average accuracy improvements of over 5%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generalization Based Privacy-Preserving Provenance Publishing 15th

Generalization Based Privacy-Preserving Provenance Publishin...

引用

15th Web information Systems and Applications Conference, WISA 2018

作者： Wu, Jian Ni, Weiwei Zhang, Sen Department of Computer Science and Engineering Southeast University Nanjing211189 China Key Laboratory of Computer Network and Information Integration in Southeast University Ministry of Education Nanjing211189 China

ISBN: (纸本)9783030029333

With thriving of data sharing, demands of data provenance publishing become increasingly urgent. Data provenance describes about how data is generated and evolves with time. Data provenance has many applications, in-cluding evaluation of data quality, audit trail, replication recipes, data citation, etc. Some in-out mapping relations and related intermediate parameters in data provenance may be private. How to protect the privacy in the data provenance publishing attracts increasing attention from researchers in recent years. Existing solutions rely primarily on Γ-privacy model, hiding certain properties to solve the module’s privacy-preserving problem. However, the Γ-privacy model has the following disadvantages: (1) The attribute domains are limited. (2) It’s difficult to set consistent Γ value for the workflow. (3) The attribute selection strategy is unreasonable. Concerning these problems, a novel privacy-preserving provenance model is devised to balance the tradeoff between privacy-preserving and utility of data provenance. The devised model applies the generalization and introduces the generalized level. Furthermore, an effective privacy-preserving provenance publishing method based on generalization is proposed to achieve the privacy security in the data provenance publishing. Finally, theoretical analysis and experimental results testifies the effectiveness of our solution. © 2018, Springer Nature Switzerland AG.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

Smoothing Neural network for Non-Lipschitz Optimization with Linear Inequality Constraints

引用

Chinese Journal of Electronics 2021年第4期30卷 634-643页

作者： YU Xin WU Lingzhen XIE Mian WANG Yanlin XU Liuming LU Huixia XU Chenhua Department of Computer and Electronic Information Guangxi University The Guangxi Key Laboratory of Multimedia Communications and Network Technology School of Computer Science and Engineering Guilin University of Aerospace Technology Department of Electrical Engineering Guangxi University

This paper presents a smoothing neural network to solve a class of non-Lipschitz optimization problem with linear inequality constraints. The proposed neural network is modelled with a differential inclusion equation, which introduces the smoothing approximate techniques. Under certain conditions, we prove that the trajectory of neural network reaches the feasible region in finite time and stays there thereafter, and that any accumulation point of the solution is a stationary point of the original optimization problem. Furthermore, if all stationary points of the optimization problem are isolated,then the trajectory converges to a stationary point of the optimization problem. Two typical numerical examples are given to verify the effectiveness of the proposed neural network.

关键词： Non-Lipschitz optimization Neural networks Stationary points Convergence

来源：评论

学校读者我要写书评

暂无评论

A Clustering-Based Similarity Measurement for Collaborative Filtering 2

A Clustering-Based Similarity Measurement for Collaborative ...

引用

2nd International Conference on Advanced Cloud and Big Data, CBD 2014

作者： Gu, Liang Yang, Peng Dong, Yongqiang School of Computer Science and Engineering Southeast University Nanjing211189 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing211189 China

ISBN: (纸本)9781479980857

Similarity measurement is a crucial process in collaborative filtering. User similarity is computed solely based on the numerical ratings of users. In this paper, we argue that the social information of users should be also taken into consideration to improve the performance of traditional similarity measurements. To achieve this, we propose a clustering-based similarity measurement approach incorporating user social information. In order to cluster the users effectively, we propose a novel distance metric based on taxonomy tree which can easily process the numerical and categorical information of users. Meanwhile, we also address how to determine the contribution of different types of information in the distance metric. After clustering the users, we introduce the incorporating strategy of our proposed similarity measurement. We perform a series of experiments on a real world dataset and compare the performance of our approach against that of traditional approaches. Experiments demonstrate that the proposed approach considerably outperforms the traditional approaches. © 2014 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

BaKer-nets: Bayesian random kernel mapping networks 29

BaKer-nets: Bayesian random kernel mapping networks

引用

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Xue, Hui Wu, Zheng-Fan School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing210096 China

ISBN: (纸本)9780999241165

Recently, deep spectral kernel networks (DSKNs) have attracted wide attention. They consist of periodic computational elements that can be activated across the whole feature spaces. In theory, DSKNs have the potential to reveal input-dependent and long-range characteristics, and thus are expected to perform more competitive than prevailing networks. But in practice, they are still unable to achieve the desired effects. The structural superiority of DSKNs comes at the cost of the difficult optimization. The periodicity of computational elements leads to many poor and dense local minima in loss landscapes. DSKNs are more likely stuck in these local minima, and perform worse than expected. Hence, in this paper, we propose the novel Bayesian random Kernel mapping networks (BaKer-Nets) with preferable learning processes by escaping randomly from most local minima. Specifically, BaKer-Nets consist of two core components: 1) a prior-posterior bridge is derived to enable the uncertainty of computational elements reasonably;2) a Bayesian learning paradigm is presented to optimize the prior-posterior bridge efficiently. With the well-tuned uncertainty, BaKer-Nets can not only explore more potential solutions to avoid local minima, but also exploit these ensemble solutions to strengthen their robustness. Systematical experiments demonstrate the significance of BaKer-Nets in improving learning processes on the premise of preserving the structural superiority. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

An enhanced application-level multicast protocol: A Qos perspective

An enhanced application-level multicast protocol: A Qos pers...

引用

8th International Symposium on Parallel Architectures, Algorithms and networks, I-SPAN 2005

作者： Chu, Zi Yang, Yin-Yin Department of Computer Science and Engineering Southeast University Nanjing 210096 China Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University Nanjing 210096 China

ISBN: (纸本)0769525091

Ubicast, an enhanced application-level multicast protocol, is presented in this paper. It is built upon Pastry, a robust and self-organizing peer-to-peer substrate overlay, and leverages its merits of reliable application-level routing and object location. Ubicast is mainly applied to real-time multimedia applications with QoS heterogeneity. It tries to minimize the delay radius of the multicast tree, while meeting different bandwidth requirements. It extends traditional degree-bound model and satisfies nodes' heterogeneous QoS requirements to provide customizable multicast services. Besides, Priority Joining Algorithm based on the concept of potential parents is proposed to limit the number of nodes that a participant needs to probe. The join cost is decreased substantially to guarantee the scalability for a potentially large network topology. Simulation and experimental analysis over large-scale topology confirm the performance improvement of Ubicast which is especially suited for small sized multicast groups. © 2005 IEEE.

关键词： network protocols

来源：评论

学校读者我要写书评

暂无评论

Mining opinion polarity from multilingual song lyrics 2nd

Mining opinion polarity from multilingual song lyrics

引用

2nd International Workshop on Worldwide Language Service Infrastructure, WLSI 2015

作者： Liu, Qian Gao, Zhiqiang School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration of Ministry of Education Southeast University Nanjing210096 China

ISBN: (纸本)9783319314679

Song opinion is an important criterion when people organize and access songs. The ever growing amount of song data in the Web, which includes multilingual songs, calls for the development of automatic tools in classifying songs by opinion polarity. Sony lyric is a critical resource for song opinion classification. In this paper, we propose an approach to mine the opinion polarity of songs based on song lyrics in a multilingual environment. This approach is based on classification and translation. Firstly, we build monolingual opinion classifiers using supervised learning techniques for resource-rich languages, i.e., languages that are rich of labeled training data. However, it is difficult to build a classifier for a resource-rare language. In this case, we employ Language Grid, which is an infrastructure that is built on the top of the Internet, and provides easy-to-use services for multilingual translation, to bridge the gap between the resources in different languages. Song lyrics are translated from resource-rare languages into resource-rich languages, then the pre-trained monolingual opinion classifiers can be used to classify the translated unseen lyrics. To build effective monolingual opinion classifiers, we employ statistical information of song lyrics as features rather than individual words in the song lyrics. Experiments show that, our proposed approach performs better than two typical baseline approaches. © Springer International Publishing Switzerland 2016.

关键词： Classification (of information)

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：