Text format information is full of most of the resources of Internet,which puts forward higher and higher requirements for the accuracy of text classification.Therefore,in this manuscript,firstly,we design a hybrid mo...Text format information is full of most of the resources of Internet,which puts forward higher and higher requirements for the accuracy of text classification.Therefore,in this manuscript,firstly,we design a hybrid model of bidirectional encoder representation from transformers-hierarchical attention networks-dilated convolutions networks(BERT_HAN_DCN)which based on BERT pre-trained model with superior ability of extracting characteristic.The advantages of HAN model and DCN model are taken into account which can help gain abundant semantic information,fusing context semantic features and hierarchical characteristics.Secondly,the traditional softmax algorithm increases the learning difficulty of the same kind of samples,making it more difficult to distinguish similar features.Based on this,AM-softmax is introduced to replace the traditional softmax.Finally,the fused model is validated,which shows superior performance in the accuracy rate and F1-score of this hybrid model on two datasets and the experimental analysis shows the general single models such as HAN,DCN,based on BERT pre-trained model.Besides,the improved AM-softmax network model is superior to the general softmax network model.展开更多
Text extraction from images using the traditional techniques of image collecting,and pattern recognition using machine learning consume time due to the amount of extracted features from the images.Deep Neural Networks...Text extraction from images using the traditional techniques of image collecting,and pattern recognition using machine learning consume time due to the amount of extracted features from the images.Deep Neural Networks introduce effective solutions to extract text features from images using a few techniques and the ability to train large datasets of images with significant results.This study proposes using Dual Maxpooling and concatenating convolution Neural Networks(CNN)layers with the activation functions Relu and the Optimized Leaky Relu(OLRelu).The proposed method works by dividing the word image into slices that contain characters.Then pass them to deep learning layers to extract feature maps and reform the predicted words.Bidirectional Short Memory(BiLSTM)layers extractmore compelling features and link the time sequence fromforward and backward directions during the training phase.The Connectionist Temporal Classification(CTC)function calcifies the training and validation loss rates.In addition to decoding the extracted feature to reform characters again and linking them according to their time sequence.The proposed model performance is evaluated using training and validation loss errors on the Mjsynth and Integrated Argument Mining Tasks(IAM)datasets.The result of IAM was 2.09%for the average loss errors with the proposed dualMaxpooling and OLRelu.In the Mjsynth dataset,the best validation loss rate shrunk to 2.2%by applying concatenating CNN layers,and Relu.展开更多
针对畜禽疫病文本语料匮乏、文本内包含大量疫病名称及短语等未登录词问题,提出了一种结合词典匹配的BERT-BiLSTM-CRF畜禽疫病文本分词模型。以羊疫病为研究对象,构建了常见疫病文本数据集,将其与通用语料PKU结合,利用BERT(Bidirectiona...针对畜禽疫病文本语料匮乏、文本内包含大量疫病名称及短语等未登录词问题,提出了一种结合词典匹配的BERT-BiLSTM-CRF畜禽疫病文本分词模型。以羊疫病为研究对象,构建了常见疫病文本数据集,将其与通用语料PKU结合,利用BERT(Bidirectional encoder representation from transformers)预训练语言模型进行文本向量化表示;通过双向长短时记忆网络(Bidirectional long short-term memory network,BiLSTM)获取上下文语义特征;由条件随机场(Conditional random field,CRF)输出全局最优标签序列。基于此,在CRF层后加入畜禽疫病领域词典进行分词匹配修正,减少在分词过程中出现的疫病名称及短语等造成的歧义切分,进一步提高了分词准确率。实验结果表明,结合词典匹配的BERT-BiLSTM-CRF模型在羊常见疫病文本数据集上的F1值为96.38%,与jieba分词器、BiLSTM-Softmax模型、BiLSTM-CRF模型、未结合词典匹配的本文模型相比,分别提升11.01、10.62、8.3、0.72个百分点,验证了方法的有效性。与单一语料相比,通用语料PKU和羊常见疫病文本数据集结合的混合语料,能够同时对畜禽疫病专业术语及疫病文本中常用词进行准确切分,在通用语料及疫病文本数据集上F1值都达到95%以上,具有较好的模型泛化能力。该方法可用于畜禽疫病文本分词。展开更多
当前大语言模型的兴起为自然语言处理、搜索引擎、生命科学研究等领域的研究者提供了新思路,但大语言模型存在资源消耗高、推理速度慢,难以在工业场景尤其是垂直领域应用等方面的缺点。针对这一问题,提出了一种多尺度卷积神经网络(convo...当前大语言模型的兴起为自然语言处理、搜索引擎、生命科学研究等领域的研究者提供了新思路,但大语言模型存在资源消耗高、推理速度慢,难以在工业场景尤其是垂直领域应用等方面的缺点。针对这一问题,提出了一种多尺度卷积神经网络(convolutional neural network,CNN)与双向长短期记忆神经网络(long short term memory,LSTM)融合的唐卡问句分类模型,本文模型将数据的全局特征与局部特征进行融合实现唐卡问句分类任务,全局特征反映数据的本质特点,局部特征关注数据中易被忽视的部分,将二者以拼接的方式融合以丰富句子的特征表示。通过在Thangka数据集与THUCNews数据集上进行实验,结果表明,本文模型相较于Bert模型在精确度上略优,在训练时间上缩短了1/20,运算推理时间缩短了1/3。在公开数据集上的实验表明,本文模型在文本分类任务上也表现出了较好的适用性和有效性。展开更多
针对商品包装文本检测任务中弯曲密集型文本导致的错检、漏检问题,提出了一种由2个子网络组成的基于链接关系预测的文本检测框架(text detection network based on relational prediction,RPTNet)。在文本组件检测网络中,下采样采用卷...针对商品包装文本检测任务中弯曲密集型文本导致的错检、漏检问题,提出了一种由2个子网络组成的基于链接关系预测的文本检测框架(text detection network based on relational prediction,RPTNet)。在文本组件检测网络中,下采样采用卷积神经网络和自注意力并行的双分支结构提取局部和全局特征,并加入空洞特征增强模块(DFM)减少深层特征图在降维过程中信息的丢失;上采样采用特征金字塔与多级注意力融合模块(MAFM)相结合的方式进行多级特征融合以增强文本特征间的潜在联系,通过文本检测器从上采样输出的特征图中检测文本组件;在链接关系预测网络中,采用基于图卷积网络的关系推理框架预测文本组件间的深层相似度,采用双向长短时记忆网络将文本组件聚合为文本实例。为验证RRNet的检测性能,构建了一个由商品包装图片组成的文本检测数据集(text detection dataset composed of commodity packaging,CPTD1500)。实验结果表明:RPTNet不仅在公开文本数据集CTW-1500和Total-Text上取得了优异的性能,而且在CPTD1500数据集上的召回率和F值分别达到了85.4%和87.5%,均优于当前主流算法。展开更多
为实现英文文本标题的自动化生成,研究一套基于长短期记忆网络的句子级LSTM编码策略,并在标题生成模型中引入注意力机制来获取英文文本的上下文向量,保留文本中的重要信息。在此基础上,通过负对数似然函数来对模型加以训练。最后通过Byt...为实现英文文本标题的自动化生成,研究一套基于长短期记忆网络的句子级LSTM编码策略,并在标题生成模型中引入注意力机制来获取英文文本的上下文向量,保留文本中的重要信息。在此基础上,通过负对数似然函数来对模型加以训练。最后通过Byte Cup 2018数据集对本文提出的英语标题自动生成算法进行实验,并通过过ROUGE-N指标对标题生成质量加以评价。实验研究发现,所提出的句子级LSTM编码方案在英文文本标题生成准确性方面相比于其他常规摘要生成模型来说具有显著优势。展开更多
安全是民航业的核心主题。针对目前民航非计划事件分析严重依赖专家经验及分析效率低下的问题,文章提出一种结合Word2vec和双向长短期记忆(bidirectional long short-term memory,BiLSTM)神经网络模型的民航非计划事件分析方法。首先采...安全是民航业的核心主题。针对目前民航非计划事件分析严重依赖专家经验及分析效率低下的问题,文章提出一种结合Word2vec和双向长短期记忆(bidirectional long short-term memory,BiLSTM)神经网络模型的民航非计划事件分析方法。首先采用Word2vec模型针对事件文本语料进行词向量训练,缩小空间向量维度;然后通过BiLSTM模型自动提取特征,获取事件文本的完整序列信息和上下文特征向量;最后采用softmax函数对民航非计划事件进行分类。实验结果表明,所提出的方法分类效果更好,能达到更优的准确率和F 1值,对不平衡数据样本同样具有较稳定的分类性能,证明了该方法在民航非计划事件分析上的适用性和有效性。展开更多
针对景区手写诗词存在背景纹理复杂、字体尺寸及风格多样等特点导致景区游客难以识别手写诗词的问题,首先,分析研究景区手写诗词的识别场景,设计景区诗词检测网络(detection of poetry in scenic areas-network,DPSA-Net)以提取景区手...针对景区手写诗词存在背景纹理复杂、字体尺寸及风格多样等特点导致景区游客难以识别手写诗词的问题,首先,分析研究景区手写诗词的识别场景,设计景区诗词检测网络(detection of poetry in scenic areas-network,DPSA-Net)以提取景区手写诗词不同尺度的特征,并结合手写诗词字符间的链接依赖关系实现景区手写诗词检测;其次,设计了卷积循环聚合网络(convolution recurrent aggregation network,CRA-Net)以对景区手写诗词进行识别,结合卷积神经网络(convolutional neural networks,CNN)和双向长短期记忆网络提取手写诗词图像的序列特征,并通过聚合交叉熵(aggregation cross-entropy,ACE)实现特征向文本的转换;最后,结合景区知识图谱对CRA-Net的输出进行校正,进而提高景区手写诗词的识别准确率。实验结果表明,通过景区手写诗词矫正技术对CRA-Net的识别结果矫正后,识别准确率达到了79.04%,同时,该技术具有较好的抗干扰能力和良好的应用前景。展开更多
基金Fundamental Research Funds for the Central University,China(No.2232018D3-17)。
文摘Text format information is full of most of the resources of Internet,which puts forward higher and higher requirements for the accuracy of text classification.Therefore,in this manuscript,firstly,we design a hybrid model of bidirectional encoder representation from transformers-hierarchical attention networks-dilated convolutions networks(BERT_HAN_DCN)which based on BERT pre-trained model with superior ability of extracting characteristic.The advantages of HAN model and DCN model are taken into account which can help gain abundant semantic information,fusing context semantic features and hierarchical characteristics.Secondly,the traditional softmax algorithm increases the learning difficulty of the same kind of samples,making it more difficult to distinguish similar features.Based on this,AM-softmax is introduced to replace the traditional softmax.Finally,the fused model is validated,which shows superior performance in the accuracy rate and F1-score of this hybrid model on two datasets and the experimental analysis shows the general single models such as HAN,DCN,based on BERT pre-trained model.Besides,the improved AM-softmax network model is superior to the general softmax network model.
基金supported this project under the Fundamental Research Grant Scheme(FRGS)FRGS/1/2019/ICT02/UKM/02/9 entitled“Convolution Neural Network Enhancement Based on Adaptive Convexity and Regularization Functions for Fake Video Analytics”.This grant was received by Prof.Assis.Dr.S.N.H.Sheikh Abdullah,https://www.ukm.my/spifper/research_news/instrumentfunds.
文摘Text extraction from images using the traditional techniques of image collecting,and pattern recognition using machine learning consume time due to the amount of extracted features from the images.Deep Neural Networks introduce effective solutions to extract text features from images using a few techniques and the ability to train large datasets of images with significant results.This study proposes using Dual Maxpooling and concatenating convolution Neural Networks(CNN)layers with the activation functions Relu and the Optimized Leaky Relu(OLRelu).The proposed method works by dividing the word image into slices that contain characters.Then pass them to deep learning layers to extract feature maps and reform the predicted words.Bidirectional Short Memory(BiLSTM)layers extractmore compelling features and link the time sequence fromforward and backward directions during the training phase.The Connectionist Temporal Classification(CTC)function calcifies the training and validation loss rates.In addition to decoding the extracted feature to reform characters again and linking them according to their time sequence.The proposed model performance is evaluated using training and validation loss errors on the Mjsynth and Integrated Argument Mining Tasks(IAM)datasets.The result of IAM was 2.09%for the average loss errors with the proposed dualMaxpooling and OLRelu.In the Mjsynth dataset,the best validation loss rate shrunk to 2.2%by applying concatenating CNN layers,and Relu.
文摘针对畜禽疫病文本语料匮乏、文本内包含大量疫病名称及短语等未登录词问题,提出了一种结合词典匹配的BERT-BiLSTM-CRF畜禽疫病文本分词模型。以羊疫病为研究对象,构建了常见疫病文本数据集,将其与通用语料PKU结合,利用BERT(Bidirectional encoder representation from transformers)预训练语言模型进行文本向量化表示;通过双向长短时记忆网络(Bidirectional long short-term memory network,BiLSTM)获取上下文语义特征;由条件随机场(Conditional random field,CRF)输出全局最优标签序列。基于此,在CRF层后加入畜禽疫病领域词典进行分词匹配修正,减少在分词过程中出现的疫病名称及短语等造成的歧义切分,进一步提高了分词准确率。实验结果表明,结合词典匹配的BERT-BiLSTM-CRF模型在羊常见疫病文本数据集上的F1值为96.38%,与jieba分词器、BiLSTM-Softmax模型、BiLSTM-CRF模型、未结合词典匹配的本文模型相比,分别提升11.01、10.62、8.3、0.72个百分点,验证了方法的有效性。与单一语料相比,通用语料PKU和羊常见疫病文本数据集结合的混合语料,能够同时对畜禽疫病专业术语及疫病文本中常用词进行准确切分,在通用语料及疫病文本数据集上F1值都达到95%以上,具有较好的模型泛化能力。该方法可用于畜禽疫病文本分词。
文摘当前大语言模型的兴起为自然语言处理、搜索引擎、生命科学研究等领域的研究者提供了新思路,但大语言模型存在资源消耗高、推理速度慢,难以在工业场景尤其是垂直领域应用等方面的缺点。针对这一问题,提出了一种多尺度卷积神经网络(convolutional neural network,CNN)与双向长短期记忆神经网络(long short term memory,LSTM)融合的唐卡问句分类模型,本文模型将数据的全局特征与局部特征进行融合实现唐卡问句分类任务,全局特征反映数据的本质特点,局部特征关注数据中易被忽视的部分,将二者以拼接的方式融合以丰富句子的特征表示。通过在Thangka数据集与THUCNews数据集上进行实验,结果表明,本文模型相较于Bert模型在精确度上略优,在训练时间上缩短了1/20,运算推理时间缩短了1/3。在公开数据集上的实验表明,本文模型在文本分类任务上也表现出了较好的适用性和有效性。
文摘针对商品包装文本检测任务中弯曲密集型文本导致的错检、漏检问题,提出了一种由2个子网络组成的基于链接关系预测的文本检测框架(text detection network based on relational prediction,RPTNet)。在文本组件检测网络中,下采样采用卷积神经网络和自注意力并行的双分支结构提取局部和全局特征,并加入空洞特征增强模块(DFM)减少深层特征图在降维过程中信息的丢失;上采样采用特征金字塔与多级注意力融合模块(MAFM)相结合的方式进行多级特征融合以增强文本特征间的潜在联系,通过文本检测器从上采样输出的特征图中检测文本组件;在链接关系预测网络中,采用基于图卷积网络的关系推理框架预测文本组件间的深层相似度,采用双向长短时记忆网络将文本组件聚合为文本实例。为验证RRNet的检测性能,构建了一个由商品包装图片组成的文本检测数据集(text detection dataset composed of commodity packaging,CPTD1500)。实验结果表明:RPTNet不仅在公开文本数据集CTW-1500和Total-Text上取得了优异的性能,而且在CPTD1500数据集上的召回率和F值分别达到了85.4%和87.5%,均优于当前主流算法。
文摘为实现英文文本标题的自动化生成,研究一套基于长短期记忆网络的句子级LSTM编码策略,并在标题生成模型中引入注意力机制来获取英文文本的上下文向量,保留文本中的重要信息。在此基础上,通过负对数似然函数来对模型加以训练。最后通过Byte Cup 2018数据集对本文提出的英语标题自动生成算法进行实验,并通过过ROUGE-N指标对标题生成质量加以评价。实验研究发现,所提出的句子级LSTM编码方案在英文文本标题生成准确性方面相比于其他常规摘要生成模型来说具有显著优势。
文摘安全是民航业的核心主题。针对目前民航非计划事件分析严重依赖专家经验及分析效率低下的问题,文章提出一种结合Word2vec和双向长短期记忆(bidirectional long short-term memory,BiLSTM)神经网络模型的民航非计划事件分析方法。首先采用Word2vec模型针对事件文本语料进行词向量训练,缩小空间向量维度;然后通过BiLSTM模型自动提取特征,获取事件文本的完整序列信息和上下文特征向量;最后采用softmax函数对民航非计划事件进行分类。实验结果表明,所提出的方法分类效果更好,能达到更优的准确率和F 1值,对不平衡数据样本同样具有较稳定的分类性能,证明了该方法在民航非计划事件分析上的适用性和有效性。
