首页 | 官方网站   微博 | 高级检索  
文章检索
  按 检索   检索词:      
出版年份:   被引次数:   他引次数: 提示:输入*表示无穷大
  收费全文   788篇
  免费   23篇
  国内免费   38篇
文化教育   849篇
  2023年   2篇
  2022年   10篇
  2021年   16篇
  2020年   29篇
  2019年   17篇
  2018年   15篇
  2017年   24篇
  2016年   24篇
  2015年   23篇
  2014年   36篇
  2013年   79篇
  2012年   59篇
  2011年   85篇
  2010年   47篇
  2009年   38篇
  2008年   49篇
  2007年   50篇
  2006年   40篇
  2005年   51篇
  2004年   32篇
  2003年   38篇
  2002年   37篇
  2001年   19篇
  2000年   15篇
  1999年   5篇
  1998年   4篇
  1997年   3篇
  1957年   2篇
排序方式: 共有849条查询结果,搜索用时 16 毫秒
1.
[目的/意义] 针对SAO结构短文本分类时面临的语义特征短缺和领域知识不足问题,提出一种融合语义联想和BERT的SAO分类方法,以期提高短文本分类效果。[方法/过程] 以图情领域SAO短文本为数据源,首先设计了一种包含"扩展-重构-降噪"三环节的语义联想方案,即通过语义扩展和SAO重构延展SAO语义信息,通过语义降噪解决扩展后的噪声干扰问题;然后利用BERT模型对语义联想后的SAO短文本进行训练;最后在分类部分实现自动分类。[结果/结论] 在分别对比了不同联想值、学习率和分类器后,实验结果表明当联想值为10、学习率为4e-5时SAO短文本分类效果达到最优,平均F1值为0.852 2,与SVM、LSTM和单纯的BERT相比,F1值分别提高了0.103 1、0.153 8和0.140 5。  相似文献   
2.
Bast fibres have been commonly used as a textile material in Northern Europe since Neolithic times. However, the process of identifying the different species has been problematic, and many important questions related to their cultural history are still unanswered. For example, a modified Herzog test and the presence of calcium oxalate crystals have both been used in identification. In order to generate more reliable results, further research and advancement in multi-methodological methods is required. This paper introduces a combination of methods which can be used to identify and distinguish flax (Linum usitatissimum), hemp (Cannabis sativa), and stinging nettle (Urtica dioica). The research material consisted of reference fibres and 25 fibre samples obtained from 12 textiles assumed to be made of nettle. The textiles were from the Finno-Ugric and Historical Collections of The National Museum of Finland. The fibre samples were studied by observing the surface characteristics and cross sections with transmitted light microscopy, and by using a modified Herzog test with polarized light, in order to identify the distinguishable features in their morphological structures. The study showed that five out of 25 samples were cotton, 16 nettle, one flax, and one hemp. Findings from two samples were inconsistent. The results show that it is possible to distinguish common north European bast fibres from each other by using a combination of microscopic methods. Furthermore, by utilizing these combined methods, new and more reliable information could be obtained from historical ethnographic textiles, which creates new vistas for the interpretation of their cultural history.  相似文献   
3.
[目的/意义]整合定性与定量的舆情研究视角,统一多模态研究对象,实现网络舆情信息受众的观点测度,可修复网络舆情分析与治理的理论与实践裂痕。[方法/过程]通过引入网络舆情场的概念,对网络舆情信息受众、受众观点测度的内涵进行诠释,就网络舆情场与信息受众观点测度的逻辑关系加以辩证讨论。[结果/结论]提出网络舆情场内舆情受众观点测度机理和具体测度路径,为后续网络舆情场中的网络舆情信息分析、多维度信息受众观点测度,受众认知规律发现,网络舆情监督和管控限制等层面的研究做相应铺垫。  相似文献   
4.
本文系统性地研究面向查询的观点摘要任务,旨在构建一种查询式观点摘要模型框架,探究不同的摘要方法对摘要效果的影响。通过综合考虑情感倾向与句子相似度,从待检文档中抽取出待摘要语句,再结合神经网络和词嵌入技术生成摘要,进而构建面向查询的观点摘要框架。从Debatepedia网站上爬取议题和论述内容构建观点摘要实验数据集,将本文方法应用到该数据集上,以检验不同模型的效果。实验结果表明,在该数据集上,仅使用基于抽取式的方法生成的观点摘要质量更高,取得了最高的平均ROUGE分数、深度语义相似度分数和情感分数,较生成式方法分别提高6.58%、1.79%和11.52%,而比组合式方法提高了8.33%、2.80%和13.86%;同时,本文提出的句子深度语义相似度和情感分数评估指标有助于更好地评估面向查询的观点摘要模型效果。研究结果对于提升面向查询的观点摘要效果,促进观点摘要模型在情报学领域的应用具有重要意义。  相似文献   
5.
从2002年起渥太华市档案馆一直致力于探索建立城市电子文件管理体系,为此渥太华市档案馆进行了一系列的工作,包括将各种形式的现行和非现行的文件管理与其档案价值联系起来,按照业务分类法对各类电子文件进行分类管理,依据宏观鉴定方法确定档案保管期限与处置方案,并通过在线联合目录的方式为政府和公众提供利用服务等。渥太华市档案馆基于文件连续体理念,正在探索多元主体协同的信息治理新方案。  相似文献   
6.
文章探究如何分类组织非物质文化遗产信息资源,以达到活态利用、传承和发展非物质文化遗产的目的。采用文献调研法和内容分析法,以传统体育、游艺与杂技类为例,一方面借鉴学界对非遗分类的研究成果以及分类法研究中相关类目的划分思路,从学科属性划分传统体育、游艺与杂技类非遗信息资源的二、三级类目;另一方面兼顾非遗数字采集规范,对传统体育、游艺与杂技类非遗国家级项目的信息描述进行分析与综合,构建类目复分表揭示该类非遗资源内容属性中所涉及的共性方面。从纵、横两个角度对传统体育、游艺与杂技类非遗信息资源进行分类组织,以期能够为非遗信息资源分类体系的构建提供可行的研究步骤和参考。  相似文献   
7.
ABSTRACT

As an important part of art and culture, ancient murals depict a variety of different artistic images, and these individual images have important research value. For research purposes, it is often important to first determine the type of objects represented in a painting. However, the mural painting environment makes datasets difficult to collect, and long-term exposure leads to underlying features that are not distinct, which makes this task challenging. This study proposes a convolutional neural network model based on the classic AlexNet network model and combines it with feature fusion to automatically classify ancient mural images. Due to the lack of large-scale mural datasets, the model first expands the dataset by applying image enhancement algorithms such as scaling, brightness conversion, noise addition, and flipping; then, it extracts the underlying features (such as fresco edges) shared by the first stage of a dual channel structure. Subsequently, a second-stage deep abstraction is conducted on the features extracted by the first stage using a two-channel network, each of which has a different structure. The obtained characteristics from both channels are merged, and a loss function is constructed to obtain the classification result. This approach improves the model's robustness and feature expression ability. The model achieves an accuracy of 84.24%, a recall rate of 84.15%, and an F1-measure of 84.13% when applied to a constructed mural image dataset. Compared with the AlexNet model and other improved convolutional neural network models, the proposed model improves each evaluation index by approximately 5%, verifying the rationality and effectiveness of the model for automatic mural image classification. The mural classification model proposed in this paper comprehensively considers the influences of network width and depth and can extract rich details from mural images from multiple local channels. An effective classification method could help researchers manage and protect mural images in an orderly fashion and quickly and effectively search for target images in a digital mural library based on a specified image category, aiding mural condition monitoring and restoration efforts as well as archaeological and art historical research.  相似文献   
8.
The purpose of this study is to find a theoretically grounded, practically applicable and useful granularity level of an algorithmically constructed publication-level classification of research publications (ACPLC). The level addressed is the level of research topics. The methodology we propose uses synthesis papers and their reference articles to construct a baseline classification. A dataset of about 31 million publications, and their mutual citations relations, is used to obtain several ACPLCs of different granularity. Each ACPLC is compared to the baseline classification and the best performing ACPLC is identified. The results of two case studies show that the topics of the cases are closely associated with different classes of the identified ACPLC, and that these classes tend to treat only one topic. Further, the class size variation is moderate, and only a small proportion of the publications belong to very small classes. For these reasons, we conclude that the proposed methodology is suitable to determine the topic granularity level of an ACPLC and that the ACPLC identified by this methodology is useful for bibliometric analyses.  相似文献   
9.
中外情报学论文创新性特征研究   总被引:1,自引:0,他引:1  
[目的/意义] 综合运用定性与定量相结合的方法对近年中外情报学论文的创新性进行分析和对比,揭示情报学领域研究的创新性特征,发现领域学术论文中创新句内部的知识关系,进行更细粒度的论文创新性分析,为研究领域创新点深层次利用提供条件,同时丰富科技论文创新性监测的途径,促进科学研究创新。[方法/过程] 从句子级创新性识别出发,选取中英文各两种情报学期刊作为样本,采用信息抽取和机器学习的方法,将创新句的抽取从现有的摘要扩展到全文,充分利用句子结构和句法特征识别领域创新内容,探讨近年中外情报学论文在创新对象、主题、类别等方面的特征,并做对比分析,最后通过对自动分类的论文集合进行定性的内容分析,总结归纳出中外情报学论文创新的表达范式。[结果/结论] 从创新的表达来看,中外情报学论文创新句的分布情况基本一致,英文期刊论文创新的表达更丰富。从创新性特征来看,英文情报学期刊论文创新主题较集中,而中文主题多样和分散;具体方法的创新是近年情报学领域的创新热点,而在研究方法上创新不足;中英文情报学期刊论文的创新性特点都反映了应用研究、实证研究的成果较多,而理论创新推动缓慢的趋势。  相似文献   
10.
基于深度学习的中文专利自动分类方法研究   总被引:2,自引:0,他引:2  
[目的/意义] 面向当前国内专利审查和专利情报分析工作中对于海量专利分类的客观需求,设计了7种基于深度学习的专利自动分类方法,对比各种方法的分类效果,从而助力专利分类效率和效果的提升。[方法/过程] 针对传统机器学习方法存在的缺陷,基于Word2Vec、CNN、RNN、Attention机制等深度学习技术,考虑专利文本语序特征、上下文特征以及分类关键特征,设计Word2Vec+TextCNN、Word2Vec+GRU、Word2Vec+BiGRU、Word2Vec+BiGRU+TextCNN等7种深度学习模型,以中国专利为例,选取IPC主分类号的"部"作为分类依据,对比这7种模型与3种传统分类模型在中文专利分类任务中的效果。[结果/结论] 实证研究效果显示,采用考虑语序特征、上下文特征及强化关键特征的深度学习方法进行中文专利分类具有更优的分类效果。  相似文献   
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号