检索结果-内蒙古大学图书馆

Modeling multi-turn conversation with deep utterance aggregation 27

学校读者我要写书评

暂无评论

Modeling multi-turn conversation with deep utterance aggrega...

27th International Conference on Computational Linguistics, COLING 2018

作者： Zhang, Zhuosheng Li, Jiangtong Zhu, Pengfei Zhao, Hai Liu, Gongshen Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai200240 China College of Zhiyuan Shanghai Jiao Tong University China School of Cyber Security Shanghai Jiao Tong University China School of Computer Science and Software Engineering East China Normal University China

ISBN: (纸本)9781948087506

Multi-turn conversation understanding is a major challenge for building intelligent dialogue systems. This work focuses on retrieval-based response matching for multi-turn conversation whose related work simply concatenates the conversation utterances, ignoring the interactions among previous utterances for context modeling. In this paper, we formulate previous utterances into context using a proposed deep utterance aggregation model to form a fine-grained context representation. In detail, a self-matching attention is first introduced to route the vital information in each utterance. Then the model matches a response with each refined utterance and the final matching score is obtained after attentive turns aggregation. Experimental results show our model outperforms the state-of-the-art methods on three multi-turn conversation benchmarks, including a newly introduced e-commerce dialogue corpus. © 2018 COLING 2018 - 27th International Conference on Computational Linguistics, Proceedings. All rights reserved.

关键词： Speech processing

A unified syntax-aware framework for semantic role labeling

学校读者我要写书评

暂无评论

A unified syntax-aware framework for semantic role labeling

2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018

作者： Li, Zuchao He, Shexia Cai, Jiaxun Zhang, Zhuosheng Zhao, Hai Liu, Gongshen Li, Linlin Si, Luo Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China School of Cyber Security Shanghai Jiao Tong University China Alibaba Group Hangzhou China

ISBN: (纸本)9781948087841

Semantic role labeling (SRL) aims to recognize the predicate-argument structure of a sentence. Syntactic information has been paid a great attention over the role of enhancing SRL. However, the latest advance shows that syntax would not be so important for SRL with the emerging much smaller gap between syntax-aware and syntax-agnostic SRL. To comprehensively explore the role of syntax for SRL task, we extend existing models and propose a unified framework to investigate more effective and more diverse ways of incorporating syntax into sequential neural networks. Exploring the effect of syntactic input quality on SRL performance, we confirm that high-quality syntactic parse could still effectively enhance syntactically-driven SRL. Using empirically optimized integration strategy, we even enlarge the gap between syntax-aware and syntax-agnostic SRL. Our framework achieves state-of-the-art results on CoNLL-2009 benchmarks both for English and Chinese, substantially outperforming all previous models. © 2018 Association for Computational Linguistics

关键词： Syntactics

Deep Active Learning for Anchor User Prediction

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Cheng, Anfeng Zhou, Chuan Yang, Hong Wu, Jia Li, Lei Tan, Jianlong Guo, Li Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Centre for Artificial Intelligence School of Software FEIT University of Technology Sydney Australia Department of Computing Macquarie University Sydney Australia School of Computer Science and Information Engineering Hefei University of Technology China

Predicting pairs of anchor users plays an important role in the cross-network analysis. Due to the expensive costs of labeling anchor users for training prediction models, we consider in this paper the problem of minimizing the number of user pairs across multiple networks for labeling as to improve the accuracy of the prediction. To this end, we present a deep active learning model for anchor user prediction (DALAUP for short). However, active learning for anchor user sampling meets the challenges of non-i.i.d. user pair data caused by network structures and the correlation among anchor or non-anchor user pairs. To solve the challenges, DALAUP uses a couple of neural networks with shared-parameter to obtain the vector representations of user pairs, and ensembles three query strategies to select the most informative user pairs for labeling and model training. Experiments on real-world social network data demonstrate that DALAUP outperforms the state-of-the-art approaches. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep learning

Autonomous extraction of a hierarchical structure of tasks in reinforcement learning, a sequential associate rule mining approach

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Ghazanfari, Behzad Afghah, Fatemeh Taylor, Matthew E. School of Informatics Computing and Cyber Security Northern Arizona University School of Electrical Engineering and Computer Science Washington State University

Reinforcement learning (RL) techniques, while often powerful, can suffer from slow learning speeds, particularly in high dimensional spaces. Decomposition of tasks into a hierarchical structure holds the potential to significantly speed up learning, generalization, and transfer learning. However, the current task decomposition techniques often rely on high-level knowledge provided by an expert (e.g. using dynamic Bayesian networks) to extract a hierarchical task structure;which is not necessarily available in autonomous systems. In this paper, we propose a novel method based on Sequential Association Rule Mining that can extract Hierarchical Structure of Tasks in Reinforcement Learning (SARM-HSTRL) in an autonomous manner for both Markov decision processes (MDPs) and factored MDPs. The proposed method leverages association rule mining to discover the causal and temporal relationships among states in different trajectories, and extracts a task hierarchy that captures these relationships among sub-goals as termination conditions of different sub-tasks. We prove that the extracted hierarchical policy offers a hierarchically optimal policy in MDPs and factored MDPs. It should be noted that SARM-HSTRL extracts this hierarchical optimal policy without having dynamic Bayesian networks in scenarios with a single task trajectory and also with multiple tasks’ trajectories. Furthermore, it has been theoretically and empirically shown that the extracted hierarchical task structure is consistent with trajectories and provides the most efficient, reliable, and compact structure under appropriate assumptions. The numerical results compare the performance of the proposed SARM-HSTRL method with conventional HRL algorithms in terms of the accuracy in detecting the sub-goals, the validity of the extracted hierarchies, and the speed of learning in several testbeds. Copyright © 2018, The Authors. All rights reserved.

关键词： Trajectories

Privacy issues and data protection in big data: A case study analysis under GDPR

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Gruschka, Nils Mavroeidis, Vasileios Vishi, Kamer Jensen, Meiko Research Group of Information and Cyber Security University of Oslo Norway Faculty of Computer Science and Electrical Engineering Kiel University of Applied Science Germany

Big data has become a great asset for many organizations, promising improved operations and new business opportunities. However, big data has increased access to sensitive information that when processed can directly jeopardize the privacy of individuals and violate data protection laws. As a consequence, data controllers and data processors may be imposed tough penalties for non-compliance that can result even to bankruptcy. In this paper, we discuss the current state of the legal regulations and analyse different data protection and privacy-preserving techniques in the context of big data analysis. In addition, we present and analyse two real-life research projects as case studies dealing with sensitive data and actions for complying with the data regulation laws. We show which types of information might become a privacy risk, the employed privacy-preserving techniques in accordance with the legal requirements, and the influence of these techniques on the data processing phase and the research results. Copyright © 2018, The Authors. All rights reserved.

关键词： Big data

Password Guessing Time Based on Guessing Entropy and Long-Tailed Password Distribution in the Large-Scale Password Dataset 11

学校读者我要写书评

暂无评论

Password Guessing Time Based on Guessing Entropy and Long-Ta...

2017 11th IEEE International Conference on Anti-counterfeiting,security,and Identification(ASID)

作者： Shuo Zhang Jianping Zeng Zewen Zhang School of Computer Science Fudan University Engineering Research Center of Cyber Security Auditing and Monitoring Ministry of Education

ISBN: (纸本)9781538605349;9781538605332

Currently the password security is serious, but there is not an appropriate metric for measuring passwords. Thus, the main purpose of this paper is to provide a security time period for the user's password in an online system, allowing the user to modify the password before the security period arrives to prevent the attacker from guessing correctly. We use the guessing chain to calculate the expected time that the attacker need to guess the target password correctly based on the guessing entropy. We assume that the attacker uses a dictionary attack, which is also a probability sequence, and the dictionary is non-ordered or ordered. At the same time, we analyze the large-scale password dataset Rockyou, which contains nearly 32 million passwords. And we assume that the ordered dictionary is organized in descending frequency, in which the probability of the occurrence of the password obeys a long-tailed distribution. We explore the form of the distribution function. And we first find that the simple Zipf distribution can better fit with the empirical distribution of ordered dictionary.

关键词： password security guessing chain guessing entropy long-tailed distributions

security and privacy on blockchain

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zhang, Rui Xue, Rui Liu, Ling State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences 89 Minzhuang Rd Haidian Dist Beijing Beijing100093 China School of Cyber Security University of Chinese Academy of Sciences 19 Yuquan Rd Shijingshan Dist Beijing Beijing100049 China School of Computer Science Georgia Institute of Technology USA AtlantaGA30332-0765 United States

Blockchain offers an innovative approach to storing information, executing transactions, performing functions, and establishing trust in an open environment. Many consider blockchain as a technology breakthrough for cryptography and cybersecurity, with use cases ranging from globally deployed cryptocurrency systems like Bitcoin, to smart contracts, smart grids over the Internet of Things, and so forth. Although blockchain has received growing interests in both academia and industry in the recent years, the security and privacy of blockchains continue to be at the center of the debate when deploying blockchain in different applications. This paper presents a comprehensive overview of the security and privacy of blockchain. To facilitate the discussion, we first introduce the notion of blockchains and its utility in the context of Bitcoin like online transactions. Then we describe the basic security properties that are supported as the essential requirements and building blocks for Bitcoin like cryptocurrency systems, followed by presenting the additional security and privacy properties that are desired in many blockchain applications. Finally, we review the security and privacy techniques for achieving these security properties in blockchain-based systems, including representative consensus algorithms, hash chained storage, mixing protocols, anonymous signatures, non-interactive zero-knowledge proof, and so forth. We conjecture that this survey can help readers to gain an in-depth understanding of the security and privacy of blockchain with respect to concept, attributes, techniques and systems. Copyright © 2019, The Authors. All rights reserved.

关键词： Blockchain

Malware Detection in Cloud Infrastructures Using Convolutional Neural Networks

学校读者我要写书评

暂无评论

Malware Detection in Cloud Infrastructures Using Convolution...

IEEE International Conference on Cloud Computing, CLOUD

作者： Mahmoud Abdelsalam Ram Krishnan Yufei Huang Ravi Sandhu Department of Computer Science Institute for Cyber Security and Center for Security and Privacy Enhanced Cloud Computing Department of Electrical and Computer Engineering University of Texas at San Antonio San Antonio Texas USA

A major challenge in Infrastructure as a Service (IaaS) clouds is its exposure to malware. Malware can spread rapidly within a datacenter and can cause major disruption to a cloud service provider and its clients. This paper introduces and discusses an effective malware detection approach in cloud infrastructure using Convolutional Neural Network (CNN), a deep learning approach. We initially employ a standard 2d CNN by training on metadata available for each of the processes in a virtual machine (VM) obtained by means of the hypervisor. We enhance the CNN classifier accuracy by using a novel 3d CNN (where an input is a collection of samples over a time interval), which greatly helps reduce mislabelled samples during data collection and training. Our experiments are performed on data collected by running various malware (mostly Trojans and Rootkits) on VMs. The malware used in our experiments are randomly selected. This reduces the selection bias of known-to-be highly active malware for easy detection. We demonstrate that our 2d CNN model reaches an accuracy of ≃ 79%, and our 3d CNN model significantly improves the accuracy to ≃ 90%.

关键词： Malware Cloud computing Measurement Feature extraction Static analysis Training Machine learning

iSplit LBI: Individualized partial ranking with ties via split LBI

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Xu, Qianqian Sun, Xinwei Yang, Zhiyong Cao, Xiaochun Huang, Qingming Yao, Yuan Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS Microsoft Research Asia State Key Laboratory of Information Security Institute of Information Engineering CAS School of Cyber Security University of Chinese Academy of Sciences School of Computer Science and Tech. University of Chinese Academy of Sciences Key Laboratory of Big Data Mining and Knowledge Management CAS Peng Cheng Laboratory Department of Mathematics Hong Kong University of Science and Technology Hong Kong

Due to the inherent uncertainty of data, the problem of predicting partial ranking from pairwise comparison data with ties has attracted increasing interest in recent years. However, in real-world scenarios, different individuals often hold distinct preferences. It might be misleading to merely look at a global partial ranking while ignoring personal diversity. In this paper, instead of learning a global ranking which is agreed with the consensus, we pursue the tie-aware partial ranking from an individualized perspective. Particularly, we formulate a unified framework which not only can be used for individualized partial ranking prediction, but also be helpful for abnormal user selection. This is realized by a variable splitting-based algorithm called iSplitLBI. Specifically, our algorithm generates a sequence of estimations with a regularization path, where both the hyperparameters and model parameters are updated. At each step of the path, the parameters can be decomposed into three orthogonal parts, namely, abnormal signals, personalized signals and random noise. The abnormal signals can serve the purpose of abnormal user selection, while the abnormal signals and personalized signals together are mainly responsible for individual partial ranking prediction. Extensive experiments on simulated and real-world datasets demonstrate that our new approach significantly outperforms state-of-the-art alternatives. The code is now availiable at https://***/qianqianxu010/ NeurIPS2019-iSplitLBI. Copyright © 2019, The Authors. All rights reserved.

关键词： Forecasting