针对农业领域文本信息密度大、语义模糊、特征稀疏的特点,提出一种基于MacBERT(MLM as correction-BERT)、深度金字塔卷积网络(DPCNN)和注意力机制(Attention)的农业文本分类模型,命名为MacBERT—DPCNN—Attention(MDA)。首先,使用MacB...针对农业领域文本信息密度大、语义模糊、特征稀疏的特点,提出一种基于MacBERT(MLM as correction-BERT)、深度金字塔卷积网络(DPCNN)和注意力机制(Attention)的农业文本分类模型,命名为MacBERT—DPCNN—Attention(MDA)。首先,使用MacBERT模型充分提取农业类文本内容的上下文信息,强化文本的语义特征表示。然后,DPCNN模型通过其多层卷积神经网络和池化操作,有效捕获文本的局部特征。最后,注意力机制进一步增强农业文本序列的特征表达。结果表明,与其他主流模型如BERT—DPCNN、BERT—CNN、BERT—RNN相比,MDA模型在农业文本分类任务上的精确率提升1.04%以上,召回率提升0.95%以上,F1值提升0.14%以上。表明所提模型在解决农业领域文本分类问题方面的有效性和优越性。展开更多
针对农业新闻目前面临的针对性差、分类不清和数据集缺乏等问题,提出一种基于ERNIE(Enhanced Representation through kNowledge IntEgration)、深度金字塔卷积神经网络(DPCNN)和双向门控循环单元(BiGRU)的农业新闻分类模型——EGC。首...针对农业新闻目前面临的针对性差、分类不清和数据集缺乏等问题,提出一种基于ERNIE(Enhanced Representation through kNowledge IntEgration)、深度金字塔卷积神经网络(DPCNN)和双向门控循环单元(BiGRU)的农业新闻分类模型——EGC。首先利用ERNIE对数据集进行编码,然后利用改进后的DPCNN和BiGRU同时提取新闻文本的特征,再将两者提取的特征进行拼合并经过Softmax得到最终结果。为了使EGC模型适用于农业新闻分类领域,对DPCNN进行改进,减少它的卷积层以保留更多特征。实验结果表明,与ERNIE相比,EGC模型的精确率、召回率和F1分数别提升了1.47、1.29和1.42个百分点,优于传统分类模型。展开更多
Rapid and accurate identification of high-quality patents can accelerate the transformation process of scientific and technological achievements, optimize the management of intellectual property rights and enhance the...Rapid and accurate identification of high-quality patents can accelerate the transformation process of scientific and technological achievements, optimize the management of intellectual property rights and enhance the vitality of innovation. Aiming at the shortcomings of the traditional high-value patent assessment method, which is relatively simple and seldom considers the influence of patentees, this paper proposes a high-quality patent method HMFM (High-Value Patent Multi-Feature Fusion Method) that fuses multi-dimensional features. A weighted node importance assessment method in complex network called GLE (Glob-Local-struEntropy) based on improved structural entropy is designed to calculate the influence of the patentee to form the patentee’s features, and the patent text features are extracted by BERT-DPCNN deep learning model, which is supplemented to the basic patent indicator system. Finally a machine learning algorithm is used to assess the value of patents. Experiment results show that our method can identify high-value patents more effectively and accurately.展开更多
文摘针对农业领域文本信息密度大、语义模糊、特征稀疏的特点,提出一种基于MacBERT(MLM as correction-BERT)、深度金字塔卷积网络(DPCNN)和注意力机制(Attention)的农业文本分类模型,命名为MacBERT—DPCNN—Attention(MDA)。首先,使用MacBERT模型充分提取农业类文本内容的上下文信息,强化文本的语义特征表示。然后,DPCNN模型通过其多层卷积神经网络和池化操作,有效捕获文本的局部特征。最后,注意力机制进一步增强农业文本序列的特征表达。结果表明,与其他主流模型如BERT—DPCNN、BERT—CNN、BERT—RNN相比,MDA模型在农业文本分类任务上的精确率提升1.04%以上,召回率提升0.95%以上,F1值提升0.14%以上。表明所提模型在解决农业领域文本分类问题方面的有效性和优越性。
文摘针对农业新闻目前面临的针对性差、分类不清和数据集缺乏等问题,提出一种基于ERNIE(Enhanced Representation through kNowledge IntEgration)、深度金字塔卷积神经网络(DPCNN)和双向门控循环单元(BiGRU)的农业新闻分类模型——EGC。首先利用ERNIE对数据集进行编码,然后利用改进后的DPCNN和BiGRU同时提取新闻文本的特征,再将两者提取的特征进行拼合并经过Softmax得到最终结果。为了使EGC模型适用于农业新闻分类领域,对DPCNN进行改进,减少它的卷积层以保留更多特征。实验结果表明,与ERNIE相比,EGC模型的精确率、召回率和F1分数别提升了1.47、1.29和1.42个百分点,优于传统分类模型。
文摘Rapid and accurate identification of high-quality patents can accelerate the transformation process of scientific and technological achievements, optimize the management of intellectual property rights and enhance the vitality of innovation. Aiming at the shortcomings of the traditional high-value patent assessment method, which is relatively simple and seldom considers the influence of patentees, this paper proposes a high-quality patent method HMFM (High-Value Patent Multi-Feature Fusion Method) that fuses multi-dimensional features. A weighted node importance assessment method in complex network called GLE (Glob-Local-struEntropy) based on improved structural entropy is designed to calculate the influence of the patentee to form the patentee’s features, and the patent text features are extracted by BERT-DPCNN deep learning model, which is supplemented to the basic patent indicator system. Finally a machine learning algorithm is used to assess the value of patents. Experiment results show that our method can identify high-value patents more effectively and accurately.
