期刊文献+
共找到663篇文章
< 1 2 34 >
每页显示 20 50 100
Relational Turkish Text Classification Using Distant Supervised Entities and Relations
1
作者 Halil Ibrahim Okur Kadir Tohma Ahmet Sertbas 《Computers, Materials & Continua》 SCIE EI 2024年第5期2209-2228,共20页
Text classification,by automatically categorizing texts,is one of the foundational elements of natural language processing applications.This study investigates how text classification performance can be improved throu... Text classification,by automatically categorizing texts,is one of the foundational elements of natural language processing applications.This study investigates how text classification performance can be improved through the integration of entity-relation information obtained from the Wikidata(Wikipedia database)database and BERTbased pre-trained Named Entity Recognition(NER)models.Focusing on a significant challenge in the field of natural language processing(NLP),the research evaluates the potential of using entity and relational information to extract deeper meaning from texts.The adopted methodology encompasses a comprehensive approach that includes text preprocessing,entity detection,and the integration of relational information.Experiments conducted on text datasets in both Turkish and English assess the performance of various classification algorithms,such as Support Vector Machine,Logistic Regression,Deep Neural Network,and Convolutional Neural Network.The results indicate that the integration of entity-relation information can significantly enhance algorithmperformance in text classification tasks and offer new perspectives for information extraction and semantic analysis in NLP applications.Contributions of this work include the utilization of distant supervised entity-relation information in Turkish text classification,the development of a Turkish relational text classification approach,and the creation of a relational database.By demonstrating potential performance improvements through the integration of distant supervised entity-relation information into Turkish text classification,this research aims to support the effectiveness of text-based artificial intelligence(AI)tools.Additionally,it makes significant contributions to the development ofmultilingual text classification systems by adding deeper meaning to text content,thereby providing a valuable addition to current NLP studies and setting an important reference point for future research. 展开更多
关键词 Text classification relation extraction NER distant supervision deep learning machine learning
下载PDF
Multi-relational classification on the basis of the attribute reduction twice
2
作者 PAN Cao WANG Hong-yuan 《通讯和计算机(中英文版)》 2009年第11期49-52,共4页
关键词 属性 分类 基础 关系数据挖掘 剪枝策略 实验证明 低品质 作者
下载PDF
Discriminative explicit instance selection for implicit discourse relation classification
3
作者 Wei SONG Hongfei HAN +4 位作者 Xu HAN Miaomiao CHENG Jiefu GONG Shijin WANG Ting LIU 《Frontiers of Computer Science》 SCIE EI CSCD 2024年第4期129-138,共10页
Discourse relation classification is a fundamental task for discourse analysis,which is essential for understanding the structure and connection of texts.Implicit discourse relation classification aims to determine th... Discourse relation classification is a fundamental task for discourse analysis,which is essential for understanding the structure and connection of texts.Implicit discourse relation classification aims to determine the relationship between adjacent sentences and is very challenging because it lacks explicit discourse connectives as linguistic cues and sufficient annotated training data.In this paper,we propose a discriminative instance selection method to construct synthetic implicit discourse relation data from easy-to-collect explicit discourse relations.An expanded instance consists of an argument pair and its sense label.We introduce the argument pair type classification task,which aims to distinguish between implicit and explicit argument pairs and select the explicit argument pairs that are most similar to natural implicit argument pairs for data expansion.We also propose a simple label-smoothing technique to assign robust sense labels for the selected argument pairs.We evaluate our method on PDTB 2.0 and PDTB 3.0.The results show that our method can consistently improve the performance of the baseline model,and achieve competitive results with the state-of-the-art models. 展开更多
关键词 discourse analysis PDTB discourse relation implicit discourse relation classification data expansion
原文传递
Genetic analysis of morphological index and its related taxonomic traits for classification of indica 被引量:1
4
《Chinese Rice Research Newsletter》 1999年第3期1-2,共2页
The Cheng index distinguishes indica andjaponica rice based on six taxonomic traits.This index has been widely used for classifi- cation of indica and japonica varieties in China.In this study,a double haploid(DH)popu... The Cheng index distinguishes indica andjaponica rice based on six taxonomic traits.This index has been widely used for classifi- cation of indica and japonica varieties in China.In this study,a double haploid(DH)popula-tion derived from anther culture of ZYQ8/JX17 F,a typical inter-subspecies hybrid,was used to investigate the six taxonomictraits,i.e.leaf hairiness(LH),color of hullwhen heading(CHH),hairiness of hull(HH),length of the first and second panicle internode(LPI),length/width of grain(L/W),andphenol reaction(PH).The morphological in- dex(MI)was also calculated.Based on themolecular linkage map constructed from this 展开更多
关键词 LPI MI Genetic analysis of morphological index and its related taxonomic traits for classification of indica length
下载PDF
Classification Study on Relative Permeability Curves
5
作者 Pingzhi Gong Bin Liu +2 位作者 Junting Zhang Zheng Lv Guohao Zhang 《World Journal of Engineering and Technology》 2018年第4期723-737,共15页
The classification method of relative permeability curves is rarely reported, when relative permeability curves are applied;if the multiple relative permeability curves are normalized directly, but not classified, the... The classification method of relative permeability curves is rarely reported, when relative permeability curves are applied;if the multiple relative permeability curves are normalized directly, but not classified, the calculated result maybe cause a large error. For example, the relationship curve between oil displacement efficiency and water cut, which derived from the relative permeability curve in LD oilfield is uncertain in the shape of low water cut stage. If being directly normalized, the result of the interpretation of the water flooded zone is very high. In this study, two problems were solved: 1) The mathematical equation of the relationship between oil displacement efficiency and water cut was deduced, and repaired the lost data of oil displacement efficiency and water cut curve, which solve the problem of uncertain curve shape. After analysis, the reason why the curve is not available is that relative permeability curves are not classified and optimized;2) Two kinds of classification and evaluation methods of relative permeability curve were put forward, the direct evaluation method and the analogy method;it can get the typical relative permeability curve by identifying abnormal curve. 展开更多
关键词 relatIVE PERMEABILITY CURVE DISPLACEMENT Efficiency classification CORRECTION
下载PDF
Durability classification of red beds rocks in central Yunnan based on particle size distribution and slaking procedure 被引量:3
6
作者 ZHU Jun-jie DENG Hui 《Journal of Mountain Science》 SCIE CSCD 2019年第3期714-724,共11页
Moisture induced disintegration of soft rock in Red Beds is common all over the world. The slake durability index test is most useful to quantify durability of the soft rocks. Based on a series of slaking test, this a... Moisture induced disintegration of soft rock in Red Beds is common all over the world. The slake durability index test is most useful to quantify durability of the soft rocks. Based on a series of slaking test, this article aims to develop a durability classification involving particle size and slaking procedure. To describe the slaking procedure in detail,the Relative Slake Durability Index(Id_i) is proposed. The Id_i is the percentage ratio of the i^(th) weight of oven-dry retained portion to the(i-1)^(th) weight of ovendry retained portion. Results show that the Id_i of samples have a large difference in certain slaking procedure, whereas the traditional Durability Slake Index(Id) is almost constant. Considering this limitation of Id in durability classification, an advanced classification by applying the Id_i and disintegration ratio(DR) is further established in this article. Compared to the durability classification based on Slake Durability Index(Id), the new classification accounts for the particle size of the slaked material and the slaking procedure, so it provides a better measure of the degree of slaking. The classification recommended in this article divide the slake durability into three classes(i.e., low, medium and high class). Furthermore, it divides both the low class and the medium class into 3 subclasses. 展开更多
关键词 Slaking test DURABILITY classification relatIVE DURABILITY INDEX DURABILITY INDEX Disintegrate rate
原文传递
Mapping of Freshwater Lake Wetlands Using Object-Relations and Rule-based Inference 被引量:1
7
作者 RUAN Renzong Susan USTIN 《Chinese Geographical Science》 SCIE CSCD 2012年第4期462-471,共10页
Inland freshwater lake wetlands play an important role in regional ecological balance. Hongze Lake is the fourth biggest freshwater lake in China. In the past three decades, there has been significant loss of freshwat... Inland freshwater lake wetlands play an important role in regional ecological balance. Hongze Lake is the fourth biggest freshwater lake in China. In the past three decades, there has been significant loss of freshwater wet- lands within the lake and at the mouths of neighboring rivers, due to disturbance, primarily from human activities. The main purpose of this paper was to explore a practical technology for differentiating wetlands effectively from upland types in close proximity to them. In the paper, an integrated method, which combined per-pixel and per-field classifi- cation, was used for mapping wetlands of Hongze Lake and their neighboring upland types. Firstly, Landsat ETM+ imagery was segmented and classified by using spectral and textural features. Secondly, ETM+ spectral bands, textural features derived from ETM+ Pan imagery, relative relations between neighboring classes, shape fea^xes, and elevation were used in a decision tree classification. Thirdly, per-pixel classification results from the decision tree classifier were improved by using classification results from object-oriented classification as a context. The results show that the technology has not only overcome the salt-and-pepper effect commonly observed in the past studies, but also has im- proved the accuracy of identification by nearly 5%. 展开更多
关键词 rule-based inferring object-based classification freshwater lake wetland relation feature Hongze Lake
下载PDF
Landform Classification for Community Siting: A case Study in Quxian County, China
8
作者 ZHAO Ke DENG Zhao-hua 《Journal of Mountain Science》 SCIE CSCD 2015年第4期1025-1037,共13页
This study is to explore a suitable method to classify landform, in order to support the decision making for community siting in mountainous areas.It first proposes the landform classification for community siting(LCC... This study is to explore a suitable method to classify landform, in order to support the decision making for community siting in mountainous areas.It first proposes the landform classification for community siting(LCCS) method with detailed discussions on its rationality and the chosen parameters.This method is then tested and verified in Quxian county.The LCCS method entails twograde parameters, which uses relative relief as the first grading parameter, slope as the second, followed by a synthesis process to form a suitable landform classification system.By applying the LCCS method in Quxian county, the result shows that its use of watershed to identify geomorphometric units, and its use of the altitude datum concept, can effectively classify landform according to the local cultural traditions, and the economic and environmental conditions.The verification result shows that comparing to the conventional methods, the LCCS method respects to people's daily experience due to its bottom-up approach.It not only help to minimize the disturbance to the nature when choosing locations for community development, but also helps to prepare more precise land management policies,which maximizes agricultural production and minimizes terrain transformation. 展开更多
关键词 Landform classification Community siting relative relief SLOPE Mountainous areas China
原文传递
Exploiting multi-context analysis in semantic image classification
9
作者 田永鸿 黄铁军 高文 《Journal of Zhejiang University-Science A(Applied Physics & Engineering)》 SCIE EI CAS CSCD 2005年第11期1268-1283,共16页
As the popularity of digital images is rapidly increasing on the Internet, research on technologies for semantic image classification has become an important research topic. However, the well-known content-based image... As the popularity of digital images is rapidly increasing on the Internet, research on technologies for semantic image classification has become an important research topic. However, the well-known content-based image classification methods do not overcome the so-called semantic gap problem in which low-level visual features cannot represent the high-level semantic content of images. Image classification using visual and textual information often performs poorly since the extracted textual features are often too limited to accurately represent the images. In this paper, we propose a semantic image classification ap- proach using multi-context analysis. For a given image, we model the relevant textual information as its multi-modal context, and regard the related images connected by hyperlinks as its link context. Two kinds of context analysis models, i.e., cross-modal correlation analysis and link-based correlation model, are used to capture the correlation among different modals of features and the topical dependency among images induced by the link structure. We propose a new collective classification model called relational support vector classifier (RSVC) based on the well-known Support Vector Machines (SVMs) and the link-based cor- relation model. Experiments showed that the proposed approach significantly improved classification accuracy over that of SVM classifiers using visual and/or textual features. 展开更多
关键词 Image classification Multi-context analysis Cross-modal correlation analysis Link-based correlation model Linkage semantic kernels relational support vector classifier
下载PDF
The Power of Group Generators and Relations: An Examination of the Concept and Its Applications
10
作者 Tiancheng Zhou 《Journal of Applied Mathematics and Physics》 2018年第11期2425-2444,共20页
This paper investigates the approach of presenting groups by generators and relations from an original angle. It starts by interpreting this familiar concept with the novel notion of “formal words” created by juxtap... This paper investigates the approach of presenting groups by generators and relations from an original angle. It starts by interpreting this familiar concept with the novel notion of “formal words” created by juxtaposing letters in a set. Taking that as basis, several fundamental results related to free groups, such as Dyck’s Theorem, are proven. Then, the paper highlights three creative applications of the concept in classifying finite groups of a fixed order, representing all dihedral groups geometrically, and analyzing knots topologically. All three applications are of considerable significance in their respective topic areas and serve to illustrate the advantages and certain limitations of the approach flexibly and comprehensively. 展开更多
关键词 Generators and relationS Free GROUP Dyck’s Theorem Dihedral GROUP Presentation classification of Finite GROUPS (Application) Realizing Dihedral GROUPS Geometrically (Application) KNOT GROUP (Application)
下载PDF
Electrical responses and classification of complex waterflooded layers in carbonate reservoirs: A case study of Zananor Oilfield, Kazakhstan
11
作者 WANG Fei BIAN Huiyuan +2 位作者 ZHAO Lun YU Jun TAN Chengqian 《Petroleum Exploration and Development》 2020年第6期1299-1306,共8页
Experiments of electrical responses of waterflooded layers were carried out on porous,fractured,porous-fractured and composite cores taken from carbonate reservoirs in the Zananor Oilfield,Kazakhstan to find out the e... Experiments of electrical responses of waterflooded layers were carried out on porous,fractured,porous-fractured and composite cores taken from carbonate reservoirs in the Zananor Oilfield,Kazakhstan to find out the effects of injected water salinity on electrical responses of carbonate reservoirs.On the basis of the experimental results and the mathematical model of calculating oil-water relative permeability of porous reservoirs by resistivity and the relative permeability model of two-phase flow in fractured reservoirs,the classification standards of water-flooded layers suitable for carbonate reservoirs with complex pore structure were established.The results show that the salinity of injected water is the main factor affecting the resistivity of carbonate reservoir.When low salinity water(fresh water)is injected,the relationship curve between resistivity and water saturation is U-shaped.When high salinity water(salt water)is injected,the curve is L-shaped.The classification criteria of water-flooded layers for carbonate reservoirs are as follows:(1)In porous reservoirs,the water cut(fw)is less than or equal to 5%in oil layers,5%–20%in weak water-flooded layers,20%–50%in moderately water-flooded layers,and greater than 50%in strong water-flooded layers.(2)For fractured,porous-fractured and composite reservoirs,the oil layers,weakly water-flooded layers,moderately water-flooded layers,and severely water-flooded layers have a water content of less than or equal to 5%,5%and 10%,10%to 50%,and larger than 50%respectively. 展开更多
关键词 Zananor Oilfield carbonate reservoir water-flooded layer electrical response characteristics relative permeability curve classification criterion of water-flooded level
下载PDF
引入激活扩散的类分布关系近邻分类器
12
作者 董飒 欧阳若川 +4 位作者 徐海啸 刘杰 刘大有 李婷婷 王鑫禄 《吉林大学学报(理学版)》 CAS 北大核心 2024年第4期915-922,共8页
针对同质性关系分类器基于一阶Markov假设简化处理的局限性,在类分布关系近邻分类器构建类向量和参考向量时,引入局部图排序激活扩散方法,并结合松弛标注的协作推理方法,通过适当扩大分类时邻居节点的范围增加网络数据中待分类节点的同... 针对同质性关系分类器基于一阶Markov假设简化处理的局限性,在类分布关系近邻分类器构建类向量和参考向量时,引入局部图排序激活扩散方法,并结合松弛标注的协作推理方法,通过适当扩大分类时邻居节点的范围增加网络数据中待分类节点的同质性,从而降低分类错误率.对比实验结果表明,该方法扩大了待分类节点的邻域,在网络数据上分类精度较好. 展开更多
关键词 人工智能 网络数据分类 激活扩散 类分布关系近邻分类器 协作推理
下载PDF
临床科室功能定位和病种结构分类的精细化管理
13
作者 钟晓 吴粤 +1 位作者 庄虹 叶冬炜 《现代医院》 2024年第8期1259-1261,共3页
目的探索医院临床科室分类方法,为实现科室的精细化管理提供科学依据。方法利用2022年深圳市某三甲医院临床科室的实际占用总床日数、出院患者手术占比、出院患者四级手术比例、CMI值、DRG组数进行快速聚类分析,把临床科室分成三个类别... 目的探索医院临床科室分类方法,为实现科室的精细化管理提供科学依据。方法利用2022年深圳市某三甲医院临床科室的实际占用总床日数、出院患者手术占比、出院患者四级手术比例、CMI值、DRG组数进行快速聚类分析,把临床科室分成三个类别,分析不同类别的特点和临床科室的分类结果。结果30个临床科室分类成一般手术科室、非手术科室和高难度治疗科室。分类结果与预期一致,但普外科分类于非手术科室,而新生儿科分类于一般手术科室。结论应用快速聚类法进行临床科室分类,能客观反映科室特点,达到医院精细化管理的目的。利用分组异常结果信息,有利于分析临床科室的功能定位和病种结构特点,进行调整优化。 展开更多
关键词 快速聚类法 科室分类 疾病诊断相关分组 绩效考核
下载PDF
关系信息增强的少样本关系分类原型表示研究
14
作者 王磊 任鹏瑞 瞿剑峰 《小型微型计算机系统》 CSCD 北大核心 2024年第7期1615-1621,共7页
少样本关系分类任务旨在只使用极少量样本来识别出句子中给定实体对的关系,现有工作在FewRel 1.0数据集上进行了大量研究,并没有考虑“以上都不是”(none-of-the-above,NOTA)关系的检测问题,而已有的考虑NOTA关系的工作都是在间接地计... 少样本关系分类任务旨在只使用极少量样本来识别出句子中给定实体对的关系,现有工作在FewRel 1.0数据集上进行了大量研究,并没有考虑“以上都不是”(none-of-the-above,NOTA)关系的检测问题,而已有的考虑NOTA关系的工作都是在间接地计算查询样例与NOTA的相似度,这容易导致误差累积,模型性能因此表现不佳.为此,本文提出了一种基于关系信息增强的能够直接生成NOTA关系原型表示的方法.首先,本文提出了一种易混淆实例采样策略,通过挑选出信息丰富且易混淆的实例作为NOTA关系的支持数据并直接计算NOTA关系的原型表示;然后,本文使用了关系名和关系的描述信息作为外部关系信息,来提供给模型更多可用信息以生成更准确的原型表示.在广泛使用的FewRel 2.0数据集上的大量实验结果证明了本文提出的方法的优越性. 展开更多
关键词 少样本学习 关系分类 原型网络 易混淆实例 关系信息
下载PDF
基于任务感知关系网络的少样本图像分类
15
作者 郭礼华 王广飞 《电子与信息学报》 EI CAS CSCD 北大核心 2024年第3期977-985,共9页
针对关系网络(RN)模型缺乏对分类任务整体相关信息的感知能力的问题,该文提出基于任务感知关系网络(TARN)的小样本学习(FSL)算法。引入模糊C均值(FCM)聚类生成基于任务全局分布的类别原型,同时设计任务相关注意力机制(TCA),改进RN中的1... 针对关系网络(RN)模型缺乏对分类任务整体相关信息的感知能力的问题,该文提出基于任务感知关系网络(TARN)的小样本学习(FSL)算法。引入模糊C均值(FCM)聚类生成基于任务全局分布的类别原型,同时设计任务相关注意力机制(TCA),改进RN中的1对1度量方式,使得在与类别原型对比时,局部特征聚合了任务全局信息。和RN比,在数据集Mini-ImageNet上,5-way 1-shot和5-way 5-shot设置中的分类准确率分别提高了8.15%和7.0%,在数据集Tiered-ImageNet上,5-way 1-shot和5-way 5-shot设置中的分类准确率分别提高了7.81%和6.7%。与位置感知的关系网络模型比,在数据集Mini-ImageNet上,5-way 1-shot设置中分类准确率也提高了1.24%。与其他小样本图像分类算法性能比较,TARN模型在两个数据集上都获得了最佳的识别精度。该方法将任务相关信息和度量网络模型进行结合可以有效提高小样本图像分类准确率。 展开更多
关键词 小样本学习 图像分类 度量学习 任务感知 关系网络
下载PDF
基于残差卷积与多头自注意力的CXR图像分类
16
作者 陈辉 张甜 陈润斌 《工程科学与技术》 EI CAS CSCD 北大核心 2024年第3期219-227,共9页
为了提高新型冠状病毒肺炎(COVID-19)检测的效率和准确性,本文提出一种自动识别COVID-19胸部X射线(CXR)图像的网络模型(MHRA-RCNet)。在ResNet50模型的基础上,首先,采用残差卷积对CXR图像中形状复杂的感染区域进行局部特征提取。其次,... 为了提高新型冠状病毒肺炎(COVID-19)检测的效率和准确性,本文提出一种自动识别COVID-19胸部X射线(CXR)图像的网络模型(MHRA-RCNet)。在ResNet50模型的基础上,首先,采用残差卷积对CXR图像中形状复杂的感染区域进行局部特征提取。其次,选择在ResNet50的第2、3阶段引入多头关系聚合模块,以增强对全局信息的建模能力;为了进一步将局部信息和全局信息进行融合,以提高特征的表达能力和特征之间位置的相关性,在ResNet50的最后阶段引入了空洞视觉Transforme模块,有助于识别CXR图像中复杂的病变区域。最后,将融合后的特征以串联方式输入全局平均池化层进行全局空间信息整合,通过多层感知机进行图像分类并进行可视化分析。在公开访问的COVID-19 Radiography Database数据集与其他深度学习模型进行实验对比。实验结果表明:本文模型在多项分类指标上具有较好的分类精度;另外,从精确度、灵敏度和特异性上也可以直观地看出本文模型能够较好地识别新冠肺炎,进一步证明了本文模型在图像分类任务中的优越性和有效性。 展开更多
关键词 新型冠状病毒肺炎 图像分类 残差卷积 多头关系聚合 空洞视觉Transformer
下载PDF
运用PCNE分类系统对呼吸道疾病患者进行药学监护的应用研究 被引量:2
17
作者 康曼 张弦 +3 位作者 李茗薇 张华 徐静 王晓娟 《中国药师》 CAS 2024年第2期336-344,共9页
目的 运用欧洲医药保健网(PCNE)分类系统对呼吸道疾病患者进行药学监护,探索呼吸科的有效药学监护模式,促进临床合理用药。方法 选取安徽理工大学第一附属医院2022年诊断为慢性阻塞性肺疾病(COPD)和肺部感染的住院患者,分为简单组和干预... 目的 运用欧洲医药保健网(PCNE)分类系统对呼吸道疾病患者进行药学监护,探索呼吸科的有效药学监护模式,促进临床合理用药。方法 选取安徽理工大学第一附属医院2022年诊断为慢性阻塞性肺疾病(COPD)和肺部感染的住院患者,分为简单组和干预组;根据PCNE分类系统,对药物相关问题(DRPs)的类型、原因、干预、干预的接受情况及解决状态等方面进行分析。结果 共纳入病例120例,简单组60例,干预组60例。DRPs发生人数方面,简单组15例,干预组45例,两组差异有统计学意义(P <0.05)。DRPs共82个,主要涉及治疗效果(51.22%)和安全性(46.34%),原因为患者药物使用方法不正确、用法用量不适宜和未定期安全监测等。药师干预中,药物层面75个(91.46%),医生层面38个(46.34%),患者层面43个(52.44%);药师干预后,接受率为97.56%,74.39%的DRPs得到解决。结论 应用PCNE分类系统进行药学监护能够增强临床药师发现和处理DRPs的能力,减少临床发生不良事件的风险,促进患者的合理、安全用药;同时还有助于药学监护实施记录的标准化和规范化,可为呼吸科患者的药学服务模式提供参考。 展开更多
关键词 药物相关问题 欧洲医药保健网分类系统 药学监护 临床药师
原文传递
基于对span的预判断和多轮分类的实体关系抽取
18
作者 佟缘 姚念民 《计算机工程与科学》 CSCD 北大核心 2024年第5期916-928,共13页
针对自然语言处理领域中的实体识别和关系抽取任务,提出一种对词元序列(Token Sequence,又称span)进行预测的模型Smrc。模型整体上利用BERT预训练模型作为编码器,另外包含实体预判断(Pej)、实体多轮分类(Emr)和关系多轮分类(Rmr)3个模块... 针对自然语言处理领域中的实体识别和关系抽取任务,提出一种对词元序列(Token Sequence,又称span)进行预测的模型Smrc。模型整体上利用BERT预训练模型作为编码器,另外包含实体预判断(Pej)、实体多轮分类(Emr)和关系多轮分类(Rmr)3个模块。Smrc模型通过Pej模块的初步判断及Emr模块的多轮实体分类来进行实体识别,再利用Rmr模块的多轮关系分类来判断实体对间的关系,进而完成关系抽取任务。在CoNLL04、SciERC和ADE 3个实验数据集上,Smrc模型的实体识别F1值分别达到89.67%,70.62%和89.56%,关系抽取F1值分别达到73.11%,51.03%和79.89%,相较之前在3个数据集上的最佳模型Spert,Smrc模型凭借实体预判断和实体及关系多轮分类,在2个子任务上其F1值分别提高了0.73%,0.29%,0.61%及1.64%,0.19%,1.05%,表明了该模型的有效性及其优势。 展开更多
关键词 对span的预判断 实体关系抽取 BERT预训练模型 多轮实体分类 多轮关系分类
下载PDF
基于关系增强图卷积网络的机器阅读理解式事件检测
19
作者 纪婉婷 鲁闻一 +3 位作者 马宇航 丁琳琳 宋宝燕 张浩林 《计算机应用》 CSCD 北大核心 2024年第10期3288-3293,共6页
在面对具有复杂句法关系的长文本上下文时,现有机器阅读理解式事件检测模型难以挖掘关键词之间长距离依赖关系。针对上述问题,提出一种基于关系增强图卷积网络(REGCN)的机器阅读理解式事件检测模型(MRCREGCN)。首先,利用预训练语言模型... 在面对具有复杂句法关系的长文本上下文时,现有机器阅读理解式事件检测模型难以挖掘关键词之间长距离依赖关系。针对上述问题,提出一种基于关系增强图卷积网络(REGCN)的机器阅读理解式事件检测模型(MRCREGCN)。首先,利用预训练语言模型对问题和文本进行联合编码,得到融入先验信息的单词向量表示;其次,引入动态的关系增强标签信息,并利用REGCN深入学习单词之间的句法依存关系,增强模型对长文本句法结构的感知能力;最后,利用多分类器得到文本单词在所有事件类型下的概率分布。在ACE2005英文语料上的实验结果表明,所提模型在触发词分类上的F1分值相较于同类机器阅读理解模型EEQA(Event Extraction by Answering(almost)natural Questions)和最佳基线模型DEGREE(Data-Efficient GeneRation-based Event Extraction)分别提升了2.49%和1.23%,验证了MRC-REGCN具有更好的事件检测性能。 展开更多
关键词 机器阅读理解 事件检测 图卷积网络 句法依存关系 触发词分类
下载PDF
限定域关系抽取技术研究综述 被引量:1
20
作者 侯景 邓晓梅 汉鹏武 《计算机科学》 CSCD 北大核心 2024年第1期252-265,共14页
限定域关系抽取技术是在预定义实体类型和关系类型的前提下,从文本中捕获关键信息的技术,多采用由头尾实体和关系构成的三元组作为信息表示形式。作为信息抽取领域的重要研究方向之一,其在知识问答、信息检索等任务中被广泛应用。文中... 限定域关系抽取技术是在预定义实体类型和关系类型的前提下,从文本中捕获关键信息的技术,多采用由头尾实体和关系构成的三元组作为信息表示形式。作为信息抽取领域的重要研究方向之一,其在知识问答、信息检索等任务中被广泛应用。文中在介绍相关概念和任务范式的基础上,分析了深度学习背景下限定域关系抽取任务的研究进展,根据句中实体是否可见,分为关系分类任务和三元组抽取任务,依据任务表现特征,前者可细分为有监督条件下的关系分类任务、小样本关系分类任务和远程监督条件下的关系分类任务。文中探讨和分析了以上任务中常用的技术方法及其优缺点,最后归纳总结了关系抽取技术在低资源、多模态等更为接近真实情景下的发展潜力和现存的挑战。 展开更多
关键词 限定域关系抽取 深度学习 关系分类 三元组 远程监督
下载PDF
上一页 1 2 34 下一页 到第
使用帮助 返回顶部