检索结果-南通市图书馆

维普期刊数据库

Exploiting unlabeled data for Neural Grammatical Error Detection

在线全文

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2017年第4期32卷 758-767页

作者： Zhuo-Ran Liu Yang Liu School of Software Beihang University Beijing 100191 China State Key Laboratory of Intelligent Technology and Systems Tsinghua University Beijing 100084 China Tsinghua National Laboratory for Information Science and Technology Tsinghua University Beijing 100084 China Department of Computer Science and Technology Tsinghua University Beijing 100084 China Jiangsu Collaborative Innovation Center for Language Competence Xuzhou 221009 China

Identifying and correcting grammatical errors in the text written by non-native writers have received increasing attention in recent years. Although a number of annotated corpora have been established to facilitate data-driven grammatical error detection and correction approaches, they are still limited in terms of quantity and coverage because human annotation is labor-intensive, time-consuming, and expensive. In this work, we propose to utilize unlabeled data to train neural network based grammatical error detection models. The basic idea is to cast error detection as a binary classification problem and derive positive and negative training examples from unlabeled data. We introduce an attention-based neural network to capture long-distance dependencies that influence the word being detected. Experiments show that the proposed approach significantly outperforms SVM and convolutional networks with fixed-size context window.

关键词： unlabeled data grammatical error detection neural network

Combining supervised classifiers with unlabeled data

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Central South University 2016年第5期23卷 1176-1182页

作者：刘雪艳张雪英李凤莲黄丽霞 College of Information Engineering Taiyuan University of Technology

Ensemble learning is a wildly concerned *** ensemble techniques are always adopted to seek better results with labeled data and base *** fail to address the ensemble task where only unlabeled data are available.A label propagation based ensemble(LPBE) approach is proposed to further combine base classification results with unlabeled ***,a graph is constructed by taking unlabeled data as vertexes,and the weights in the graph are calculated by correntropy *** prediction results are gained from base classifiers,and then propagated under a regularization framework and adaptively enhanced over the *** proposed approach is further enriched when small labeled data are *** proposed algorithms are evaluated on several UCI benchmark data *** of simulations show that the proposed algorithms achieve satisfactory performance compared with existing ensemble methods.

关键词： correntropy unlabeled data regularization framework ensemble learning

维普期刊数据库

Efficient poisoning attacks and defenses for unlabeled data in DDoS prediction of intelligent transportation systems

在线全文

学校读者我要写书评

暂无评论

Security and Safety 2022年第1期1卷 121-141页

作者： Zhong Li Xianke Wu Changjun Jiang College of Information Science and Technology Donghua University Key Laboratory of the Ministry of Education for Embedded System and Service Computing Department of Computer Science Tongji University Shanghai Network Financial Security Collaborative Innovation Center Tongji University

Nowadays, large numbers of smart sensors(e.g., road-side cameras) which communicate with nearby base stations could launch distributed denial of services(DDoS) attack storms in intelligent transportation systems. DDoS attacks disable the services provided by base stations. Thus in this paper, considering the uneven communication traffic flows and privacy preserving, we give a hidden Markov model-based prediction model by utilizing the multi-step characteristic of DDoS with a federated learning framework to predict whether DDoS attacks will happen on base stations in the future. However, in the federated learning,we need to consider the problem of poisoning attacks due to malicious participants. The poisoning attacks will lead to the intelligent transportation systems paralysis without security protection. Traditional poisoning attacks mainly apply to the classification model with labeled data. In this paper, we propose a reinforcement learning-based poisoning method specifically for poisoning the prediction model with unlabeled data. Besides, previous related defense strategies rely on validation datasets with labeled data in the server. However, it is unrealistic since the local training datasets are not uploaded to the server due to privacy preserving, and our datasets are also unlabeled. Furthermore, we give a validation dataset-free defense strategy based on Dempster–Shafer(D–S) evidence theory avoiding anomaly aggregation to obtain a robust global model for precise DDoS prediction. In our experiments, we simulate 3000 points in combination with DARPA2000 dataset to carry out evaluations. The results indicate that our poisoning method can successfully poison the global prediction model with unlabeled data in a short time. Meanwhile, we compare our proposed defense algorithm with three popularly used defense algorithms. The results show that our defense method has a high accuracy rate of excluding poisoners and can obtain a high attack prediction probability.

关键词： Poisoning attacks Defenses Multi-step DDoS prediction unlabeled data Intelligent transportation systems

Effcient poisoning attacks and defenses for unlabeled data in DDoS prediction of intelligent transportation systems

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Security and Safety 2022年第1期1卷 145-165页

作者： Zhong Li Xianke Wu Changjun Jiang College of Information Science and Technology Donghua UniversityShanghai 201620China Key Laboratory of the Ministry of Education for Embedded System and Service Computing Department of Computer ScienceTongji UniversityShanghai 201804China Shanghai Network Financial Security Collaborative Innovation Center Tongji UniversityShanghai 201804China

Nowadays,large numbers of smart sensors(e.g.,road-side cameras)which com-municate with nearby base stations could launch distributed denial of services(DDoS)attack storms in intelligent transportation *** attacks disable the services provided by base *** in this paper,considering the uneven communication traffic ows and privacy preserving,we give a hidden Markov model-based prediction model by utilizing the multi-step characteristic of DDoS with a federated learning framework to predict whether DDoS attacks will happen on base stations in the ***,in the federated learning,we need to consider the problem of poisoning attacks due to malicious *** poisoning attacks will lead to the intelligent transportation systems paralysis without security *** poisoning attacks mainly apply to the classi cation model with labeled *** this paper,we propose a reinforcement learning-based poisoningmethod speci cally for poisoning the prediction model with unlabeled ***,previous related defense strategies rely on validation datasets with labeled data in the ***,it is unrealistic since the local training datasets are not uploaded to the server due to privacy preserving,and our datasets are also ***,we give a validation dataset-free defense strategy based on Dempster-Shafer(D-S)evidence theory avoiding anomaly aggregation to obtain a robust global model for precise DDoS *** our experiments,we simulate 3000 points in combination with DARPA2000 dataset to carry out *** results indicate that our poisoning method can successfully poison the global prediction model with unlabeled data in a short ***,we compare our proposed defense algorithm with three popularly used defense *** results show that our defense method has a high accuracy rate of excluding poisoners and can obtain a high attack prediction probability.

关键词： Poisoning attacks Defenses Multi-step DDoS prediction unlabeled data Intel-ligent transportation systems

Crowdsourcing label quality: a theoretical analysis

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2015年第11期58卷 113-124页

作者： WANG Wei ZHOU Zhi-Hua National Key Laboratory for Novel Software Technology Nanjing University

Crowdsourcing has been an effective and efficient paradigm for providing labels for large-scale unlabeled data. In the past few years, many methods have been developed for inferring labels from the crowd,but few theoretical analyses have been presented to support this popular human-machine interaction *** this paper, we theoretically study the quality of labels inferred from crowd workers by majority voting and provide an analysis of label quality that shows that the label error rate decreases exponentially with the number of workers selected for each task. We also study the problem of eliminating low-quality workers from the crowd,and provide a conservative condition for eliminating low-quality workers without eliminating any non-low-quality worker with high probability. We also provide an aggressive condition for eliminating all low-quality workers with high probability.

关键词： unlabeled data crowdsourcing majority voting label quality worker selection

Learning to select pseudo labels: a semi-supervisedmethod for named entity recognition

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2020年第6期21卷 903-916页

作者： Zhen-zhen LI Da-wei FENG Dong-sheng LI Xi-cheng LU College of Computer National University of Defense TechnologyChangsha 410073China

Deep learning models have achieved state-of-the-art performance in named entity recognition(NER);the good performance,however,relies heavily on substantial amounts of labeled *** some specific areas such as medical,financial,and military domains,labeled data is very scarce,while unlabeled data is readily *** studies have used unlabeled data to enrich word representations,but a large amount of entity information in unlabeled data is neglected,which may be beneficial to the NER *** this study,we propose a semi-supervised method for NER tasks,which learns to create high-quality labeled data by applying a pre-trained module to filter out erroneous pseudo *** labels are automatically generated for unlabeled data and used as if they were true *** semi-supervised framework includes three steps:constructing an optimal single neural model for a specific NER task,learning a module that evaluates pseudo labels,and creating new labeled data and improving the NER model *** results on two English NER tasks and one Chinese clinical NER task demonstrate that our method further improves the performance of the best single neural *** when we use only pre-trained static word embeddings and do not rely on any external knowledge,our method achieves comparable performance to those state-of-the-art models on the CoNLL-2003 and OntoNotes 5.0 English NER tasks.

关键词： Named entity recognition unlabeled data Deep learning Semi-supervised method

Iterative Semi-Supervised Learning Using Softmax Probability

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第9期72卷 5607-5628页

作者： Heewon Chung Jinseok Lee Department of Biomedical Engineering College of Electronics and InformationKyung Hee UniversityYongin-siGyeonggi-do17104Korea

For the classification problem in practice,one of the challenging issues is to obtain enough labeled data for ***,even if such labeled data has been sufficiently accumulated,most datasets often exhibit long-tailed distribution with heavy class imbalance,which results in a biased model towards a majority *** alleviate such class imbalance,semisupervised learning methods using additional unlabeled data have been ***,as a matter of course,the accuracy is much lower than that from supervised *** this study,under the assumption that additional unlabeled data is available,we propose the iterative semi-supervised learning algorithms,which iteratively correct the labeling of the extra unlabeled data based on softmax *** results show that the proposed algorithms provide the accuracy as high as that from the supervised *** validate the proposed algorithms,we tested on the two scenarios:with the balanced unlabeled dataset and with the imbalanced unlabeled *** both scenarios,our proposed semi-supervised learning algorithms provided higher accuracy than previous *** is available at https://***/HeewonChung92/iterative-semi-learning.

关键词： Semi-supervised learning class imbalance iterative learning unlabeled data

Research and Implementation of Unsupervised Clustering-Based Intrusion Detection

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Wuhan University Journal of Natural Sciences 2003年第3A期8卷 803-807页

作者： Luo Min, Zhang Huan\|guo, Wang Li\|na School of Computer, Wuhan University, Wuhan 430072, Hubei, China School of Computer Wuhan University Wuhan Hubei China

An unsupervised clustering\|based intrusion detection algorithm is discussed in this paper. The basic idea of the algorithm is to produce the cluster by comparing the distances of unlabeled training data sets. With the classified data instances, anomaly data clusters can be easily identified by normal cluster ratio and the identified cluster can be used in real data detection. The benefit of the algorithm is that it doesn't need labeled training data sets. The experiment concludes that this approach can detect unknown intrusions efficiently in the real network connections via using the data sets of KDD99.

关键词： intrusion detection data mining unsupervised clustering unlabeled data

维普期刊数据库

Breast Cancer Diagnosis Using an Unsupervised Feature Extraction Algorithm Based on Deep Learning

在线全文

学校读者我要写书评

暂无评论

Breast Cancer Diagnosis Using an Unsupervised Feature Extrac...