Semantic role labeling based on conditional random fields

Due to the fact that semantic role labeling （SRL） is very necessary for deep natural language processing, a method based on conditional random fields （CRFs） is proposed for the SRL task. This method takes shallow syntactic parsing as the foundation, phrases or named entities as the labeled units, and the CRFs model is trained to label the predicates＇ semantic roles in a sentence. The key of the method is parameter estimation and feature selection for the CRFs model. The L-BFGS algorithm was employed for parameter estimation, and three category features： features based on sentence constituents, features based on predicate, and predicate-constituent features as a set of features for the model were selected. Evaluation on the datasets of CoNLL-2005 SRL shared task shows that the method can obtain better performance than the maximum entropy model, and can achieve 80. 43 % precision and 63. 55 % recall for semantic role labeling.

On Hyponymy and Semantic Fields

This paper aims at elaborating on the semantics. The concept of hyponymy is mentioned first. Then the concept of semantic fields is mentioned. In order to make a comparison between hyponymy and semantic fields, there are some examples in the paper.

A Remote Sensing Image Semantic Segmentation Method by Combining Deformable Convolution with Conditional Random Fields

Currently,deep convolutional neural networks have made great progress in the field of semantic segmentation.Because of the fixed convolution kernel geometry,standard convolution neural networks have been limited the ability to simulate geometric transformations.Therefore,a deformable convolution is introduced to enhance the adaptability of convolutional networks to spatial transformation.Considering that the deep convolutional neural networks cannot adequately segment the local objects at the output layer due to using the pooling layers in neural network architecture.To overcome this shortcoming,the rough prediction segmentation results of the neural network output layer will be processed by fully connected conditional random fields to improve the ability of image segmentation.The proposed method can easily be trained by end-to-end using standard backpropagation algorithms.Finally,the proposed method is tested on the ISPRS dataset.The results show that the proposed method can effectively overcome the influence of the complex structure of the segmentation object and obtain state-of-the-art accuracy on the ISPRS Vaihingen 2D semantic labeling dataset.

COVID-19 Lexicon in English News Reports Based on the Theory of Semantic Field

Coronavirus disease,or simply COVID-19,has affected many regions worldwide.The pandemic has caused great losses from all walks of life.Millions of people have died from the virus.In order to facilitate people’s understanding of COVID-19,the present study adopts the theory of semantic field to analyze the COVID-19 lexicon that appeared in China Daily,an authoritative international daily newspaper issued by China.A total of 100 pieces of English news issued by China Daily have been randomly selected for this research.According to the theory of semantic field in structural linguistics,the meaning of a word cannot stand alone,but come into being with the meanings of its related words.Therefore,it is reasonable to try to understand COVID-19 as thoroughly as possible with relevant words,which form its semantic field.

Bilateral U-Net semantic segmentation with spatial attention mechanism

Aiming at the problem that the existing models have a poor segmentation effect on imbalanced data sets with small-scale samples,a bilateral U-Net network model with a spatial attention mechanism is designed.The model uses the lightweight MobileNetV2 as the backbone network for feature hierarchical extraction and proposes an Attentive Pyramid Spatial Attention(APSA)module compared to the Attenuated Spatial Pyramid module,which can increase the receptive field and enhance the information,and finally adds the context fusion prediction branch that fuses high-semantic and low-semantic prediction results,and the model effectively improves the segmentation accuracy of small data sets.The experimental results on the CamVid data set show that compared with some existing semantic segmentation networks,the algorithm has a better segmentation effect and segmentation accuracy,and its mIOU reaches 75.85%.Moreover,to verify the generality of the model and the effectiveness of the APSA module,experiments were conducted on the VOC 2012 data set,and the APSA module improved mIOU by about 12.2%.

Identifying Semantic in High-Dimensional Web Data Using Latent Semantic Manifold

Latent Semantic Analysis involves natural language processing techniques for analyzing relationships between a set of documents and the terms they contain, by producing a set of concepts (related to the documents and terms) called semantic topics. These semantic topics assist search engine users by providing leads to the more relevant document. We develope a novel algorithm called Latent Semantic Manifold (LSM) that can identify the semantic topics in the high-dimensional web data. The LSM algorithm is established upon the concepts of topology and probability. Asearch tool is also developed using the LSM algorithm. This search tool is deployed for two years at two sites in Taiwan: 1) Taipei Medical University Library, Taipei, and 2) Biomedical Engineering Laboratory, Institute of Biomedical Engineering, National Taiwan University, Taipei. We evaluate the effectiveness and efficiency of the LSM algorithm by comparing with other contemporary algorithms. The results show that the LSM algorithm outperforms compared with others. This algorithm can be used to enhance the functionality of currently available search engines.

Is There an Information Field in the Life World？ Empirical Approach Using Electrophotonic Analysis

This paper presents a brief review of distant biological communication phenomena, information fields explained as a transduction of information without energy displacement, experimental requirements for testing this hypothesis with human beings using electrophotonic analysis, oxymetry and electromagnetic shielding. Finally, authors present preliminary results and future work on this new field of interdisciplinary research.

Fusing PLSA model and Markov random fields for automatic image annotation

A novel image auto-annotation method is presented based on probabilistic latent semantic analysis(PLSA) model and multiple Markov random fields(MRF).A PLSA model with asymmetric modalities is first constructed to estimate the joint probability between images and semantic concepts,then a subgraph is extracted served as the corresponding structure of Markov random fields and inference over it is performed by the iterative conditional modes so as to capture the final annotation for the image.The novelty of our method mainly lies in two aspects:exploiting PLSA to estimate the joint probability between images and semantic concepts as well as multiple MRF to further explore the semantic context among keywords for accurate image annotation.To demonstrate the effectiveness of this approach,an experiment on the Corel5 k dataset is conducted and its results are compared favorably with the current state-of-the-art approaches.

Exploiting PLSA model and conditional random field for refining image annotation

This paper presents a new method for refining image annotation by integrating probabilistic la- tent semantic analysis （PLSA） with conditional random field （CRF）. First a PLSA model with asymmetric modalities is constructed to predict a candidate set of annotations with confidence scores, and then model semantic relationship among the candidate annotations by leveraging conditional ran- dom field. In CRF, the confidence scores generated lay the PLSA model and the Fliekr distance be- tween pairwise candidate annotations are considered as local evidences and contextual potentials re- spectively. The novelty of our method mainly lies in two aspects ： exploiting PLSA to predict a candi- date set of annotations with confidence scores as well as CRF to further explore the semantic context among candidate annotations for precise image annotation. To demonstrate the effectiveness of the method proposed in this paper, an experiment is conducted on the standard Corel dataset and its re- sults are ＇compared favorably with several state-of-the-art approaches.

Application of Field Theory on Memorizing Business English Lexicons

Since Reform and Opening, the international business activities in China have become more and more frequent,hence,the importance of business English goes without saying. However, due to its lexicons is complexity and specificity, it's really a struggle matter for business English learners to memorize these lexicons. Through analyzing features of business English lexicons and establishing appropriate semantic field, business English learners could memorize these lexicons more effectively.

基于Transformer的多尺度遥感语义分割网络

为了提升遥感图像语义分割效果,本文针对分割目标类间方差小、类内方差大的特点,从全局上下文信息和多尺度语义特征2个关键点提出一种基于Transformer的多尺度遥感语义分割网络(muliti-scale Transformer network,MSTNet)。其由编码器和解码器2个部分组成,编码器包含基于Transformer改进的视觉注意网络(visual attention network,VAN)主干和基于空洞空间金字塔池化(atrous spatial pyramid pooling, ASPP)结构改进的多尺度语义特征提取模块(multi-scale semantic feature extraction module, MSFEM)。解码器采用轻量级多层感知器(multi-layer perception,MLP)配合编码器设计,充分分析所提取的包含全局上下文信息和多尺度表示的语义特征。MSTNet在2个高分辨率遥感语义分割数据集ISPRS Potsdam和LoveDA上进行验证,平均交并比(mIoU)分别达到79.50%和54.12%,平均F1-score(m F1)分别达到87.46%和69.34%,实验结果验证了本文所提方法有效提升了遥感图像语义分割的效果。

基于改进U^(2)-Net网络的金属涂层剥落与腐蚀图像分割方法

针对金属涂层缺陷图像分割中存在特征提取能力弱和分割精度低的问题,提出了一种改进的U^(2)-Net分割模型。首先,在U型残差块(RSU)中嵌入改进的增大感受野模块(receptive field block light,RFB_l),组成新的特征提取层,增强对细节特征的学习能力,解决了网络由于感受野受限造成分割精度低的问题;其次,在U^(2)-Net分割模型的解码阶段引入有效的边缘增强注意力机制(contour enhanced attention,CEA),抑制网络中的冗余特征,获取具有详细位置信息的特征注意力图,增强了边界与背景信息的差异性,从而达到更精确的分割效果。实验结果表明,该模型在两个金属涂层剥落与腐蚀数据集上的平均交并比、准确率、查准率、召回率和F_1-measure分别达到80.36%、96.29%、87.43%、84.61%和86.00%,相比于常用的SegNet、U-Net以及U^(2)-Net分割网络的性能都有较大提升。

基于改进SwiftNet的堆场图像实时分割网络

在堆场环境下,实时图像语义分割可以提供直观的场景类别信息。为节约工控机等边缘设备的硬件资源以及为多源信息融合提供图像语义类别信息,提出一种轻量化的实时语义分割网络模型。首先提出基于空间注意力引导的上采样融合模块,通过引入空间注意力和残差注意力结构设计一种轻量化的解码器,在上采样过程中还原空间细节,抑制冗余信息,进而融合不同来源的特征图;其次提出一种轻量化的级联空洞空间金字塔模块,利用级联的空洞卷积单元增大网络感受野,有效提取多尺度特征;最后使用通道分离、通道混洗、通道池化等操作,降低多尺度聚合过程中的计算开销。在公开数据集Camvid上,该模型的平均交并比(MIoU)为70.1%,推理速度为146.3帧/s,分割精度和推理速度优于ENet、ICNet等模型,消融实验结果也证明了所提各模块的有效性;在实际堆场图像数据集上,该模型的MIoU为93.5%,推理速度为123.8帧/s,证明模型结构具有良好的泛化性能。

基于潜在语义以及关键字的油气田工程智能知识信息检索方法

在油气田工程智能知识信息中,有效信息分布结构及其检索目标特征语义分析程度不同的影响,很难在特定条件下完成有效信息的全局检索,且所得检索结果与预期结果偏差较大,严重影响油气田工程智能知识信息分析进度。为了解决这一难题,提出基于潜在语义与关键字对其展开检索方法研究。建立基于潜在语义的油气田工程智能知识信息数据预处理模型,基于模型进行潜在语义分析、关键字信息空间的多重分析、知识信息检索相似度识别,实现高精度检索信息的效果。实验结果表明,提出方法能够有效提升目标信息检索精准度,在检索速率、完整度及检索稳定性方面具有提升优化作用。

基于改进DeeplabV3+的水面多类型漂浮物分割方法研究

【目的】为解决传统图像处理方法鲁棒性差、常用深度学习检测方法无法准确识别大片漂浮物的边界等问题,【方法】提出一种基于改进DeeplabV3+的水面多类型漂浮物识别的语义分割方法,提高水面漂浮的识别能力。对所收集实际水面漂浮物进行分类,采用自制数据集进行对比试验。算法选择xception网络作为主干网络以获得初步漂浮物特征,在加强特征提取网络部分引入注意力机制以强调有效特征信息,在后处理阶段加入全连接条件随机场模型,将单个像素点的局部信息与全局语义信息融合。【结果】对比图像分割性能指标,改进后的算法mPA(Mean Pixel Accuracy)提升了5.73%,mIOU(Mean Intersection Over Union)提升了4.37%。【结论】相比于其他算法模型,改进后的DeeplabV3+算法对漂浮物特征的获取能力更强,同时能获得丰富的细节信息以更精准地识别多类型水面漂浮物的边界与较难分类的漂浮物,在对多个水库场景测试后满足实际水域环境中漂浮物检测的需求。

The Application of the Semantic Field Theory in College English Vocabulary Instruction

词汇是语言的一个重要因素。本文研究语义场理论在大学英语词汇教学中的运用。作者首先探讨了如何建立各种语义关系,包括同义、反义、上下义等纵向语义关系及搭配、多义、隐喻等横向语义关系。然后,文章呈现了运用语义场理论进行词汇教学的综合教学过程。本研究的教学意义在于建立新词项的纵向语义关系可以帮助扩大学习者的词汇量;而建立新词项的横向语义关系可以加深学习者对词汇,尤其是其内涵及搭配的掌握。

基于改进UNet3+的岩心图像颗粒提取算法

在石油勘探过程中,岩心颗粒是研究地质层序、评估油气含量以及认识地质构造的有效资料,对岩心颗粒图像进行颗粒提取有利于地质研究人员后续的深入分析.岩心颗粒图像通常存在颗粒边缘模糊、背景与颗粒色彩复杂的问题.为了改善岩心颗粒提取的效果,本文设计了一种基于改进UNet3+的岩心图像颗粒提取算法.该算法在UNet3+的每个编码层后加入感受野模块(RFB)来扩大网络的感受野,从而有效地解决网络因感受野受限而导致的分割精度低的问题,并在RFB模块后嵌入了卷积块注意力模块(CBAM)使网络更加精确地聚焦于目标区域,提高目标区域的特征权重.实验结果表明,改进后的算法在岩心颗粒图像上具有良好的分割效果,相比原始UNet3+网络,分别在mIoU、mPA和FWIoU上提升了5.43%、2.99%和5.34%.

Image Semantic Segmentation Approach for Studying Human Behavior on Image Data

Image semantic segmentation is an essential technique for studying human behavior through image data.This paper proposes an image semantic segmentation method for human behavior research.Firstly,an end-to-end convolutional neural network architecture is proposed,which consists of a depth-separable jump-connected fully convolutional network and a conditional random field network;then jump-connected convolution is used to classify each pixel in the image,and an image semantic segmentation method based on convolu-tional neural network is proposed;and then a conditional random field network is used to improve the effect of image segmentation of hu-man behavior and a linear modeling and nonlinear modeling method based on the semantic segmentation of conditional random field im-age is proposed.Finally,using the proposed image segmentation network,the input entrepreneurial image data is semantically segmented to obtain the contour features of the person;and the segmentation of the images in the medical field.The experimental results show that the image semantic segmentation method is effective.It is a new way to use image data to study human behavior and can be extended to other research areas.

基于新一代脑磁图的语义视听单试次检测

为解码人脑在语义情境下的视听双模态与单模态中的响应差异,本研究设计了相关任务范式并应用新一代脑磁图(OPM-MEG)结合机器学习方法对采集信号从行为学响应、事件相关场(ERF)和单试次检测3个角度进行分析.结果显示单模态语义响应主要集中在枕叶,而双模态语义响应主要集中在顶叶.同时,双模态下的被试响应速率及单试次检测准确率显著高于单模态.此外,支持向量机(SVM)在4种机器学习模型中显示出了最佳分类效能,在被试内分类平均准确率可达75.16%,被试间平均准确率达80.56%.结果表明基于OPM-MEG结合机器学习为实现解码语义情境下的视听双模态与单模态响应差异提供了一条新的有效途径.

基于深度学习的茶嫩芽分割与采摘点定位方法研究

为实现茶嫩芽快速识别与采摘点定位,研究一种轻量级深度学习网络实现茶嫩芽分割与采摘点定位。采用MobileNetV2主干网络与空洞卷积相结合,较好地平衡茶嫩芽图像分割速度与精度的矛盾,实现较高分割精度的同时,满足茶嫩芽快速识别的要求,并设计外轮廓扫描与面积阈值过滤相结合的采摘点定位方法。试验表明:所提出的茶嫩芽分割算法在单芽尖及一芽一叶数据集中精度优异,平均交并比mIoU分别达到91.65%和91.36%;在保持高精度的同时,模型复杂度低,参数量仅5.81 M、计算量仅39.78 GFOLPs;在单芽尖、一芽一叶及一芽两叶数据集中各随机抽取200张图片进行采摘点定位验证,定位准确率分别达到90.38%、95.26%和96.60%。