In order to prevent possible casualties and economic loss, it is critical to accurate prediction of the Remaining Useful Life (RUL) in rail prognostics health management. However, the traditional neural networks is di...In order to prevent possible casualties and economic loss, it is critical to accurate prediction of the Remaining Useful Life (RUL) in rail prognostics health management. However, the traditional neural networks is difficult to capture the long-term dependency relationship of the time series in the modeling of the long time series of rail damage, due to the coupling relationship of multi-channel data from multiple sensors. Here, in this paper, a novel RUL prediction model with an enhanced pulse separable convolution is used to solve this issue. Firstly, a coding module based on the improved pulse separable convolutional network is established to effectively model the relationship between the data. To enhance the network, an alternate gradient back propagation method is implemented. And an efficient channel attention (ECA) mechanism is developed for better emphasizing the useful pulse characteristics. Secondly, an optimized Transformer encoder was designed to serve as the backbone of the model. It has the ability to efficiently understand relationship between the data itself and each other at each time step of long time series with a full life cycle. More importantly, the Transformer encoder is improved by integrating pulse maximum pooling to retain more pulse timing characteristics. Finally, based on the characteristics of the front layer, the final predicted RUL value was provided and served as the end-to-end solution. The empirical findings validate the efficacy of the suggested approach in forecasting the rail RUL, surpassing various existing data-driven prognostication techniques. Meanwhile, the proposed method also shows good generalization performance on PHM2012 bearing data set.展开更多
Cyberbullying,a critical concern for digital safety,necessitates effective linguistic analysis tools that can navigate the complexities of language use in online spaces.To tackle this challenge,our study introduces a ...Cyberbullying,a critical concern for digital safety,necessitates effective linguistic analysis tools that can navigate the complexities of language use in online spaces.To tackle this challenge,our study introduces a new approach employing Bidirectional Encoder Representations from the Transformers(BERT)base model(cased),originally pretrained in English.This model is uniquely adapted to recognize the intricate nuances of Arabic online communication,a key aspect often overlooked in conventional cyberbullying detection methods.Our model is an end-to-end solution that has been fine-tuned on a diverse dataset of Arabic social media(SM)tweets showing a notable increase in detection accuracy and sensitivity compared to existing methods.Experimental results on a diverse Arabic dataset collected from the‘X platform’demonstrate a notable increase in detection accuracy and sensitivity compared to existing methods.E-BERT shows a substantial improvement in performance,evidenced by an accuracy of 98.45%,precision of 99.17%,recall of 99.10%,and an F1 score of 99.14%.The proposed E-BERT not only addresses a critical gap in cyberbullying detection in Arabic online forums but also sets a precedent for applying cross-lingual pretrained models in regional language applications,offering a scalable and effective framework for enhancing online safety across Arabic-speaking communities.展开更多
Arabic Dialect Identification(DID)is a task in Natural Language Processing(NLP)that involves determining the dialect of a given piece of text in Arabic.The state-of-the-art solutions for DID are built on various deep ...Arabic Dialect Identification(DID)is a task in Natural Language Processing(NLP)that involves determining the dialect of a given piece of text in Arabic.The state-of-the-art solutions for DID are built on various deep neural networks that commonly learn the representation of sentences in response to a given dialect.Despite the effectiveness of these solutions,the performance heavily relies on the amount of labeled examples,which is labor-intensive to atain and may not be readily available in real-world scenarios.To alleviate the burden of labeling data,this paper introduces a novel solution that leverages unlabeled corpora to boost performance on the DID task.Specifically,we design an architecture that enables learning the shared information between labeled and unlabeled texts through a gradient reversal layer.The key idea is to penalize the model for learning source dataset specific features and thus enable it to capture common knowledge regardless of the label.Finally,we evaluate the proposed solution on benchmark datasets for DID.Our extensive experiments show that it performs signifcantly better,especially,with sparse labeled data.By comparing our approach with existing Pre-trained Language Models(PLMs),we achieve a new state-of-the-art performance in the DID field.The code will be available on GitHub upon the paper's acceptance.展开更多
Semi-supervised new intent discovery is a significant research focus in natural language understanding.To address the limitations of current semi-supervised training data and the underutilization of implicit informati...Semi-supervised new intent discovery is a significant research focus in natural language understanding.To address the limitations of current semi-supervised training data and the underutilization of implicit information,a Semi-supervised New Intent Discovery for Elastic Neighborhood Syntactic Elimination and Fusion model(SNID-ENSEF)is proposed.Syntactic elimination contrast learning leverages verb-dominant syntactic features,systematically replacing specific words to enhance data diversity.The radius of the positive sample neighborhood is elastically adjusted to eliminate invalid samples and improve training efficiency.A neighborhood sample fusion strategy,based on sample distribution patterns,dynamically adjusts neighborhood size and fuses sample vectors to reduce noise and improve implicit information utilization and discovery accuracy.Experimental results show that SNID-ENSEF achieves average improvements of 0.88%,1.27%,and 1.30%in Normalized Mutual Information(NMI),Accuracy(ACC),and Adjusted Rand Index(ARI),respectively,outperforming PTJN,DPN,MTP-CLNN,and DWG models on the Banking77,StackOverflow,and Clinc150 datasets.The code is available at https://github.com/qsdesz/SNID-ENSEF,accessed on 16 January 2025.展开更多
Emotion Recognition in Conversations(ERC)is fundamental in creating emotionally intelligentmachines.Graph-BasedNetwork(GBN)models have gained popularity in detecting conversational contexts for ERC tasks.However,their...Emotion Recognition in Conversations(ERC)is fundamental in creating emotionally intelligentmachines.Graph-BasedNetwork(GBN)models have gained popularity in detecting conversational contexts for ERC tasks.However,their limited ability to collect and acquire contextual information hinders their effectiveness.We propose a Text Augmentation-based computational model for recognizing emotions using transformers(TA-MERT)to address this.The proposed model uses the Multimodal Emotion Lines Dataset(MELD),which ensures a balanced representation for recognizing human emotions.Themodel used text augmentation techniques to producemore training data,improving the proposed model’s accuracy.Transformer encoders train the deep neural network(DNN)model,especially Bidirectional Encoder(BE)representations that capture both forward and backward contextual information.This integration improves the accuracy and robustness of the proposed model.Furthermore,we present a method for balancing the training dataset by creating enhanced samples from the original dataset.By balancing the dataset across all emotion categories,we can lessen the adverse effects of data imbalance on the accuracy of the proposed model.Experimental results on the MELD dataset show that TA-MERT outperforms earlier methods,achieving a weighted F1 score of 62.60%and an accuracy of 64.36%.Overall,the proposed TA-MERT model solves the GBN models’weaknesses in obtaining contextual data for ERC.TA-MERT model recognizes human emotions more accurately by employing text augmentation and transformer-based encoding.The balanced dataset and the additional training samples also enhance its resilience.These findings highlight the significance of transformer-based approaches for special emotion recognition in conversations.展开更多
识别服装质量抽检通告中的实体信息,对于评估不同区域的服装质量状况以及制定宏观政策具有重要意义。针对质量抽检通告命名实体识别存在的长文本序列信息丢失、小类样本特征学习不全等问题,以注意力机制为核心,提出了基于BERT(bidirecti...识别服装质量抽检通告中的实体信息,对于评估不同区域的服装质量状况以及制定宏观政策具有重要意义。针对质量抽检通告命名实体识别存在的长文本序列信息丢失、小类样本特征学习不全等问题,以注意力机制为核心,提出了基于BERT(bidirectional encoder representations from transformers)和TENER(transformer encoder for NER)模型的领域命名实体识别模型。BERT-TENER模型通过预训练模型BERT获得字符的动态字向量;将字向量输入TENER模块中,基于注意力机制使得同样的字符拥有不同的学习过程,基于改进的Transformer模型进一步捕捉字符与字符之间的距离和方向信息,增强模型对不同长度、小类别文本内容的理解,并采用条件随机场模型获得每个字符对应的实体标签。在领域数据集上,BERT-TENER模型针对服装抽检领域的实体识别F_1达到92.45%,相较传统方法有效提升了命名实体识别率,并且在长文本以及非均衡的实体类别中也表现出较好的性能。展开更多
首先利用bidirectional encoder representations from transformers(BERT)模型的强大的语境理解能力来提取数据法律文本的深层语义特征,然后引入细粒度特征提取层,依照注意力机制,重点关注文本中与数据法律问答相关的关键部分,最后对...首先利用bidirectional encoder representations from transformers(BERT)模型的强大的语境理解能力来提取数据法律文本的深层语义特征,然后引入细粒度特征提取层,依照注意力机制,重点关注文本中与数据法律问答相关的关键部分,最后对所采集的法律问答数据集进行训练和评估.结果显示:与传统的多个单一模型相比,所提出的模型在准确度、精确度、召回率、F1分数等关键性能指标上均有提升,表明该系统能够更有效地理解和回应复杂的数据法学问题,为研究数据法学的专业人士和公众用户提供更高质量的问答服务.展开更多
While encryption technology safeguards the security of network communications,malicious traffic also uses encryption protocols to obscure its malicious behavior.To address the issues of traditional machine learning me...While encryption technology safeguards the security of network communications,malicious traffic also uses encryption protocols to obscure its malicious behavior.To address the issues of traditional machine learning methods relying on expert experience and the insufficient representation capabilities of existing deep learning methods for encrypted malicious traffic,we propose an encrypted malicious traffic classification method that integrates global semantic features with local spatiotemporal features,called BERT-based Spatio-Temporal Features Network(BSTFNet).At the packet-level granularity,the model captures the global semantic features of packets through the attention mechanism of the Bidirectional Encoder Representations from Transformers(BERT)model.At the byte-level granularity,we initially employ the Bidirectional Gated Recurrent Unit(BiGRU)model to extract temporal features from bytes,followed by the utilization of the Text Convolutional Neural Network(TextCNN)model with multi-sized convolution kernels to extract local multi-receptive field spatial features.The fusion of features from both granularities serves as the ultimate multidimensional representation of malicious traffic.Our approach achieves accuracy and F1-score of 99.39%and 99.40%,respectively,on the publicly available USTC-TFC2016 dataset,and effectively reduces sample confusion within the Neris and Virut categories.The experimental results demonstrate that our method has outstanding representation and classification capabilities for encrypted malicious traffic.展开更多
The rapid expansion of online content and big data has precipitated an urgent need for efficient summarization techniques to swiftly comprehend vast textual documents without compromising their original integrity.Curr...The rapid expansion of online content and big data has precipitated an urgent need for efficient summarization techniques to swiftly comprehend vast textual documents without compromising their original integrity.Current approaches in Extractive Text Summarization(ETS)leverage the modeling of inter-sentence relationships,a task of paramount importance in producing coherent summaries.This study introduces an innovative model that integrates Graph Attention Networks(GATs)with Transformer-based Bidirectional Encoder Representa-tions from Transformers(BERT)and Latent Dirichlet Allocation(LDA),further enhanced by Term Frequency-Inverse Document Frequency(TF-IDF)values,to improve sentence selection by capturing comprehensive topical information.Our approach constructs a graph with nodes representing sentences,words,and topics,thereby elevating the interconnectivity and enabling a more refined understanding of text structures.This model is stretched to Multi-Document Summarization(MDS)from Single-Document Summarization,offering significant improvements over existing models such as THGS-GMM and Topic-GraphSum,as demonstrated by empirical evaluations on benchmark news datasets like Cable News Network(CNN)/Daily Mail(DM)and Multi-News.The results consistently demonstrate superior performance,showcasing the model’s robustness in handling complex summarization tasks across single and multi-document contexts.This research not only advances the integration of BERT and LDA within a GATs but also emphasizes our model’s capacity to effectively manage global information and adapt to diverse summarization challenges.展开更多
Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requir...Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requires more syntactic elements.Most existing strategies focus on the general semantics of a conversation without involving the context of the sentence,recognizing the progress and comparing impacts.An ensemble pre-trained language model was taken up here to classify the conversation sentences from the conversation corpus.The conversational sentences are classified into four categories:information,question,directive,and commission.These classification label sequences are for analyzing the conversation progress and predicting the pecking order of the conversation.Ensemble of Bidirectional Encoder for Representation of Transformer(BERT),Robustly Optimized BERT pretraining Approach(RoBERTa),Generative Pre-Trained Transformer(GPT),DistilBERT and Generalized Autoregressive Pretraining for Language Understanding(XLNet)models are trained on conversation corpus with hyperparameters.Hyperparameter tuning approach is carried out for better performance on sentence classification.This Ensemble of Pre-trained Language Models with a Hyperparameter Tuning(EPLM-HT)system is trained on an annotated conversation dataset.The proposed approach outperformed compared to the base BERT,GPT,DistilBERT and XLNet transformer models.The proposed ensemble model with the fine-tuned parameters achieved an F1_score of 0.88.展开更多
针对标书文本重要信息的抽取需求,提出一种基于BERT(bidirectional encoder representations from transformers)的阅读理解式标书文本信息抽取方法。该方法将信息抽取任务转换为阅读理解任务,根据标书文本内容,生成对应问题,再抽取标...针对标书文本重要信息的抽取需求,提出一种基于BERT(bidirectional encoder representations from transformers)的阅读理解式标书文本信息抽取方法。该方法将信息抽取任务转换为阅读理解任务,根据标书文本内容,生成对应问题,再抽取标书文本片段作为问题答案。利用BERT预训练模型,得到强健的语言模型,获取更深层次的上下文关联。相比传统的命名实体识别方法,基于阅读理解的信息抽取方法能够很好地同时处理非嵌套实体和嵌套实体的抽取,也能充分利用问题所包含的先验语义信息,区分出具有相似属性的信息。从中国政府采购网下载标书文本数据进行了实验,本文方法总体EM(exact match)值达到92.41%,F1值达到95.03%。实验结果表明本文提出的方法对标书文本的信息抽取是有效的。展开更多
多项选择作为机器阅读理解中的一项重要任务,在自然语言处理(natural language processing,NLP)领域受到了广泛关注。由于数据中需要处理的文本长度不断增长,长文本多项选择成为了一项新的挑战。然而,现有的长文本处理方法容易丢失文本...多项选择作为机器阅读理解中的一项重要任务,在自然语言处理(natural language processing,NLP)领域受到了广泛关注。由于数据中需要处理的文本长度不断增长,长文本多项选择成为了一项新的挑战。然而,现有的长文本处理方法容易丢失文本中的有效信息,导致结果不准确。针对上述问题,提出了一种基于压缩与推理的长文本多项选择答题方法(Long Text Multiple Choice Answer Method Based on Compression and Reasoning,LTMCA),通过训练评判模型识别相关句子,将相关句拼接成短文本输入到推理模型进行推理。为了提高评判模型的精度,在评判模型中增加了文章与选项之间的交互以补充文章对选项的注意力,有针对性地进行相关语句识别,更加准确地完成多项选择答题任务。在本文构建的CLTMCA中文长文本多项选择数据集上进行了实验验证,结果表明本文方法能够有效地解决BERT在处理长文本多项选择任务时的限制问题,相比于其他方法,在各项评价指标上均取得了较高的提升。展开更多
In the era of big data,E-commerce plays an increasingly important role,and steel E-commerce certainly occupies a positive position.However,it is very difficult to choose satisfactory steel raw materials from diverse s...In the era of big data,E-commerce plays an increasingly important role,and steel E-commerce certainly occupies a positive position.However,it is very difficult to choose satisfactory steel raw materials from diverse steel commodities online on steel E-commerce platforms in the purchase of staffs.In order to improve the efficiency of purchasers searching for commodities on the steel E-commerce platforms,we propose a novel deep learning-based loss function for named entity recognition(NER).Considering the impacts of small sample and imbalanced data,in our NER scheme,the focal loss,the label smoothing,and the cross entropy are incorporated into a lite bidirectional encoder representations from transformers(BERT)model to avoid the over-fitting.Moreover,through the analysis of different classic annotation techniques used to tag data,an ideal one is chosen for the training model in our proposed scheme.Experiments are conducted on Chinese steel E-commerce datasets.The experimental results show that the training time of a lite BERT(ALBERT)-based method is much shorter than that of BERT-based models,while achieving the similar computational performance in terms of metrics precision,recall,and F1 with BERT-based models.Meanwhile,our proposed approach performs much better than that of combining Word2Vec,bidirectional long short-term memory(Bi-LSTM),and conditional random field(CRF)models,in consideration of training time and F1.展开更多
文摘In order to prevent possible casualties and economic loss, it is critical to accurate prediction of the Remaining Useful Life (RUL) in rail prognostics health management. However, the traditional neural networks is difficult to capture the long-term dependency relationship of the time series in the modeling of the long time series of rail damage, due to the coupling relationship of multi-channel data from multiple sensors. Here, in this paper, a novel RUL prediction model with an enhanced pulse separable convolution is used to solve this issue. Firstly, a coding module based on the improved pulse separable convolutional network is established to effectively model the relationship between the data. To enhance the network, an alternate gradient back propagation method is implemented. And an efficient channel attention (ECA) mechanism is developed for better emphasizing the useful pulse characteristics. Secondly, an optimized Transformer encoder was designed to serve as the backbone of the model. It has the ability to efficiently understand relationship between the data itself and each other at each time step of long time series with a full life cycle. More importantly, the Transformer encoder is improved by integrating pulse maximum pooling to retain more pulse timing characteristics. Finally, based on the characteristics of the front layer, the final predicted RUL value was provided and served as the end-to-end solution. The empirical findings validate the efficacy of the suggested approach in forecasting the rail RUL, surpassing various existing data-driven prognostication techniques. Meanwhile, the proposed method also shows good generalization performance on PHM2012 bearing data set.
基金funded by Scientific Research Deanship at University of Ha’il-Saudi Arabia through Project Number RG-23092。
文摘Cyberbullying,a critical concern for digital safety,necessitates effective linguistic analysis tools that can navigate the complexities of language use in online spaces.To tackle this challenge,our study introduces a new approach employing Bidirectional Encoder Representations from the Transformers(BERT)base model(cased),originally pretrained in English.This model is uniquely adapted to recognize the intricate nuances of Arabic online communication,a key aspect often overlooked in conventional cyberbullying detection methods.Our model is an end-to-end solution that has been fine-tuned on a diverse dataset of Arabic social media(SM)tweets showing a notable increase in detection accuracy and sensitivity compared to existing methods.Experimental results on a diverse Arabic dataset collected from the‘X platform’demonstrate a notable increase in detection accuracy and sensitivity compared to existing methods.E-BERT shows a substantial improvement in performance,evidenced by an accuracy of 98.45%,precision of 99.17%,recall of 99.10%,and an F1 score of 99.14%.The proposed E-BERT not only addresses a critical gap in cyberbullying detection in Arabic online forums but also sets a precedent for applying cross-lingual pretrained models in regional language applications,offering a scalable and effective framework for enhancing online safety across Arabic-speaking communities.
基金supported by the Deanship of Scientific Research at King Khalid University through Small Groups funding(Project Grant No.RGP1/243/45)The funding was awarded to Dr.Mohammed Abker.And Natural Science Foundation of China under Grant 61901388.
文摘Arabic Dialect Identification(DID)is a task in Natural Language Processing(NLP)that involves determining the dialect of a given piece of text in Arabic.The state-of-the-art solutions for DID are built on various deep neural networks that commonly learn the representation of sentences in response to a given dialect.Despite the effectiveness of these solutions,the performance heavily relies on the amount of labeled examples,which is labor-intensive to atain and may not be readily available in real-world scenarios.To alleviate the burden of labeling data,this paper introduces a novel solution that leverages unlabeled corpora to boost performance on the DID task.Specifically,we design an architecture that enables learning the shared information between labeled and unlabeled texts through a gradient reversal layer.The key idea is to penalize the model for learning source dataset specific features and thus enable it to capture common knowledge regardless of the label.Finally,we evaluate the proposed solution on benchmark datasets for DID.Our extensive experiments show that it performs signifcantly better,especially,with sparse labeled data.By comparing our approach with existing Pre-trained Language Models(PLMs),we achieve a new state-of-the-art performance in the DID field.The code will be available on GitHub upon the paper's acceptance.
基金supported by Research Projects of the Nature Science Foundation of Hebei Province(F2021402005).
文摘Semi-supervised new intent discovery is a significant research focus in natural language understanding.To address the limitations of current semi-supervised training data and the underutilization of implicit information,a Semi-supervised New Intent Discovery for Elastic Neighborhood Syntactic Elimination and Fusion model(SNID-ENSEF)is proposed.Syntactic elimination contrast learning leverages verb-dominant syntactic features,systematically replacing specific words to enhance data diversity.The radius of the positive sample neighborhood is elastically adjusted to eliminate invalid samples and improve training efficiency.A neighborhood sample fusion strategy,based on sample distribution patterns,dynamically adjusts neighborhood size and fuses sample vectors to reduce noise and improve implicit information utilization and discovery accuracy.Experimental results show that SNID-ENSEF achieves average improvements of 0.88%,1.27%,and 1.30%in Normalized Mutual Information(NMI),Accuracy(ACC),and Adjusted Rand Index(ARI),respectively,outperforming PTJN,DPN,MTP-CLNN,and DWG models on the Banking77,StackOverflow,and Clinc150 datasets.The code is available at https://github.com/qsdesz/SNID-ENSEF,accessed on 16 January 2025.
文摘Emotion Recognition in Conversations(ERC)is fundamental in creating emotionally intelligentmachines.Graph-BasedNetwork(GBN)models have gained popularity in detecting conversational contexts for ERC tasks.However,their limited ability to collect and acquire contextual information hinders their effectiveness.We propose a Text Augmentation-based computational model for recognizing emotions using transformers(TA-MERT)to address this.The proposed model uses the Multimodal Emotion Lines Dataset(MELD),which ensures a balanced representation for recognizing human emotions.Themodel used text augmentation techniques to producemore training data,improving the proposed model’s accuracy.Transformer encoders train the deep neural network(DNN)model,especially Bidirectional Encoder(BE)representations that capture both forward and backward contextual information.This integration improves the accuracy and robustness of the proposed model.Furthermore,we present a method for balancing the training dataset by creating enhanced samples from the original dataset.By balancing the dataset across all emotion categories,we can lessen the adverse effects of data imbalance on the accuracy of the proposed model.Experimental results on the MELD dataset show that TA-MERT outperforms earlier methods,achieving a weighted F1 score of 62.60%and an accuracy of 64.36%.Overall,the proposed TA-MERT model solves the GBN models’weaknesses in obtaining contextual data for ERC.TA-MERT model recognizes human emotions more accurately by employing text augmentation and transformer-based encoding.The balanced dataset and the additional training samples also enhance its resilience.These findings highlight the significance of transformer-based approaches for special emotion recognition in conversations.
文摘识别服装质量抽检通告中的实体信息,对于评估不同区域的服装质量状况以及制定宏观政策具有重要意义。针对质量抽检通告命名实体识别存在的长文本序列信息丢失、小类样本特征学习不全等问题,以注意力机制为核心,提出了基于BERT(bidirectional encoder representations from transformers)和TENER(transformer encoder for NER)模型的领域命名实体识别模型。BERT-TENER模型通过预训练模型BERT获得字符的动态字向量;将字向量输入TENER模块中,基于注意力机制使得同样的字符拥有不同的学习过程,基于改进的Transformer模型进一步捕捉字符与字符之间的距离和方向信息,增强模型对不同长度、小类别文本内容的理解,并采用条件随机场模型获得每个字符对应的实体标签。在领域数据集上,BERT-TENER模型针对服装抽检领域的实体识别F_1达到92.45%,相较传统方法有效提升了命名实体识别率,并且在长文本以及非均衡的实体类别中也表现出较好的性能。
文摘首先利用bidirectional encoder representations from transformers(BERT)模型的强大的语境理解能力来提取数据法律文本的深层语义特征,然后引入细粒度特征提取层,依照注意力机制,重点关注文本中与数据法律问答相关的关键部分,最后对所采集的法律问答数据集进行训练和评估.结果显示:与传统的多个单一模型相比,所提出的模型在准确度、精确度、召回率、F1分数等关键性能指标上均有提升,表明该系统能够更有效地理解和回应复杂的数据法学问题,为研究数据法学的专业人士和公众用户提供更高质量的问答服务.
基金This research was funded by National Natural Science Foundation of China under Grant No.61806171Sichuan University of Science&Engineering Talent Project under Grant No.2021RC15+2 种基金Open Fund Project of Key Laboratory for Non-Destructive Testing and Engineering Computer of Sichuan Province Universities on Bridge Inspection and Engineering under Grant No.2022QYJ06Sichuan University of Science&Engineering Graduate Student Innovation Fund under Grant No.Y2023115The Scientific Research and Innovation Team Program of Sichuan University of Science and Technology under Grant No.SUSE652A006.
文摘While encryption technology safeguards the security of network communications,malicious traffic also uses encryption protocols to obscure its malicious behavior.To address the issues of traditional machine learning methods relying on expert experience and the insufficient representation capabilities of existing deep learning methods for encrypted malicious traffic,we propose an encrypted malicious traffic classification method that integrates global semantic features with local spatiotemporal features,called BERT-based Spatio-Temporal Features Network(BSTFNet).At the packet-level granularity,the model captures the global semantic features of packets through the attention mechanism of the Bidirectional Encoder Representations from Transformers(BERT)model.At the byte-level granularity,we initially employ the Bidirectional Gated Recurrent Unit(BiGRU)model to extract temporal features from bytes,followed by the utilization of the Text Convolutional Neural Network(TextCNN)model with multi-sized convolution kernels to extract local multi-receptive field spatial features.The fusion of features from both granularities serves as the ultimate multidimensional representation of malicious traffic.Our approach achieves accuracy and F1-score of 99.39%and 99.40%,respectively,on the publicly available USTC-TFC2016 dataset,and effectively reduces sample confusion within the Neris and Virut categories.The experimental results demonstrate that our method has outstanding representation and classification capabilities for encrypted malicious traffic.
文摘The rapid expansion of online content and big data has precipitated an urgent need for efficient summarization techniques to swiftly comprehend vast textual documents without compromising their original integrity.Current approaches in Extractive Text Summarization(ETS)leverage the modeling of inter-sentence relationships,a task of paramount importance in producing coherent summaries.This study introduces an innovative model that integrates Graph Attention Networks(GATs)with Transformer-based Bidirectional Encoder Representa-tions from Transformers(BERT)and Latent Dirichlet Allocation(LDA),further enhanced by Term Frequency-Inverse Document Frequency(TF-IDF)values,to improve sentence selection by capturing comprehensive topical information.Our approach constructs a graph with nodes representing sentences,words,and topics,thereby elevating the interconnectivity and enabling a more refined understanding of text structures.This model is stretched to Multi-Document Summarization(MDS)from Single-Document Summarization,offering significant improvements over existing models such as THGS-GMM and Topic-GraphSum,as demonstrated by empirical evaluations on benchmark news datasets like Cable News Network(CNN)/Daily Mail(DM)and Multi-News.The results consistently demonstrate superior performance,showcasing the model’s robustness in handling complex summarization tasks across single and multi-document contexts.This research not only advances the integration of BERT and LDA within a GATs but also emphasizes our model’s capacity to effectively manage global information and adapt to diverse summarization challenges.
文摘Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requires more syntactic elements.Most existing strategies focus on the general semantics of a conversation without involving the context of the sentence,recognizing the progress and comparing impacts.An ensemble pre-trained language model was taken up here to classify the conversation sentences from the conversation corpus.The conversational sentences are classified into four categories:information,question,directive,and commission.These classification label sequences are for analyzing the conversation progress and predicting the pecking order of the conversation.Ensemble of Bidirectional Encoder for Representation of Transformer(BERT),Robustly Optimized BERT pretraining Approach(RoBERTa),Generative Pre-Trained Transformer(GPT),DistilBERT and Generalized Autoregressive Pretraining for Language Understanding(XLNet)models are trained on conversation corpus with hyperparameters.Hyperparameter tuning approach is carried out for better performance on sentence classification.This Ensemble of Pre-trained Language Models with a Hyperparameter Tuning(EPLM-HT)system is trained on an annotated conversation dataset.The proposed approach outperformed compared to the base BERT,GPT,DistilBERT and XLNet transformer models.The proposed ensemble model with the fine-tuned parameters achieved an F1_score of 0.88.
文摘多项选择作为机器阅读理解中的一项重要任务,在自然语言处理(natural language processing,NLP)领域受到了广泛关注。由于数据中需要处理的文本长度不断增长,长文本多项选择成为了一项新的挑战。然而,现有的长文本处理方法容易丢失文本中的有效信息,导致结果不准确。针对上述问题,提出了一种基于压缩与推理的长文本多项选择答题方法(Long Text Multiple Choice Answer Method Based on Compression and Reasoning,LTMCA),通过训练评判模型识别相关句子,将相关句拼接成短文本输入到推理模型进行推理。为了提高评判模型的精度,在评判模型中增加了文章与选项之间的交互以补充文章对选项的注意力,有针对性地进行相关语句识别,更加准确地完成多项选择答题任务。在本文构建的CLTMCA中文长文本多项选择数据集上进行了实验验证,结果表明本文方法能够有效地解决BERT在处理长文本多项选择任务时的限制问题,相比于其他方法,在各项评价指标上均取得了较高的提升。
基金This work was supported in part by the National Natural Science Foundation of China under Grants U1836106 and 81961138010in part by the Beijing Natural Science Foundation under Grants M21032 and 19L2029+2 种基金in part by the Beijing Intelligent Logistics System Collaborative Innovation Center under Grant BILSCIC-2019KF-08in part by the Scientific and Technological Innovation Foundation of Shunde Graduate School,USTB,under Grants BK20BF010 and BK19BF006in part by the Fundamental Research Funds for the University of Science and Technology Beijing under Grant FRF-BD-19-012A.
文摘In the era of big data,E-commerce plays an increasingly important role,and steel E-commerce certainly occupies a positive position.However,it is very difficult to choose satisfactory steel raw materials from diverse steel commodities online on steel E-commerce platforms in the purchase of staffs.In order to improve the efficiency of purchasers searching for commodities on the steel E-commerce platforms,we propose a novel deep learning-based loss function for named entity recognition(NER).Considering the impacts of small sample and imbalanced data,in our NER scheme,the focal loss,the label smoothing,and the cross entropy are incorporated into a lite bidirectional encoder representations from transformers(BERT)model to avoid the over-fitting.Moreover,through the analysis of different classic annotation techniques used to tag data,an ideal one is chosen for the training model in our proposed scheme.Experiments are conducted on Chinese steel E-commerce datasets.The experimental results show that the training time of a lite BERT(ALBERT)-based method is much shorter than that of BERT-based models,while achieving the similar computational performance in terms of metrics precision,recall,and F1 with BERT-based models.Meanwhile,our proposed approach performs much better than that of combining Word2Vec,bidirectional long short-term memory(Bi-LSTM),and conditional random field(CRF)models,in consideration of training time and F1.
