Recurrent neural network language models (RNNLMs) have been applied in a wide range of research fields, including nature language processing and speech recognition. One challenge in training RNNLMs is the heavy comput...Recurrent neural network language models (RNNLMs) have been applied in a wide range of research fields, including nature language processing and speech recognition. One challenge in training RNNLMs is the heavy computational cost of the crucial back-propagation (BP) algorithm. This paper presents an effective approach to train recurrent neural network on multiple GPUs, where parallelized stochastic gradient descent (SGD) is applied. Results on text-based experiments show that the proposed approach achieves 3.4× speedup on 4 GPUs than the single one, without any performance loss in language model perplexity.展开更多
In recent years,with the great success of pre-trained language models,the pre-trained BERT model has been gradually applied to the field of source code understanding.However,the time cost of training a language model ...In recent years,with the great success of pre-trained language models,the pre-trained BERT model has been gradually applied to the field of source code understanding.However,the time cost of training a language model from zero is very high,and how to transfer the pre-trained language model to the field of smart contract vulnerability detection is a hot research direction at present.In this paper,we propose a hybrid model to detect common vulnerabilities in smart contracts based on a lightweight pre-trained languagemodel BERT and connected to a bidirectional gate recurrent unitmodel.The downstream neural network adopts the bidirectional gate recurrent unit neural network model with a hierarchical attention mechanism to mine more semantic features contained in the source code of smart contracts by using their characteristics.Our experiments show that our proposed hybrid neural network model SolBERT-BiGRU-Attention is fitted by a large number of data samples with smart contract vulnerabilities,and it is found that compared with the existing methods,the accuracy of our model can reach 93.85%,and the Micro-F1 Score is 94.02%.展开更多
Research on Chinese Sign Language(CSL)provides convenience and support for individuals with hearing impairments to communicate and integrate into society.This article reviews the relevant literature on Chinese Sign La...Research on Chinese Sign Language(CSL)provides convenience and support for individuals with hearing impairments to communicate and integrate into society.This article reviews the relevant literature on Chinese Sign Language Recognition(CSLR)in the past 20 years.Hidden Markov Models(HMM),Support Vector Machines(SVM),and Dynamic Time Warping(DTW)were found to be the most commonly employed technologies among traditional identificationmethods.Benefiting from the rapid development of computer vision and artificial intelligence technology,Convolutional Neural Networks(CNN),3D-CNN,YOLO,Capsule Network(CapsNet)and various deep neural networks have sprung up.Deep Neural Networks(DNNs)and their derived models are integral tomodern artificial intelligence recognitionmethods.In addition,technologies thatwerewidely used in the early days have also been integrated and applied to specific hybrid models and customized identification methods.Sign language data collection includes acquiring data from data gloves,data sensors(such as Kinect,LeapMotion,etc.),and high-definition photography.Meanwhile,facial expression recognition,complex background processing,and 3D sign language recognition have also attracted research interests among scholars.Due to the uniqueness and complexity of Chinese sign language,accuracy,robustness,real-time performance,and user independence are significant challenges for future sign language recognition research.Additionally,suitable datasets and evaluation criteria are also worth pursuing.展开更多
Donggan language, which is a special variant of Mandarin, is used by Donggan people in Central Asia. Donggan language includes Gansu dialect and Shaanxi dialect. This paper proposes a convolutional neural network (CNN...Donggan language, which is a special variant of Mandarin, is used by Donggan people in Central Asia. Donggan language includes Gansu dialect and Shaanxi dialect. This paper proposes a convolutional neural network (CNN) based Donggan language speech recognition method for the Donggan Shaanxi dialect. A text corpus and a pronunciation dictionary were designed for of Donggan Shannxi dialect and the corresponding speech corpus was recorded. Then the acoustic models of Donggan Shaanxi dialect was trained by CNN. Experimental results demonstrate that the recognition rate of proposed CNNbased method achieves lower word error rate than that of the monophonic hidden Markov model (HMM) based method, triphone HMM-based method and DNN- based method.展开更多
针对关系抽取(RE)任务中实体关系语义挖掘困难和预测关系有偏差等问题,提出一种基于掩码提示与门控记忆网络校准(MGMNC)的RE方法。首先,利用提示中的掩码学习实体之间在预训练语言模型(PLM)语义空间中的潜在语义,通过构造掩码注意力权...针对关系抽取(RE)任务中实体关系语义挖掘困难和预测关系有偏差等问题,提出一种基于掩码提示与门控记忆网络校准(MGMNC)的RE方法。首先,利用提示中的掩码学习实体之间在预训练语言模型(PLM)语义空间中的潜在语义,通过构造掩码注意力权重矩阵,将离散的掩码语义空间相互关联;其次,采用门控校准网络将含有实体和关系语义的掩码表示融入句子的全局语义;再次,将它们作为关系提示校准关系信息,随后将句子表示的最终表示映射至相应的关系类别;最后,通过更好地利用提示中掩码,并结合传统微调方法的学习句子全局语义的优势,充分激发PLM的潜力。实验结果表明,所提方法在SemEval(SemEval-2010 Task 8)数据集的F1值达到91.4%,相较于RELA(Relation Extraction with Label Augmentation)生成式方法提高了1.0个百分点;在SciERC(Entities, Relations, and Coreference for Scientific knowledge graph construction)和CLTC(Chinese Literature Text Corpus)数据集上的F1值分别达到91.0%和82.8%。所提方法在上述3个数据集上均明显优于对比方法,验证了所提方法的有效性。相较于基于生成式的方法,所提方法实现了更优的抽取性能。展开更多
文摘Recurrent neural network language models (RNNLMs) have been applied in a wide range of research fields, including nature language processing and speech recognition. One challenge in training RNNLMs is the heavy computational cost of the crucial back-propagation (BP) algorithm. This paper presents an effective approach to train recurrent neural network on multiple GPUs, where parallelized stochastic gradient descent (SGD) is applied. Results on text-based experiments show that the proposed approach achieves 3.4× speedup on 4 GPUs than the single one, without any performance loss in language model perplexity.
基金supported by the National Natural Science Foundation of China(Grant Nos.62272120,62106030,U20B2046,62272119,61972105)the Technology Innovation and Application Development Projects of Chongqing(Grant Nos.cstc2021jscx-gksbX0032,cstc2021jscxgksbX0029).
文摘In recent years,with the great success of pre-trained language models,the pre-trained BERT model has been gradually applied to the field of source code understanding.However,the time cost of training a language model from zero is very high,and how to transfer the pre-trained language model to the field of smart contract vulnerability detection is a hot research direction at present.In this paper,we propose a hybrid model to detect common vulnerabilities in smart contracts based on a lightweight pre-trained languagemodel BERT and connected to a bidirectional gate recurrent unitmodel.The downstream neural network adopts the bidirectional gate recurrent unit neural network model with a hierarchical attention mechanism to mine more semantic features contained in the source code of smart contracts by using their characteristics.Our experiments show that our proposed hybrid neural network model SolBERT-BiGRU-Attention is fitted by a large number of data samples with smart contract vulnerabilities,and it is found that compared with the existing methods,the accuracy of our model can reach 93.85%,and the Micro-F1 Score is 94.02%.
基金supported by National Social Science Foundation Annual Project“Research on Evaluation and Improvement Paths of Integrated Development of Disabled Persons”(Grant No.20BRK029)the National Language Commission’s“14th Five-Year Plan”Scientific Research Plan 2023 Project“Domain Digital Language Service Resource Construction and Key Technology Research”(YB145-72)the National Philosophy and Social Sciences Foundation(Grant No.20BTQ065).
文摘Research on Chinese Sign Language(CSL)provides convenience and support for individuals with hearing impairments to communicate and integrate into society.This article reviews the relevant literature on Chinese Sign Language Recognition(CSLR)in the past 20 years.Hidden Markov Models(HMM),Support Vector Machines(SVM),and Dynamic Time Warping(DTW)were found to be the most commonly employed technologies among traditional identificationmethods.Benefiting from the rapid development of computer vision and artificial intelligence technology,Convolutional Neural Networks(CNN),3D-CNN,YOLO,Capsule Network(CapsNet)and various deep neural networks have sprung up.Deep Neural Networks(DNNs)and their derived models are integral tomodern artificial intelligence recognitionmethods.In addition,technologies thatwerewidely used in the early days have also been integrated and applied to specific hybrid models and customized identification methods.Sign language data collection includes acquiring data from data gloves,data sensors(such as Kinect,LeapMotion,etc.),and high-definition photography.Meanwhile,facial expression recognition,complex background processing,and 3D sign language recognition have also attracted research interests among scholars.Due to the uniqueness and complexity of Chinese sign language,accuracy,robustness,real-time performance,and user independence are significant challenges for future sign language recognition research.Additionally,suitable datasets and evaluation criteria are also worth pursuing.
文摘Donggan language, which is a special variant of Mandarin, is used by Donggan people in Central Asia. Donggan language includes Gansu dialect and Shaanxi dialect. This paper proposes a convolutional neural network (CNN) based Donggan language speech recognition method for the Donggan Shaanxi dialect. A text corpus and a pronunciation dictionary were designed for of Donggan Shannxi dialect and the corresponding speech corpus was recorded. Then the acoustic models of Donggan Shaanxi dialect was trained by CNN. Experimental results demonstrate that the recognition rate of proposed CNNbased method achieves lower word error rate than that of the monophonic hidden Markov model (HMM) based method, triphone HMM-based method and DNN- based method.
文摘针对关系抽取(RE)任务中实体关系语义挖掘困难和预测关系有偏差等问题,提出一种基于掩码提示与门控记忆网络校准(MGMNC)的RE方法。首先,利用提示中的掩码学习实体之间在预训练语言模型(PLM)语义空间中的潜在语义,通过构造掩码注意力权重矩阵,将离散的掩码语义空间相互关联;其次,采用门控校准网络将含有实体和关系语义的掩码表示融入句子的全局语义;再次,将它们作为关系提示校准关系信息,随后将句子表示的最终表示映射至相应的关系类别;最后,通过更好地利用提示中掩码,并结合传统微调方法的学习句子全局语义的优势,充分激发PLM的潜力。实验结果表明,所提方法在SemEval(SemEval-2010 Task 8)数据集的F1值达到91.4%,相较于RELA(Relation Extraction with Label Augmentation)生成式方法提高了1.0个百分点;在SciERC(Entities, Relations, and Coreference for Scientific knowledge graph construction)和CLTC(Chinese Literature Text Corpus)数据集上的F1值分别达到91.0%和82.8%。所提方法在上述3个数据集上均明显优于对比方法,验证了所提方法的有效性。相较于基于生成式的方法,所提方法实现了更优的抽取性能。
