检索结果-内蒙古大学图书馆

An Answer Summarization Scheme Based on Multilayer Attention Model

学校读者我要写书评

暂无评论

An Answer Summarization Scheme Based on Multilayer Attention...

International Conference on Computer Supported Cooperative Work in Design

作者： Xiaolong Xu Yihao Dong Jian Song Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China

At present, deep learning technologies have been widely used in the field of natural language process, such as text summarization. In CQA, the answer summary could help users get a complete answer quickly. There are still some problems with the current answer summary scheme, such as semantic inconsistency, repetition of words, etc. In order to solve this, we propose a novel scheme Answer Summarization based on Multi-layer Attention Scheme (ASMAM). Based on the traditional Seq2Seq, we introduce self-attention and multi-head attention scheme respectively during sentence and text encoding, which could improve text representation ability of the model. In order to solve "long distance dependence" of RNN and too many parameters of LSTM, we all use GRU as the neuron at the encoder and decoder sides. Experiments over the Yahoo! Answers dataset demonstrate that the coherence and fluency of the generated summary are all superior to the benchmark model in ROUGE evaluation system.

关键词：

SSR-TA: Sequence to Sequence based expert recurrent recommendation for ticket automation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cao, Chenhan Fang, Xiaoyu Luo, Bingqing Xia, Bin Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China

The ticket automation provides crucial support for the normal operation of IT software systems. An essential task of ticket automation is to assign experts to solve upcoming tickets. However, facing thousands of tickets, inappropriate assignments will make tickets transfer frequently among experts, which causes time delays and wasted resources. Effectively and efficiently finding an appropriate expert in fewer steps is vital to ticket automation. In this paper, we proposed a sequence to sequence based translation model combined with a recurrent recommendation network to recommend appropriate experts for tickets. The sequence to sequence model transforms the ticket description into the corresponding resolution for capturing the potential and useful features of representing tickets. The recurrent recommendation network recommends the appropriate expert based on the assumption that the previous expert in the recommendation sequence cannot solve the expert. To evaluate the performance, we conducted experiments to compare several baselines with SSR-TA on two real-world datasets, and the experimental results show that our proposed model outperforms the baselines. The comparative experiment results also show that SSR-TA has a better performance of expert recommendations for user-generated tickets. Copyright © 2023, The Authors. All rights reserved.

关键词： Automation

Community-based Message Forwarding in Mobile Social Networks

学校读者我要写书评

暂无评论

Community-based Message Forwarding in Mobile Social Networks

作者： Zhiming Chen Yang Xiang School of Computer Nanjing University of Posts and Telecommunications Jiangsu Key Laboratory of Big Data Security & Intelligent Processing

With the popularity of various smart devices and the application of sensor network technology, message transmission using mobile devices is becoming *** paper focuses on the forwarding in mobile social network(MSN).The MSN is a special Delay Tolerant Network(DTN) consisting of mobile *** MSN, nodes move and share information with each other through carried short-range wireless communication *** nodes in the MSN typically access some building areas more frequently, such as schools, companies, or apartments, while visiting other areas, such as the roads between buildings, less *** building areas that nodes frequently visit are called *** increase delivery ratio and reduce transmission time in MSN, this paper proposes a novel zero-knowledge multi-copy routing algorithm, Mixed Message Forwarding(MMF) which exploits and improves the metric, namely *** reflects the importance of a node in the *** improves copy diffusion by using different directions of node movement as *** facilities called boundary boxes are added to the network *** boxes are special throw *** boxes are relays with large storage space and fixed *** is designed and evaluated, which utilizes the aforementioned boundary boxes to reduce transmission *** simulation results show that the MMF can improve the delivery ratio and reduce the transmission delay, compared with other algorithms.

关键词：

Dlr: Adversarial Examples Detection and label Recovery for Deep Neural Networks

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Han, Keji Ge, Yao Wang, Ruchuan Li, Yun Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Jiangsu Nanjing210023 China

Deep neural networks (DNNs) are demonstrated to be vulnerable to the adversarial example crafted by the adversary to fool the target model. Adversarial training and adversarial example detection are two popular methods to mitigate the adversarial issue. The adversarial training makes the target model recognize the adversarial example correctly for the image classification task, while it does not generalize well. The adversarial detection generalizes well but cannot help the target model recognize the adversarial example. We first define the label recovery task to address the adversarial issue for DNNs. Then we propose a new generative classifier and apply it to the adversarial example label recovery task. The proposed method is named as Detection and label Recovery (DLR) defense method, which consists of Detector and Recover. Detector feeds the legitimate and adversarial examples to the target model and Recover, respectively. The Recover explores the ground-truth label of the detected adversarial example. DLR combines the merits of adversarial training and adversarial example detection. Experimental results demonstrate that our method outperforms some state-of-the-art adversarial training methods. © 2023, The Authors. All rights reserved.

关键词： Anomaly detection

Bidirectional LSTM-CRF for biomedical named entity recognition 14

学校读者我要写书评

暂无评论

Bidirectional LSTM-CRF for biomedical named entity recogniti...

14th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2018

作者： Yang, Xuemin Gao, Zhihong Li, Yongmin Pan, Chuandi Yang, Ronggen Gong, Lejun Yang, Geng Jiangsu Key Laboratory of Big Data Security Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing210003 China Zhejiang Engineering Research Center of Intelligence Medicine Wenzhou325035 China Faculty Intelligent Science and Control Engineering Jinling Institute of Technology Nanjing211169 China

ISBN: (纸本)9781538680971

Bio-medical entity recognition extracts significant entities, for instance cells, proteins and genes, which is an arduous task in an automatic system that mine knowledge in bioinformatics texts. In this thesis, we utilized a bidirectional long short-term memory (Bi-LSTM) combined with conditional random fields (CRFs) approach to automatically obtain word representation, obliterated the need for a marvelous number of feature engineering tasks. The consequences of this experiment represent the word representation method can effectually acquire potential semantic information. Without relying on any artificial features, the result on the test dataset obtained 76.81 % F-score. Therefore, the proposed method is expected to advance biomedical text mining in bioinformatics entity recognition. © 2018 IEEE.

关键词： Bioinformatics

Robust Particle Filtering via Bayesian Nonparametric Outlier Modeling

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Liu, Bin School of Computer Science Jiangsu Key Lab of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China

This paper is concerned with the online estimation of a nonlinear dynamic system from a series of noisy measurements. The focus is on cases wherein outliers are present in-between normal noises. We assume that the outliers follow an unknown generating mechanism which deviates from that of normal noises, and then model the outliers using a Bayesian nonparametric model called Dirichlet process mixture (DPM). A sequential particle-based algorithm is derived for posterior inference for the outlier model as well as the state of the system to be estimated. The resulting algorithm is termed DPM based robust PF (DPM-RPF). The nonparametric feature makes this algorithm allow the data to "speak for itself" to determine the complexity and structure of the outlier model. Simulation results show that it performs remarkably better than two state-of-the-art methods especially when outliers appear frequently along time. Copyright © 2018, The Authors. All rights reserved.

关键词： Statistics

Harnessing Low-Fidelity data to Accelerate Bayesian Optimization via Posterior Regularization

学校读者我要写书评

暂无评论

Harnessing Low-Fidelity Data to Accelerate Bayesian Optimiza...

International Conference on big data and Smart Computing (bigCOMP)

作者： Bin Liu School of Computer Science Jiangsu Key Lab of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (数字)9781728160344

ISBN: (纸本)9781728160351

Bayesian optimization (BO) is a powerful paradigm for derivative-free global optimization of a black-box objective function (BOF) that is expensive to evaluate. However, the overhead of BO can still be prohibitive for problems with highly expensive function evaluations. In this paper, we investigate how to reduce the required number of function evaluations for BO without compromise in solution quality. We explore the idea of posterior regularization to harness low fidelity (LF) data within the Gaussian process upper confidence bound (GP-UCB) framework. The LF data can arise from previous evaluations of an LF approximation of the BOF or a related optimization task. An extra GP model called LF-GP is trained to fit the LF data. We develop an operator termed dynamic weighted product of experts (DW-POE) fusion. The regularization is induced by this operator on the posterior of the BOF. The impact of the LF GP model on the resulting regularized posterior is adaptively adjusted via Bayesian formalism. Extensive experimental results on benchmark BOF optimization tasks demonstrate the superior performance of the proposed algorithm over state-of-the-art.

关键词： Optimization Hafnium Adaptation models Bayes methods Heuristic algorithms data models Acceleration

Harnessing low-fidelity data to accelerate Bayesian optimization via posterior regularization

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Liu, Bin School of Computer Science Jiangsu Key Lab of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China

关键词： Function evaluation

Particle filtering methods for stochastic optimization with application to large-scale empirical risk minimization

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Liu, Bin School of Computer Science Nanjing University of Posts and Telecommunications Jiangsu Key Lab of Big Data Security & Intelligent Processing Nanjing Jiangsu210023 China

There is a recent interest in developing statistical filtering methods for stochastic optimization (FSO) by leveraging a probabilistic perspective of incremental proximity methods (IPMs). The existent FSO methods are derived based on the Kalman filter (KF) and extended KF (EKF). Different from classical stochastic optimization methods such as the stochastic gradient descent (SGD) and typical IPMs, such KF-type algorithms possess a desirable property, namely they do not require pre-scheduling of the learning rate for convergence. However, on the other side, they have inherent limitations inherited from the nature of KF mechanisms. It is a consensus that the class of particle filters (PFs) outperforms the KF and its variants remarkably for nonlinear and/or non-Gaussian statistical filtering tasks. Hence, it is natural to ask if the FSO methods can benefit from the PF theory to get around of limitations of the KF-type stochastic optimization methods. We provide an affirmative answer to the aforementioned question by developing two PF based stochastic optimizers (PFSOs). For performance evaluation, we apply them to address nonlinear least-square fitting using simulated data sets and empirical risk minimization for binary classification using real data sets. Experimental results demonstrate that PFSOs outperform remarkably existent methods in terms of numerical stability, convergence speed, and flexibility in handling different types of loss functions. Copyright © 2018, The Authors. All rights reserved.

关键词： Monte Carlo methods