传统编目分类和规则匹配方法存在工作效能低、过度依赖专家知识、缺乏对古籍文本自身语义的深层次挖掘、编目主题边界模糊、较难实现对古籍文本领域主题的精准推荐等问题。为此,本文结合古籍语料特征探究如何实现精准推荐符合研究者需...传统编目分类和规则匹配方法存在工作效能低、过度依赖专家知识、缺乏对古籍文本自身语义的深层次挖掘、编目主题边界模糊、较难实现对古籍文本领域主题的精准推荐等问题。为此,本文结合古籍语料特征探究如何实现精准推荐符合研究者需求的文本主题内容的方法,以推动数字人文研究的进一步发展。首先,选取本课题组前期标注的古籍语料数据进行主题类别标注和视图分类;其次,构建融合BERT(bidirectional encoder representation from transformers)预训练模型、改进卷积神经网络、循环神经网络和多头注意力机制的语义挖掘模型;最后,融入“主体-关系-客体”多视图的语义增强模型,构建DJ-TextRCNN(DianJi-recurrent convolutional neural networks for text classification)模型实现对典籍文本更细粒度、更深层次、更多维度的语义挖掘。研究结果发现,DJ-TextRCNN模型在不同视图下的古籍主题推荐任务的准确率均为最优。在“主体-关系-客体”视图下,精确率达到88.54%,初步实现了对古籍文本的精准主题推荐,对中华文化深层次、细粒度的语义挖掘具有一定的指导意义。展开更多
Document classification is widely applied in many scientific areas and academic environments, using NLP techniques and term extraction algorithms like CValue, TfIdf, TermEx, GlossEx, Weirdness and the others like. Nev...Document classification is widely applied in many scientific areas and academic environments, using NLP techniques and term extraction algorithms like CValue, TfIdf, TermEx, GlossEx, Weirdness and the others like. Nevertheless, they mainly have weaknesses in extracting most important terms when input text has not been rectified grammatically, or even has non-alphabetic methodical and math or chemical notations, and cross-domain inference of terms and phrases. In this paper, we propose a novel Text-Categorization and Term-Extraction method based on human-expert choice of classified categories. Papers are the training phase substances of the proposed algorithm. They have been already labeled with some scientific pre-defined field specific categories, by a human expert, especially one with high experiences and researches and surveys in the field. Our approach thereafter extracts (concept) terms of the labeled papers of each category and assigns all to the category. Categorization of test papers is then applied based on their extracted terms and further comparing with each category’s terms. Besides, our approach will produce semantic enabled outputs that are useful for many goals such as knowledge bases and data sets complement of the Linked Data cloud and for semantic querying of them by some languages such as SparQL. Besides, further finding classified papers’ gained topic or class will be easy by using URIs contained in the ontological outputs. The experimental results, comparing LPTC with five well-known term extraction algorithms by measuring precision and recall, show that categorization effectiveness can be achieved using our approach. In other words, the method LPTC is significantly superior to CValue, TfIdf, TermEx, GlossEx and Weirdness in the target study. As well, we conclude that higher number of papers for training, even higher precision we have.展开更多
文摘传统编目分类和规则匹配方法存在工作效能低、过度依赖专家知识、缺乏对古籍文本自身语义的深层次挖掘、编目主题边界模糊、较难实现对古籍文本领域主题的精准推荐等问题。为此,本文结合古籍语料特征探究如何实现精准推荐符合研究者需求的文本主题内容的方法,以推动数字人文研究的进一步发展。首先,选取本课题组前期标注的古籍语料数据进行主题类别标注和视图分类;其次,构建融合BERT(bidirectional encoder representation from transformers)预训练模型、改进卷积神经网络、循环神经网络和多头注意力机制的语义挖掘模型;最后,融入“主体-关系-客体”多视图的语义增强模型,构建DJ-TextRCNN(DianJi-recurrent convolutional neural networks for text classification)模型实现对典籍文本更细粒度、更深层次、更多维度的语义挖掘。研究结果发现,DJ-TextRCNN模型在不同视图下的古籍主题推荐任务的准确率均为最优。在“主体-关系-客体”视图下,精确率达到88.54%,初步实现了对古籍文本的精准主题推荐,对中华文化深层次、细粒度的语义挖掘具有一定的指导意义。
文摘Document classification is widely applied in many scientific areas and academic environments, using NLP techniques and term extraction algorithms like CValue, TfIdf, TermEx, GlossEx, Weirdness and the others like. Nevertheless, they mainly have weaknesses in extracting most important terms when input text has not been rectified grammatically, or even has non-alphabetic methodical and math or chemical notations, and cross-domain inference of terms and phrases. In this paper, we propose a novel Text-Categorization and Term-Extraction method based on human-expert choice of classified categories. Papers are the training phase substances of the proposed algorithm. They have been already labeled with some scientific pre-defined field specific categories, by a human expert, especially one with high experiences and researches and surveys in the field. Our approach thereafter extracts (concept) terms of the labeled papers of each category and assigns all to the category. Categorization of test papers is then applied based on their extracted terms and further comparing with each category’s terms. Besides, our approach will produce semantic enabled outputs that are useful for many goals such as knowledge bases and data sets complement of the Linked Data cloud and for semantic querying of them by some languages such as SparQL. Besides, further finding classified papers’ gained topic or class will be easy by using URIs contained in the ontological outputs. The experimental results, comparing LPTC with five well-known term extraction algorithms by measuring precision and recall, show that categorization effectiveness can be achieved using our approach. In other words, the method LPTC is significantly superior to CValue, TfIdf, TermEx, GlossEx and Weirdness in the target study. As well, we conclude that higher number of papers for training, even higher precision we have.
