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  

吕璐成  韩涛  周健  赵亚娟 《图书情报工作》2020,64(10):75-85

[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   

转型、困惑与出路——美国“进步主义运动”略论   总被引：1，自引：0，他引：1  

王春来 《华东师范大学学报(哲学社会科学版)》2003,35(5):71-78,86

19、20世纪之交美国社会经济的巨变和转型促成了“进步主义运动”的兴起。运动的倡导者源自美国社会各主要阶层和集团，共同的社会责任感和危机意识将其维系在一起。作为自由主义改革的集大成者，这场运动从19世纪后期美国的各类改革实践中汲取营养，以之作为渊源和动力并有所超越。由于该时期美国社会转型的复杂性，“进步主义运动”也蕴涵诸多悖论，对其加以准确释读对于观照普遍意义上的资本主义转型不无裨益。  相似文献   

穴位埋线治疗对冠心病稳定型心绞痛的疗效观察     

刘卫平  林展增  吴建琼 《河北北方学院学报(医学版)》2002,19(6):8-9

目的 :观察穴位埋线对冠心病稳定型心绞痛的疗效。方法 :按随机对照方法 ,分为治疗组 32例 ,对照组 (长效硝苯地平 ) 31例。治疗 8周 ,观察心肌缺血发作次数、持续时间及缺血总负荷等指标。结果 :两组治疗前后各观察指标有显著差异 ,P <0 .0 1。两组之间比较无明显差异 ,P >0 .0 5。结论 :穴位埋线法能显著改善心肌缺血。  相似文献   

Effect of class imbalance in heterogeneous network embedding: An empirical study     

《Journal of Informetrics》2020,14(2):101009

Network science has been extensively explored in solving various bibliometrics tasks such as Co-authorship prediction, Author classification, Author clustering, Author ranking, Paper ranking, etc. While majority of the past studies exploit homogeneous bibliographic network (consists of singular type of nodes and edges), in recent past there is a surge in using heterogeneous bibliographic entities and their inter-dependencies using heterogeneous information networks (HIN). Unlike homogeneous bibliographic networks, a bibliographic HIN consists of multi-typed nodes such as Author, Paper, Venue, etc. and corresponding relations. Thus bibliographic HIN is more complex and captures rich semantics of underlying bibliographic data as well as poses more challenges. Since a real-world HIN may have different number of instances for different node types, class imbalance is ubiquitous. Recent studies discuss class imbalance in brief and exploit meta-path-based strategies to address the issue. However, there is no work which quantitatively study the effect of class imbalance in regards to solving real-world bibliometrics tasks. Therefore, this paper first proposes a metric to estimate class imbalance in HIN and study the effects of class imbalance over two bibliometrics tasks, namely (i) Co-authorship prediction and (ii) Author's research area classification, using node features generated by network embedding-based frameworks for DBLP dataset. From various experimental analysis, it is evident that class imbalance in bibliographic HIN is an inherent characteristic and for better performance of the above-mentioned bibliometrics tasks, the bibliographic HINs must consider Author, Paper, and Venue as node types.  相似文献   

Retooling Education: Testing and the Liberal Arts     

Robert L. Jackson 《Academic Questions》2007,20(4):332-346

The motivation and methodology for measuring intelligence have changed repeatedly in the modern history of large-scale student testing. Test makers have always sought to identify raw aptitude for cultivation, but they have never figured out how to promote excellence while preserving equality. They’ve settled for egalitarianism, which gives rise to “culturally fair” tests that substitute vagaries for knowledge, deprive students of any real appreciation for language, and trivialize education. Robert Jackson yearns for traditional oratorical approaches to schooling that venerate and imitate essential, time-tested masters. Unfortunately, he writes, such an education defies measurement with today’s multiple-choice instruments.

Robert L. JacksonEmail:

---

Robert L. Jackson   is associate professor of English and education at The King’s College, New York, NY 10118; rjackson@tkc.edu.  相似文献   

基于深度学习的领域本体概念自动获取方法研究     

王思丽  祝忠明  刘巍  杨恒 《情报理论与实践》2020,43(3):145-152,144

[目的/意义]实现对领域概念的自动学习抽取,解决领域本体自动化构建的首要基础任务。[方法/过程]以无监督的学习方法和端到端的识别模式为理论技术基础,首先通过对主流词嵌入模型进行对比分析,设计提出了基于Word2Vec和Skip-Gram的领域文本特征词嵌入模型的自动生成方法;其次研究构建了以IOB格式的标注文本作为输入,基于自注意力机制的BLSTM-CRF领域概念自动抽取模型;最后以资源环境学科领域为例进行了实验研究与评估分析。[结果/结论]模型能够实现对领域概念的自动抽取,对领域新概念或术语的自动识别也具有一定的健壮性。[局限]模型精度尚未达到峰值,有待进一步优化提升。  相似文献   

Predicting future dynamics from short-term time series using an Anticipated Learning Machine     

Chuan Chen  Rui Li  Lin Shu  Zhiyu He  Jining Wang  Chengming Zhang  Huanfei Ma  Kazuyuki Aihara  Luonan Chen 《国家科学评论(英文版)》2020,7(6):1079

Predicting time series has significant practical applications over different disciplines. Here, we propose an Anticipated Learning Machine (ALM) to achieve precise future-state predictions based on short-term but high-dimensional data. From non-linear dynamical systems theory, we show that ALM can transform recent correlation/spatial information of high-dimensional variables into future dynamical/temporal information of any target variable, thereby overcoming the small-sample problem and achieving multistep-ahead predictions. Since the training samples generated from high-dimensional data also include information of the unknown future values of the target variable, it is called anticipated learning. Extensive experiments on real-world data demonstrate significantly superior performances of ALM over all of the existing 12 methods. In contrast to traditional statistics-based machine learning, ALM is based on non-linear dynamics, thus opening a new way for dynamics-based machine learning.  相似文献   

Characterization of chaotic multiscale features on the time series of melt index in industrial propylene polymerization system     

Ting Wang  Xinggao Liu  Zeyin Zhang 《Journal of The Franklin Institute》2014

The chaos characteristics of melt index have been first explored, and the Hilbert–Huang transform method and time delay embedding method are applied to multiscale dynamic analysis on the time series of the melt index (MI) in the propylene polymerization industry. The research results show that the embedding delay is 2, the embedding dimension is 5, the correlation dimension D₂ is 1.57, and the maximum Lyapunov exponent is 0.143 for the melt index series, which provide clear evidence of chaotic multiscale features in the propylene polymerization process. Three intrinsic mode functions (IMFs) are decomposed from the melt index time series; the presence of non-integer fractal correlation dimension and positive finite maximum Lyapunov exponent are found in some IMF components. The PP melt index series are divided into two chaotic signals, a determined signal and a random signal respectively, and its complexity is therefore reduced. Furthermore, the coupling of subscale structures of the propylene polymerization is explored with the dimension of interaction dynamics and a robust algorithm for detecting interdependence. It is found that IMF(2) is the main driver in the coupling system of IMF(1)and IMF(2). All these provide a guideline for studying propylene polymerization process with chaotic multiscale theory and may offer more candidate tools to model and control propylene polymerization system in the future.  相似文献   

网络嵌入对技术创新绩效的影响:学习能力的视角          下载免费PDF全文

谢洪明  张颖  程聪  陈盈 《科研管理》2014,35(12):1-8

不同网络嵌入方式对企业创新绩效的影响是存在显著差异的。构建了网络嵌入、学习能力和技术创新绩效之间的理论模型,通过运用结构方程模型对广东省高新技术与民营科技型企业为样本的问卷调查数据进行实证分析。研究结果表明:(1)网络结构嵌入对技术创新绩效没有直接的显著影响,也无法通过学习能力的中介对其产生间接的影响作用;(2)网络关系嵌入对技术创新绩效不仅有直接显著的正向影响,而且还能通过学习能力的部分中介作用对技术创新绩效起到显著的正向影响;(3)在小规模企业中,网络密度对于技术创新绩效的作用并不显著。研究结论进一步深化了技术创新理论,对企业技术创新的提升有一定指导意义。  相似文献   

Identification of Chinese dark jargons in Telegram underground markets using context-oriented and linguistic features     

《Information processing & management》2022,59(5):103033

When cybercriminals communicate with their customers in underground markets, they tend to use secure and customizable instant messaging (IM) software, i.e. Telegram. It is a popular IM software with over 700 million monthly active users (MAU) up to June 2022. In recent years, more and more dark jargons (i.e. an innocent-looking replacement of sensitive terms) appear frequently on Telegram. Therefore, jargons identification is one of the most significant research perspectives to track online underground markets and cybercrimes. This paper proposes a novel Chinese Jargons Identification Framework (CJI-Framework) to identify dark jargons. Firstly, we collect chat history from Telegram groups that are related to the underground market and construct the corpus TUMCC (Telegram Underground Market Chinese Corpus), which is the first Chinese corpus in jargons identification research field. Secondly, we extract seven brand-new features which can be classified into three categories: Vectors-based Features (VF), Lexical analysis-based Features (LF), and Dictionary analysis-based Features (DF), to identify Chinese dark jargons from commonly-used words. Based on these features, we then run a statistical outlier detection to decide whether a word is a jargon. Furthermore, we employ a word vector projection method and a transfer learning method to improve the effect of the framework. Experimental results show that CJI-Framework achieves a remarkable performance with an F1-score of 89.66%. After adaptation for English, it performs better than state-of-the-art English jargons identification method as well. Our built corpus and code have been publicly released to facilitate the reproduction and extension of our work.  相似文献