Feature‐Based Relation Classification Using Quantified Relatedness Information

Feature selection is very important for feature‐based relation classification tasks. While most of the existing works on feature selection rely on linguistic information acquired using parsers, this letter proposes new features, including probabilistic and semantic relatedness features, to manifest the relatedness between patterns and certain relation types in an explicit way. The impact of each feature set is evaluated using both a chisquare estimator and a performance evaluation. The experiments show that the impact of relatedness features is superior to existing well‐known linguistic features, and the contribution of relatedness features cannot be substituted using other normally used linguistic feature sets.     

基于多尺度上下文语义信息的图像场景分类算法

传统视觉词典模型没有考虑图像的多尺度和上下文语义共生关系.本文提出一种基于多尺度上下文语义信息的图像场景分类算法.首先,对图像进行多尺度分解,从多个尺度提取不同粒度的视觉信息;其次利用基于密度的自适应选择算法确定最优概率潜在语义分析模型主题数;然后,结合Markov随机场共同挖掘图像块的上下文语义共生信息,得到图像的多尺度直方图表示;最后结合支持向量机实现场景分类.实验结果表明,本文算法能有效利用图像的多尺度和上下文语义信息,提高视觉单词的语义准确性,从而改善场景分类性能.     

Representation of Semantic Word Embeddings Based on SLDA and Word2vec Model

To solve the problem of semantic loss in text representation, this paper proposes a new embedding method of word representation in semantic space called wt2svec based on supervised latent Dirichlet allocation(SLDA) and Word2vec. It generates the global topic embedding word vector utilizing SLDA which can discover the global semantic information through the latent topics on the whole document set. It gets the local semantic embedding word vector based on the Word2vec. The new semantic word vector...     

消除语义网络中分词歧义方法研究

针对计算机语义网络中交集型和组合型词汇岐义的问题,通过分析了传统分词方法中存在的缺陷,提出基于最大概率计算的自动分词歧义方法.运用上下文语义相关度对产生歧义的词汇进行有效修正,重新计算切分候选词所产生的有效"费用",运用最大概率计算法对产生歧义的词汇进行关联程度概率计算,克服传统分词方法的弊端.成功地解决交集型岐义、连环交集型岐义、组合型岐义、混合型岐义切分问题,消除语义网络中的交集型和组合型词汇岐义的影响,取得了不错的效果.     

一种高效的语义图象分类方法

本文针对大型高维图象数据库检索，提出基于单特征进行高速，快捷的学习矢量量化算法，在独立的训练集（7537幅图像）和测量试集（5000幅图象）上，通过实验对户内／户外，城市／风景分类，并在同条件下同贝叶斯分类顺及支持向量机的结果比较，在计算复杂度和消耗时间上大大缩减，分类效果仍保持基本相似，且对有的分类问题可提高判别准确率。     

基于词义消歧的语义查询扩展研究

为了解决传统查询扩展时查准率低下的问题,基于词义消歧技术提出一种综合扩展语义树和词频共现率的语义查询扩展方法.针对查询词歧义所带来的查询主题漂移现象,利用WordNet知识源及其领域信息进行查询词义消歧,进而根据WordNet的层次结构生成扩展语义树,产生候选扩展词,并根据待扩展词与用户查询的整体最大相关性原则最终确定扩展词及其权重,使得扩展词能够充分表达用户查询请求,提高查询匹配准确率.实验表明,该方法在保证查全率的同时获得了较高的查准率.     

Unsupervised Subpixelic Classification Using Coarse-Resolution Time Series and Structural Information

In this paper, a new method is presented for a subpixelic land cover classification using both high-resolution structural information and coarse-resolution (CR) temporal information. To that aim, the linear mixture model is used for pixel disaggregation. It enables us to describe a CR time series in terms of the mixture of classes that are represented within each pixel. Then, the Bayes' rule and the maximum a posteriori criterion lead to the definition of an energy function whose minimum corresponds to the researched optimal classification. A theoretical analysis of the labeling errors that may be obtained using this energy function is provided, raising the main parameters for labeling performance. The optimal classification is computed by combining linear regressions and simulated annealing, leading to an unsupervised algorithm. The method is validated with numerical results obtained on two different agricultural scenes (i.e., the Danubian plain and the Coet Dan watershed).     

基于彩色空间3D广义共发矩阵的视觉信息检索

本文针对基于内容的图象检索（CBIR）提出一组基于HSV空间的3D广义共发矩阵的新颖的图象纹理特征，通过在CBIR检索系统iPhoto中（25，000张图象）上测试，利用本文特征地传统灰度共发矩阵。     

一种利用方位角信息基于峰值匹配的SAR图像目标分类方法

本文研究了基于峰值匹配的SAR图像目标分类问题,给出了一种利用方位角信息基于峰值匹配的SAR图像目标分类方法.该方法先对输入待分类SAR图像进行目标峰值提取,再基于提取的峰值进行目标方位角估计,然后根据该估计及其置信区间由模板SAR图像数据库检索出方位角位于该估计及该估计+180°置信区间内的所有SAR图像,并分别提取其峰值,这样即可通过寻找待分类SAR图像与由模板库检索的模板SAR图像目标峰值间的最佳匹配,实现目标分类.和不利用方位角信息的目标分类方法相比,本文方法显然具有更高的计算效率.另外,如何快速有效的确定待分类SAR图像与每一幅模板SAR图像目标峰值间的对应关系,计算其匹配度,是基于峰值匹配SAR目标分类中的另一个关键问题,针对该问题,本文提出了一种基于匹配代价函数表搜索的SAR图像目标峰值对应关系确定方法,该方法能在得到较好分类性能的同时,有效提高分类效率.实测MSTAR SAR图像数据的分类结果验证了本文方法的有效性.     

一种用于图像分类的语义增强线性编码方法

针对传统编码模型中存在的编码歧义性问题,该文提出一种考虑特征上下文的语义增强线性编码方法。首先,通过学习局部邻域中特征共生关系矩阵来表示上下文信息。然后,在编码过程中同时引入学习而得的上下文信息与特征上下文匹配权重得到语义增强编码模型。由于上下文信息与上下文匹配权重的功能,使得此编码方法不仅丰富了编码的语义信息,还能够有效避免噪声带来的影响。在3个基准数据集(Scene15, Caltech101以及 Caltech256)上充分的实验验证了该方法的有效性。     

利用配价信息的语义角色标注

语义角色标注是一种浅层语义分析.现有的汉语语义分析方法和语义角色标注体系没有结合汉语的特点并有效刻画出汉语的本质特性,导致目前汉语语义角色标注性能与英语相比相差较大.在汉语中,配价结构可以较好地刻画汉语句子的句法结构和语义构成关系,因此,我们在考察配价语法的基础上适当修改了语义角色标注体系并将谓词本身的配价信息融入语义角色标注.实验结果表明,配价信息的使用能够较大幅度提高动名词性谓词的语义角色标注性能:基于正确句法树和正确谓词识别,动词性谓词的SRL性能F1值达到93.69％;名词性谓词的SRL性能F1值达到79.23％;均优于目前国内外的同类系统.     

查询语义图辅助的信息检索性能预测模型

查询性能预测技术试图在进行费时的实际信息检索之前对特定查询的性能进行预测,以便根据预测结果在不影响查询所代表的信息需求的基础上对查询进行调整,提高最终检索结果的精确度.针对传统查询性能预测模型没有考虑查询词问语义关系的问题,本文提出了一种查询语义图辅助的信息检索性能预测模型,该模型将表征查询词间语义关系的查询语义图引入...     

A Short Text Classification Algorithm Based on Semantic Extension

A semantic-extension-based algorithm for short texts is proposed, by involving the Word2vec and the LDA model, to improve the performance of classification, which is frequently deteriorated by semantic dependencies and scarcity of features. For every keyword within a short text, weighted synonyms and related words can be generated by the Word2Vec and LDA model, respectively, and subsequently be inserted to extend the short text to a reasonable length. We not only have established a criterion by means of similarity estimation to determine whether a sentence should be extended, we designed a scheme to choose the number of extended words. The extended text will be classified. Experimental results show that, the classification performance of the proposed algorithm, in terms of the precision rate, is approximately 5％ higher than that of the TF-IDF model and approximately 10％higher than that of the VSM method.     

Effects of Grammatical Information on Word Predictability

The purpose of this investigation was to determine whether providing a respondent with the designation of the grammatical form class of words deleted from prose contexts would affect his performance in a word prediction task. Word replacements were obtained under conditions where such designations were or were not provided. The results were analyzed in terms of whether response words corresponded in grammatical form class with deleted items (FC-score), as well as in terms of verbatim replacement of items (V-score). As anticipated, grammatical information did result in a greater FC-score as compared with the absence of such information, although this was greater for function-type words (articles, prepositions, auxiliaries, etc.) than for semantic-types (nouns, verbs, adjectives). As for verbatim replacement, grammatical information led to increased V-score only in the case of function-type words, as compared with the alternative condition of no information. These results were thought to be compatible with expectations based upon differences in the numbers of words belonging to the various form classes, as well as expectations regarding the effect of grammatical information upon contextual constraint.     

用Word绘图功能绘制电路图

先绘制基本的电子元件图 ,将他们添加到自动图文集中 ,然后新建一个“电路图”工具栏 ,在该工具栏中添加各元件按钮、绘图按钮、文本框按钮、引脚按钮等 ,最后对按钮可进行优化设置。为了使用方便 ,也可新建“电路图”菜单及相关按钮     

浅谈Word 2010中宏的使用技巧

在Word 2010环境中,可以利用宏完成一系列重复的操作,从而简化工作、提高效率。本文通过两个案例,详细描述了创建宏和运用宏的具体操作步骤。     

利用名片文本图像版面信息的辅助分类方法

在基于一种知识工程和统计学习相结合的文本信息分类算法基础上,提出了利用文本在名片图像中的版面位置信息来辅助分类.此方法充分利用了名片版面中各种文本内容之间在图像中空间位置上的相互关系,对提高名片信息的分类准确性有显著的效果.     

基于语义分析的互联网人物信息提取

互联网是人类网络空间行为的体现,其中隐藏了大量人物信息.由于这些信息分散在整个网络空间中,将互联网人物信息提取并进行归类具有重要的研究意义和实用价值.文中提出了一种新的互联网人物信息提取模型,实现了人物信息的自动化提取.详细分析了基于网络爬虫的网页信息采集、基于语义分析的人物特征提取、基于向量空间模型的人物聚类算法和人物信息检索等技术原理和实现方案,能够对互联网人物信息进行分析和提取.     

多尺度语义信息融合的目标检测

针对当前目标检测算法对小目标及密集目标检测效果差的问题,该文在融合多种特征和增强浅层特征表征能力的基础上提出了浅层特征增强网络(SEFN),首先将特征提取网络VGG16中Conv4_3层和Conv5_3层提取的特征进行融合形成基础融合特征;然后将基础融合特征输入到小型的多尺度语义信息融合模块中,得到具有丰富上下文信息和空间细节信息的语义特征,同时把语义特征和基础融合特征经过特征重利用模块获得浅层增强特征;最后基于浅层增强特征进行一系列卷积获取多个不同尺度的特征,并输入各检测分支进行检测,利用非极大值抑制算法实现最终的检测结果.在PASCAL VOC2007和MS COCO2014数据集上进行测试,模型的平均精度均值分别为81.2％和33.7％,相对于经典的单极多盒检测器(SSD)算法,分别提高了2.7％和4.9％;此外,该文方法在检测小目标和密集目标场景上,检测精度和召回率都有显著提升.实验结果表明该文算法采用特征金字塔结构增强了浅层特征的语义信息,并利用特征重利用模块有效保留了浅层的细节信息用于检测,增强了模型对小目标和密集目标的检测效果.