命名实体识别技术在“数字敦煌”中的应用研究北大核心CSSCISSCI

命名实体识别是自然语言处理基础任务之一。针对“数字敦煌”项目应用命名实体识别技术存在的实体边界难以确定等问题,通过构建小规模敦煌石窟专有名词数据集,对基于BERT-BiLSTM-CRF的命名实体识别基本方法,和基于Multi-digraph的词汇增强方法进行了实验对比,结果表明基本方法已具备较高的识别准确率,而基于词汇增强的方法对未登录词识别效果提升显著。最后将训练得到的模型应用于“数字敦煌”资源库命名实体识别任务,证明了方法的有效性。     

基于关系相似度计算的实体关系分类研究

实体关系抽取和实体关系分类是信息抽取中重要的研究领域,不仅要识别文本中的实体,还要确定这些实体之间的关系,能够辅助机器对文本语义的理解。提出了一种基于关系相似度计算的实体关系分类模型,并针对7种常见实体关系进行了分类实验。     

实体识别中基于上下文仲裁的比较空间缩减机制

分布环境下实体识别过程中存在的最主要问题是实体识别的效率问题。由于实体的特征属性之间存在上下文异构,非字符串属性之间无法直接进行有意义的比较,因而字符串属性的相似性比较十分耗时。提出了基于上下文仲裁的比较空间缩减机制,通过解决实体特征属性之间存在的上下文异构,对实体特征属性中的非字符串属性进行直接比较以滤除绝大部分不匹配的实体对,极大地缩减了比较空间,最终达到了提高实体识别效率的目的。     

一种基于特征融合的医疗病例实体识别方法

在医学领域,传统的命名实体识别方法在医疗病历实体识别过程中,存在文本提取特征单一及不充分等问题,导致模型识别精准度不高。针对此问题,文章提出一种基于语义、词序、BER T预训练模型相结合的多特征融合提取方法。引入Word2vec对文本进行语义特征提取,利用Fasttext对文本的词序特征进行提取,通过BER T预训练模型获取词向量,解决Word2vec无法解决一词多义的问题。将多元特征向量融合,对相关数据的特征进行提取融合。通过卷积神经网络对融合特征进行再提取,得到更有价值的数据特征。最后通过双向长短时记忆神经网络结合条件随机场模型（BiLSTM-CRF）进行实体识别。实验结果表明：此方法在ChineseBLUE(c MedQANER)数据集上,其精准度、召回率、F1-Measure值等评价指标都有显著的提升。     

基于LSTM的生物医学核心实体提取模型研究

识别一篇生物医学文献中的核心实体是准确提取该文献信息的前提。针对目前生物医学文献实体识别和筛选方法的局限性,提出了基于LSTM的生物医学核心实体提取模型。该模型以LSTM为核心,通过更为优秀的词向量和输入生成规则改良模型输入,使用双向LSTM模型改进处理过程,将结果保存为树形结构并对该树进行合理剪枝获取标注链,实现输出结果处理,最终使实体识别的F1值达到了89.35%。此外,在核心实体筛选过程中,基于TF/IDF算法规则,充分考虑了词频、位置、逆文档频率等因素,使核心实体筛选的F1值达到了76.85%。     

大数据实体识别相关技术研究

爆炸式增长的信息量带来严重的数据质量问题。实体识别是数据清洗的一项关键技术,用以识别存在不同形式的同一对象,或区分同一形式的不同对象。介绍了实体识别相关技术,阐述了实体识别技术过程与方法,并对面向大数据的实体识别技术进行了展望。     

大数据下的实体识别算法研究

大数据下的实体识别是提高数据实体同一性的关键步骤。本文概述了实体识别问题,介绍了不同类型的实体识别算法,重点分析了复杂数据类型的大数据实体识别算法,最后对实体识别算法的相关研究进行了展望。     

电子商务中基于实体的检索系统的实现

针对电子商务中的诸多弊端,借鉴垂直搜索引擎的经验,开发出一个类似比价购物的平台至关重要.具体过程可以是通过对各个电子商务网站的商品数据的抓取和在本地做实体识别,识别出来自不同网站,不同卖家的同一种商品信息,并对这些实体进行价格排序,提供检索接口,引导用户购买.     

基于ALBERT预训练模型的通用中文命名实体识别方法

HMM、CRF等机器学习算法在中文实体抽取任务上存在大量依靠特征提取及准确率低的缺陷,而基于BiLSTM-CRF、BERT等深度神经网络算法在中文实体识别准确率高,但BiLSTM模型依赖大规模标注数据,BERT存在参数量大、效率低等问题。该研究提出了基于ALBERT-Attention-CRF模型进行中文实体抽取的方法。首先将glove、Word2vec等静态词向量替换为ALBERT预训练模型字向量,可有效解决分词错误、数据稀疏、OOV、过拟合以及一词多义等问题;然后采用ALBERT作为编码层并对其输出利用Attention机制捕获上下文语义特征;最后结合CRF作为解码层输出实体正确标签,摒弃主流BiLSTM-CRF模型,最终在《人民日报》数据的测试集上取得了理想的效果。试验结果表明,该方法有助于提升通用中文实体识别的准确率和效率,其有效性也得到了较好的验证。     

亚里士多德双重形而上学之间的关系

“形而上学”从亚里士多德开始成为哲学中的一个重要术语,亚氏对形而上学的内涵也进行了详细阐明。但亚氏在《形而上学》中却因“实体是一般的还是个别的”问题陷入了双重形而上学即一般形而上学与特殊形而上学之间的矛盾之中,也使该问题的合法性得以确证。我们应该从发生观点重新考察亚氏双重形而上学之间的关系,从而有助于对亚氏形而上学思想和实体思想有一个相对客观的认识。     

Applying ‘what works’ in psychology to enhancing examination success in schools: The potential contribution of NLP

The strengths and weaknesses of Neuro-Linguistic Programming (NLP) are described with reference to its origins, previous research and comments from critics and supporters. A case is made for this allegedly theoretical approach to provide the kind of outcomes focused intervention that psychology and psychologists can offer to schools. In particular, NLP includes a range of techniques that can be “given away” to teachers and students faced with examination pressures. The implication of such techniques with sixth form (Year 13) students in one secondary school in the South West of England is described and evaluated in terms of student comments on their helpfulness. The case is made for NLP as empowering some students to overcome exam anxiety and other related difficulties. A cyclical eight stage model is proposed for the application of NLP which is considered to offer the most likely effective learning outcomes.     

神经语言程序学视野中的语言模式

NLP是关于大脑运作、语言模式、人类认知程序以及它们之间的相互作用而产生主观认识和行为的一套学问。NLP中对语言的研究,不是研究语言本身,而是研究语言的应用技巧。NLP认为,人们存在于潜意识中的思想,经过删减、扭曲和一般化,转变成有意识的语言表达出来。语言沟通中的话语转换方法包括上调、下调和平调。提示语言模式是上调的技巧,目的是与对方的潜意识沟通,从而增加说服力。检定语言模式是下调的技巧,可以发掘对方话语中的深层意思,从而了解其真正想法。这些语言技巧,多被应用于心理治疗、演讲、人事管理和销售培训等需要与人沟通的场合。     

Neuro-linguistic programming and learning theory: a response

In an earlier issue of this journal, Craft (2001) explored Neuro-linguistic Programming (NLP) in relation to a classification of learning theories. Craft also offered various observations on, and criticisms of, aspects of NLP such as its theoretical coherence, modelling, Dilts’s ‘logical levels’ and possible dissonance of NLP’s espousal of individuality in learning with its experiential emphasis. This article offers a response to Craft’s article. It describes the origins and nature of NLP, and explores its theoretical identity. NLP is portrayed here as based primarily on the cybernetic epistemology of Gregory Bateson (1972, 1979). The article offers a critique of many of the views put across in Craft’s article, and builds on her attempt to position NLP theoretically. The broad aims of this article are to offer an informed perspective on the nature of NLP; to extend the academic literature on NLP; and to develop debate about its relevance to the theory and practice of education.     

Assessing Primary Representational System (PRS) Preference for Neurolinguistic Programming (NLP) Using Three Methods

Neurolinguistic Programming (NLP) theory suggests that each person has a preference for one of the three primary senses: visual, auditory, or kinesthetic. This preference is referred to in NLP as a primary representational system (PRS). It is necessary for a client's primary representational system (PRS) preference to be identified correctly if NLP is to be used as a therapeutic modality. Research on identifying PRS preference has been inconsistent. Three methods for identifying PRS were considered in this study.     

High-extensible scene graph framework based on component techniques

INTRODUCTION With the tremendous growth of the digital en- tertainment industry in the past decades, the scale of game scene is becoming more gigantic. To effectively manage and organize the massive data, game engine usually uses hierarchical scene graph. Many popular 3D modelling tools, such as Maya, 3D Studio Max, use scene graph to manage the scene content (Sowizral, 2000). 3D modelling software—Houdini directly edits scene graph to create and modify the virtual environment. Most v…     

Using natural language processing to support peer-feedback in the age of artificial intelligence: A cross-disciplinary framework and a research agenda

Advancements in artificial intelligence are rapidly increasing. The new-generation large language models, such as ChatGPT and GPT-4, bear the potential to transform educational approaches, such as peer-feedback. To investigate peer-feedback at the intersection of natural language processing (NLP) and educational research, this paper suggests a cross-disciplinary framework that aims to facilitate the development of NLP-based adaptive measures for supporting peer-feedback processes in digital learning environments. To conceptualize this process, we introduce a peer-feedback process model, which describes learners' activities and textual products. Further, we introduce a terminological and procedural scheme that facilitates systematically deriving measures to foster the peer-feedback process and how NLP may enhance the adaptivity of such learning support. Building on prior research on education and NLP, we apply this scheme to all learner activities of the peer-feedback process model to exemplify a range of NLP-based adaptive support measures. We also discuss the current challenges and suggest directions for future cross-disciplinary research on the effectiveness and other dimensions of NLP-based adaptive support for peer-feedback. Building on our suggested framework, future research and collaborations at the intersection of education and NLP can innovate peer-feedback in digital learning environments.

Practitioner notes

What is already known about this topic

• There is considerable research in educational science on peer-feedback processes.
• Natural language processing facilitates the analysis of students' textual data.
• There is a lack of systematic orientation regarding which NLP techniques can be applied to which data to effectively support the peer-feedback process.

What this paper adds

• A comprehensive overview model that describes the relevant activities and products in the peer-feedback process.
• A terminological and procedural scheme for designing NLP-based adaptive support measures.
• An application of this scheme to the peer-feedback process results in exemplifying the use cases of how NLP may be employed to support each learner activity during peer-feedback.

Implications for practice and/or policy

• To boost the effectiveness of their peer-feedback scenarios, instructors and instructional designers should identify relevant leverage points, corresponding support measures, adaptation targets and automation goals based on theory and empirical findings.
• Management and IT departments of higher education institutions should strive to provide digital tools based on modern NLP models and integrate them into the respective learning management systems; those tools should help in translating the automation goals requested by their instructors into prediction targets, take relevant data as input and allow for evaluating the predictions.

     

对我国虚拟经济发展的思考

简要回顾了虚拟经济的形成发展过程，阐明了虚拟经济的五大特征。分析了我国虚拟经济发展中存在的主要问题。提出了加强对虚拟经济的法规建设和监管，强化系统性风险管理和宏观调控，进一步优化实体经济结构等措施，使虚拟经济成为实体经济有益的延伸和补充。     

一个ER菜单系统

本文用实体关联模型（ER模型）代替关系模型,使多库文件之间的数据检索,数据库完整性的维护等方面得到较好的处理,其设计和实现是用一个ER菜单来描述,并作为一个前端建立在Foxpro上。     

物理学熵的哲学思考

熵的基本理论不仅适用于简单的热力学系统,而且也适用于有生命活动的物质系统,还可以拓展到从对构成宇宙的星系和银河系这种巨大世界的研究中.熵奠定了一种新的世界观,它为人类重新规范了行为界线.     

以身心语言程序学提高思想政治教育沟通效果初探

身心语言程序学是神经语言程序学的意译,是对人类主观经验进行研究的一门学问。其中NLP信息接受模式分析理论可用于思想政治教育沟通中。我们可以通过问卷来分析受教育者的信息接受模式,在思想政治教育沟通中有针对性地采取多种形式进行信息传递,以提高教育效果。