检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

1,442 篇 会议
43 册 图书
43 篇 期刊文献

馆藏范围

1,528 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,211 篇 工学
- 1,041 篇 计算机科学与技术...
- 602 篇 软件工程
- 285 篇 电气工程
- 253 篇 信息与通信工程
- 208 篇 生物工程
- 163 篇 光学工程
- 145 篇 生物医学工程（可授...
- 132 篇 控制科学与工程
- 62 篇 电子科学与技术（可...
- 53 篇 机械工程
- 41 篇 化学工程与技术
- 32 篇 材料科学与工程（可...
- 29 篇 仪器科学与技术
- 25 篇 安全科学与工程
498 篇 理学
- 234 篇 数学
- 227 篇 生物学
- 185 篇 物理学
- 80 篇 统计学（可授理学、...
- 39 篇 化学
- 34 篇 系统科学
215 篇 医学
- 199 篇 临床医学
- 85 篇 基础医学(可授医学...
- 61 篇 药学(可授医学、理...
- 29 篇 公共卫生与预防医...
209 篇 管理学
- 140 篇 图书情报与档案管...
- 84 篇 管理科学与工程(可...
- 34 篇 工商管理
43 篇 农学
- 43 篇 作物学
30 篇 法学
- 27 篇 社会学
18 篇 教育学
- 18 篇 教育学
13 篇 经济学
3 篇 军事学
1 篇 艺术学

主题

141 篇 machine learning
122 篇 deep learning
116 篇 image processing
108 篇 pattern recognit...
70 篇 feature extracti...
64 篇 convolutional ne...
57 篇 image segmentati...
46 篇 face recognition
45 篇 computer vision
41 篇 artificial intel...
39 篇 support vector m...
36 篇 image recognitio...
34 篇 image classifica...
31 篇 neural networks
25 篇 training
24 篇 object detection
24 篇 accuracy
22 篇 machine learning...
22 篇 object recogniti...
21 篇 image enhancemen...

机构

6 篇 institute of ima...
5 篇 centre for inter...
5 篇 chitkara univers...
5 篇 univ south dakot...
4 篇 indian statistic...
4 篇 university of ca...
4 篇 national researc...
4 篇 boston universit...
3 篇 dept. of compute...
3 篇 shanghai jiao to...
3 篇 peter the great ...
3 篇 natl. lab. of pa...
3 篇 technische unive...
3 篇 graphic era deem...
3 篇 bangalore
3 篇 department of co...
2 篇 university of sc...
2 篇 université laval...
2 篇 department of cs...
2 篇 italian inst tec...

作者

6 篇 santosh k. c.
5 篇 yang jie
4 篇 gennaro claudio
4 篇 ma songde
4 篇 falchi fabrizio
4 篇 stan sclaroff
4 篇 cheng h.d.
4 篇 cosimo distante
3 篇 wendling laurent
3 篇 frontoni emanuel...
3 篇 guimaraes silvio...
3 篇 battiato sebasti...
3 篇 giovanni m. fari...
3 篇 anon
3 篇 santosh k.c.
3 篇 hegadi ravindra ...
3 篇 marco leo
3 篇 ozawa shinji
3 篇 hossain syed akh...
3 篇 maier-hein klaus

语言

1,463 篇 英文
58 篇 其他
43 篇 中文
2 篇 土耳其文

检索条件"任意字段=1st International Conference on Image Processing Machine Learning and Pattern Recognition"

共 1528 条记录，以下是641-650 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Why is the winner the best?

Why is the winner the best?

引用

IEEE/CVF conference on Computer Vision and pattern recognition (CVPR)

作者： Eisenmann, M. Reinke, A. Weru, V. Tizabi, M. D. Isensee, F. Adler, T. J. Ali, S. Andrearczyk, V. Aubreville, M. Baid, U. Bakas, S. Balu, N. Bano, S. Bernal, J. Bodenstedt, S. Casella, A. Cheplygina, V. Daum, M. de Bruijne, M. Depeursinge, A. Dorent, R. Egger, J. Ellis, D. G. Engelhardt, S. Ganz, M. Ghatwary, N. Girard, G. Godau, P. Gupta, A. Hansen, L. Harada, K. Heinrich, M. Heller, N. Hering, A. Huaulme, A. Jannin, P. Kavur, A. E. Kodym, O. Kozubek, M. Li, J. Li, H. Ma, J. Martin-Isla, C. Menze, B. Noble, A. Oreiller, V. Padoy, N. Pati, S. Payette, K. Raedsch, T. Rafael-Patino, J. Bawa, V. Singh Speidel, S. Sudre, C. H. van Wijnen, K. Wagner, M. Wei, D. Yamlahi, A. Yap, M. H. Yuan, C. Zenk, M. Zia, A. Zimmerer, D. Aydogan, D. Bhattarai, B. Bloch, L. Bruengel, R. Cho, J. Choi, C. Dou, Q. Ezhov, I. Friedrich, C. M. Fuller, C. Gaire, R. R. Galdran, A. Faura, A. Garcia Grammatikopoulou, M. Hong, S. Jahanifar, M. Jang, I. Kadkhodamohammadi, A. Kang, I. Kofler, F. Kondo, S. Kuijf, H. Li, M. Luu, M. Martincic, T. Morais, P. Naser, M. A. Oliveira, B. Owen, D. Pang, S. Park, J. Park, S. Plotka, S. Puybareau, E. Rajpoot, N. Ryu, K. Saeed, N. Shephard, A. Shi, P. stepec, D. Subedi, R. Tochon, G. Torres, H. R. Urien, H. Vilaca, J. L. Wahid, K. A. Wang, H. Wang, J. Wang, L. Wang, X. Wiestler, B. Wodzinski, M. Xia, F. Xie, J. Xiong, Z. Yang, S. Yang, Y. Zhao, Z. Maier-Hein, K. Jaeger, P. F. Kopp-Schneider, A. Maier-Hein, L. German Canc Res Ctr Div Intelligent Med Syst Heidelberg Germany German Canc Res Ctr Helmholtz Imaging Heidelberg Germany Heidelberg Univ Fac Math & Comp Sci Heidelberg Germany German Canc Res Ctr Div Biostat Heidelberg Germany German Canc Res Ctr Div Med Image Comp Heidelberg Germany Univ Leeds Fac Engn & Phys Sci Sch Comp Leeds W Yorkshire England HES SO Valais Wallis Univ Appl Sci & Arts Western Inst Informat Sch Management Sierre Switzerland Lausanne Univ Hosp Dept Nucl Med & Mol Imaging Lausanne Switzerland Tech Hsch Ingolstadt Ingolstadt Germany Univ Penn Ctr Artificial Intelligence & Data Sci Integrated Philadelphia PA USA Univ Penn Ctr Biomed Image Comp & Analyt Philadelphia PA USA Univ Penn Dept Pathol & Lab Med Perelman Sch Med Philadelphia PA USA Univ Penn Dept Radiol Perelman Sch Med Philadelphia PA USA Univ Washington Dept Radiol Seattle WA USA UCL Wellcome EPSRC Ctr Intervent & Surg Sci WEISS London England UCL Dept Comp Sci London England Univ Autonoma Barcelona Barcelona Spain Comp Vis Ctr Barcelona Spain Natl Ctr Tumor Dis NCT UCC Div Translat Surg Oncol Dresden Germany Ist Italiano Tecnol Dept Adv Robot Genoa Italy Politecn Milan Dept Elect Informat & Bioengn Milan Italy IT Univ Copenhagen Copenhagen Denmark Heidelberg Univ Hosp Dept Gen Visceral & Transplantat Surg Heidelberg Germany Erasmus MC Dept Radiol & Nucl Med Biomed Imaging Grp Rotterdam Rotterdam Netherlands Univ Copenhagen Dept Comp Sci Copenhagen Denmark Univ Appl Sci Western Switzerland HES SO Inst Informat Syst Sierre Switzerland Harvard Med Sch Brigham & Womens Hosp Boston MA USA Kings Coll London Sch Biomed Engn & Imaging Sci London England Univ Hosp Essen AoR Inst Artificial Intelligence Med IKIM Essen Germany Univ Nebraska Med Ctr Omaha NE USA Heidelberg Univ Hosp Dept Internal Med 3 Heidelberg Germany Rigshosp Copenhagen Univ Hosp Neurobiol Res Unit Copenhagen Denmark Arab Acad Sci & Technol Cairo Egypt CIBM Ctr Biomed Imaging L

ISBN: (纸本)9798350301298

international benchmarking competitions have become fundamental for the comparative performance assessment of image analysis methods. However, little attention has been given to investigating what can be learnt from these competitions. Do they really generate scientific progress? What are common and successful participation strategies? What makes a solution superior to a competing method? To address this gap in the literature, we performed a multi-center study with all 80 competitions that were conducted in the scope of IEEE ISBI 2021 and MICCAI 2021. statistical analyses performed based on comprehensive descriptions of the submitted algorithms linked to their rank as well as the underlying participation strategies revealed common characteristics of winning solutions. These typically include the use of multi-task learning (63%) and/or multi-stage pipelines (61%), and a focus on augmentation (100%), image preprocessing (97%), data curation (79%), and post-processing (66%). The "typical" lead of a winning team is a computer scientist with a doctoral degree, five years of experience in biomedical image analysis, and four years of experience in deep learning. Two core general development strategies stood out for highly-ranked teams: the reflection of the metrics in the method design and the focus on analyzing and handling failure cases. According to the organizers, 43% of the winning algorithms exceeded the state of the art but only 11% completely solved the respective domain problem. The insights of our study could help researchers (1) improve algorithm development strategies when approaching new problems, and (2) focus on open research questions revealed by this work. [GRAPHICS] .

关键词： cell microscopy Medical and biological vision

来源：评论

学校读者我要写书评

暂无评论

Towards Interactive image Segmentation by Dynamic and Iterative Spanning Forest 1st

Towards Interactive Image Segmentation by Dynamic and Iterat...

引用

1st IAPR international Joint conference on Discrete Geometry and Mathematical Morphology (DGMM)

作者： Barcelos, Isabela Borlido Belem, Felipe Miranda, Paulo Falcao, Alexandre Xavier do Patrocinio, Zenilton K. G., Jr. Guimaraes, Silvio Jamil F. Pontificia Univ Catolica Minas Gerais Lab Image & Multimedia Data Sci ImSci BR-31980110 Belo Horizonte Brazil Univ Estadual Campinas Lab Image Data Sci LIDS BR-13083852 Sao Paulo Brazil Univ Estadual Campinas Inst Math & Stat BR-05508090 Sao Paulo Brazil

ISBN: (纸本)9783030766566;9783030766573

Interactive image segmentation aims to partition the image into background and foreground objects by taking into account seeds inserted by users. Nowadays, many methods are capable of generating segmentations with few user interactions, especially region-based techniques. However, such methods are highly sensitive to seed displacement and quantity, and delineation errors are often propagated to the final segmentation result. Recently, a novel superpixel segmentation framework, named Dynamic and Iterative Spanning Forest (DISF), was proposed, which achieved top delineation performance while assessing many seed-based state-of-the-art methods' drawbacks. In this work, we propose interactive DISF (iDISF), an interactive segmentation framework, by modifying each step of DISF to consider user-validated information. DISF uses the image Foresting Transform (IFT) framework for computing an optimum-path forest rooted in a seed set in the delineation step. To consider path and image gradient variation, we propose three new connectivity functions for the IFT. Finally, we also propose two new seed removal strategies for detecting relevant seeds for subsequent iterations. Results show segmentation improvements for minimal user effort-i.e., a single click-and show theoretical advances that may benefit recent optimum-path-based interactive methods from scribbles.

关键词： Graph-based image segmentation Dynamic and iterative spanning forest Interactive segmentation

来源：评论

学校读者我要写书评

暂无评论

machine learning Applied To Plant Disease Detection

Machine Learning Applied To Plant Disease Detection

引用

international conference on Computational Science and Technology (ICCst)

作者： Sushant Jadhav Gujanatti Rudrappa Arun Tigadi Bharati Chilad Sachin Urabinahatti Basavaraj Chougula Vinayakumar R Bagali Department of Electronics and Communication KLE Dr. MS Sheshgiri College of Engineering and Technology VTU Belagavi Karnataka India Department of CSE KLE Dr. M S Sheshgiri College of Engineering and Technology VTU Belagavi Karnataka India Computer Sciecne Engineering Tatyasaheb Kore Institute of Engineering and Technology Shivaji University Warnanagar Kolhapur Maharastra India Department of Electronics and Communication Jain College of Engineering VTU Belgaum Karnataka India

ISBN: (纸本)9781665476560

One of the most important factors in India's economy is agricultural output. Plants are dying because of a lack of knowledge about the signs of plant diseases and how to cure them. Improvements in both production and quality can be achieved by early disease identification. Predicting plant diseases more quickly and accurately might help mitigate costs. As deep learning has advanced, so has the possibility to enhance the efficiency and precision of the system used to identify and categorize objects. One type of deep learning known as convolutional neural networks is employed in the areas of image classification, picture segmentation, and signal processing. Here, we suggest using convolutional neural networks (CNNs) to identify plant diseases. The proposed work's primary objective is to provide a method for detecting various types of plant diseases with minimal effort.

关键词： Deep learning Plant diseases image segmentation Costs Scientific computing Production Signal processing

来源：评论

学校读者我要写书评

暂无评论

Modified ML-kNN and Rank SVM for Multi-label pattern Classification 1

Modified ML-kNN and Rank SVM for Multi-label Pattern Classif...

引用

1st international conference on Advances in Smart Sensor, Signal processing and Communication Technology, ICASSCT 2021

作者： Kassim, Thanseeha Shajee Mohan, B.S. Ahammed Muneer, K.V. M. Tech Signal Processing AE and i Dept. Govt. Engg. College Kozhikode India Dept of AE and i Govt. Engg. College Kozhikode India

To develop an efficient multi-label classifier is the main objective of this paper. In multi-label learning tasks such as classification, each example is associated with a set of labels, and the task is to predict the label set whose size is unknown apriory for each unseen example. In a realistic scenario each object or entity belongs to a multi-label category. Multi-Label k-Nearest Neighbor (ML-kNN), Rank-SVM (Ranking Support Vector machine) are two popular techniques used for multi-label pattern classification. ML-kNN is a multi-label version of standard kNN and Rank SVM is a multi-label extension of standard SVM. The main aim of this work is to enhance the performance of these methods. Multi-label classifiers generally consider ranking loss, Hamming loss, one error, average precision and coverage as a performance metrics. © Published under licence by IOP Publishing Ltd.

关键词： Vector spaces

来源：评论

学校读者我要写书评

暂无评论

1st international conference on Bioengineering and Biomedical Signal and image processing, BIOMESIP 2021

1st International Conference on Bioengineering and Biomedica...

引用

1st international conference on Bioengineering and Biomedical Signal and image processing, BIOMESIP 2021

ISBN: (纸本)9783030881627

The proceedings contain 42 papers. The special focus in this conference is on Bioengineering and Biomedical Signal and image processing. The topics include: Methodological Approaches to the Comparison of Left Ventricular stroke Volume Values Measured by Ultrasonic Technique or Estimated via Transfer Functions;investigation of Gastroparesis Using Multichannel Electro Gastro Gram – A study;3D Tomosynthesis Evaluation of Pixel Intensity Values of Breast Masses;trident U-Net: An Encoder Fusion for Improved Biomedical image Segmentation;COVID-19 Detection Method from Chest CT Scans via the Fusion of Slice Information and Lung Segmentation;denseNet for Breast Tumor Classification in Mammographic images;analysing Large Repositories of Medical images;fat Mass is Negatively Associated with Composite Indices of Femoral Neck strength in Elderly Lebanese Subjects;image Fusion to Guide Decision-Making Towards Minimally Invasive Epilepsy Treatment;optimizing Photoacoustic Tomography: Lymphatic Drainage from the Brain in Pigmented Mice;Data-Driven EEG Informed Functional MRI Combined with Network Analysis Successfully Identifies the Seizure Onset Zone;modern Neurophysiological Research of the Human Brain in Clinic and Psychophysiology;application of Resting Brain Frontal Lobe Complexity in Depression Screening;Local Contrast Normalization to Improve Preprocessing in MRI of the Brain;Morphological Characteristics Analysis of Working Memory Tracts Using BOLD-fMRI and HARDI Based Tractography in Healthy Human Brains;analysis of Accuracy and Timing in Decision-Making Tasks;Recurrent Neural Networks and Efficiency in High-Dimensional EEG Classification;Energy-Time Profiling for machine learning Methods to EEG Classification;Performance study of Ant Colony Optimization for Feature Selection in EEG Classification;Prevalence of COVID-19 Amongst Arizona First Responders.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Feature-Based Plant Seedlings Classification 1

引用

1st international Scientific conference on Telecommunications, Computing and Control, TELECCON 2019

作者： Jakovlev, Dmitri Kamaletdinova, Iuliia Shevlyakov, Georgy Peter the Great St. Petersburg Polytechnic University St. Petersburg Russia

ISBN: (数字)9789813366329

ISBN: (纸本)9789813366312

The application of image features in the plant classification task is studied. The used dataset was created at Aarhus University Flakkebjerg Research. This work aims at different approaches in plant species categorization. In this study, the feature-based approach is used. It allows to perform classifying using less computational resources. The features usage is motivated by the following purpose: to distinguish weeds from other plants by selecting the defining features of all classes of plants. The proposed method combines image thresholding, feature selection, and feature extraction for the further multiclass classification by such well-known machine learning algorithms as the support vector machines, K-nearest neighbors, decision tree, and Naive Bayes. To a greater extent, we use computer vision algorithms for the image processing step. The main classification method we choose for the task is the support vector machines: It shows the best performance among other tested algorithms;the K-nearest neighbors algorithm is slightly worse. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Identifying Paddy Crop Disease Using Enhanced Deep learning Technique 1st

Identifying Paddy Crop Disease Using Enhanced Deep Learni...

引用

1st international Research conference on Computing Technologies for Sustainable Development, IRCCTSD 2024

作者： Subramanian, Ganapathy Neduncheliyan Bharath Institute of Higher Education and Research Chennai India

ISBN: (纸本)9783031823886

The consequences of extreme weather changes on crops, the growing global population, and numerous illnesses that emerge at a severe level all have an impact on agricultural production and food security. Farmers employ expensive disease management strategies that sometimes outweigh output losses. Because it would be too expensive for them to install crop protection measures at the early beginning of the illnesses, which results in very little advantages, the farmers would only act when it was too late to stop the disease from spreading. It was suggested that computer orders using technology for calculating vision may be beneficial in a range of original-globe situations. It may be used in crop security strategies since it employs artificial intelligence, graphics, and image processing to detect illnesses, pests, and malnutrition. machine learning (ML) approaches are being utilised in the ongoing study of disease detection from plant photographs. For recognising paddy leaf disease, a unique deep neural network (DNN) classification model is employed using plant picture data. Existing system like CNN, TL and ANN gives the mere accuracy results. There is drawback in identifying the accurate crop diseases. The proposed hybrid ECNN and CSA algorithm give more accuracy when compared to the existing system. It increases the accuracy level by 95%. The hybrid ECNN & CSA based designs shown amazing success in crop disease prediction and categorization using images. These models require a lot of training data, though, and they are computationally costly. The proposed enhanced hybrid deep learning based hybrid algorithm model identifying the diseases in the paddy leaves in a most significant manner. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Various Algorithms and Techniques for Traffic Density Estimation

Various Algorithms and Techniques for Traffic Density Estima...

引用

international conference on Computational Science and Technology (ICCst)

作者： Sanjay Venkat Swagata Sarkar Shreemadhi B Karanam Poorna Siri Bavanika M Artificial Intelligence and Data Science Sri Sairam Engineering College Chennai India

ISBN: (纸本)9781665476560

Traffic has been a major problem in recent times. Traffic management is a must for safer and faster transportation. Automatic smart signal controlling systems respond to day-to-day world traffic densities to provide precedence and reduction in cross-road delays for travelers. According to the traffic density, the time between signals is adjusted so that the waiting time in traffic reduces. The ML model is capable of detecting accidents and immediately sends notifications or alert messages to nearby hospitals. The model tracks the GPS location of the ambulance and ensures no red signal in its pathway. Zebra crossing signals are also included, the signal timings are switched based on the crossing crowd. Automatic Smart Signal Control is a complete machine learning based project with some applications of IoT and Video / image processing. Implementation of the model all over the major signals and junctions provides faster and safer transportation.

关键词： Program processors machine learning algorithms Scientific computing Roads Transportation Process control Switches

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive study on Computer Aided Diagnostic Technologies for Early Prediction of Parkinson Disease

A Comprehensive Study on Computer Aided Diagnostic Technolog...

引用

international conference on Computational Science and Technology (ICCst)

作者： B. Latha M. Subashini Sri Sai Ram Engineering College Sai Leo Nagar West Tambaram Chennai

ISBN: (纸本)9781665476560

In today's society,Parkinson's Disease(PD)is concerned as a chronic neurological illness that mainly targets the elderly *** two-thirds of PD sufferers expenence uncomfortable discomfort sensations that go *** methods and technologies as a toolare required to diagnose the earlier stages of PD using important and efficient automatic techniques . This study gives a complete assessment of articles on the diagnosis of PD based on captions employing Signalprocessing, Sensor-based survey, machine learning (ML) and Deep learning (DL). We compiledvarious published articles in well-known resources, including Science Direct, Plos One, IEEEXplore, Multidisciplinary Digital Publishing Institute(MDPI), PubMed ,Association for Computational machinery (ACM), Hindawi and Springer Publishing Company, for this review. Each study has been thoroughly examined to determine its purpose,methods,and outcomes,as well as extensive information and analysis on the use of multiple modalities,databases,and investigational configurations. As a result, this study will give investigators a clear image for developing decision-making approaches that will benefit physicians and caregivers.

关键词： Prediction algorithms Feature extraction Signal processing algorithms Taxonomy Support vector machine classification Scientific computing Neurons

来源：评论

学校读者我要写书评

暂无评论

A Forgotten strategy for Pooled Contextualized Embedding learning 2020

A Forgotten Strategy for Pooled Contextualized Embedding Lea...

引用

2nd international conference on image processing and machine Vision / international conference on pattern recognition and machine learning (IPMV)

作者： Cai, Dunbo Huang, Zhiguo Qian, Ling Hang, Tao Feng, Qingsong China Mobile Suzhou Software Suzhou Peoples R China

ISBN: (纸本)9781450388412

string (word) embeddings are keys to advanced neural natural language understanding (NLU) models. Recently, a new embedding called contextual string embedding (CtxEmb) reached a new state of the art on many NLU tasks. Specially, a pooling variant of CtxEmb demonstrated new best results on named entity recognition (NER) tasks. While the pooling variant is good at reaching new best performance in terms of Micro F1 score, it poses questions on what kind of information in the pool is helpful. In particular, the pooling variant maintains a (possibly long) list of previously seen occurrences of a word, and computes embedding for the word in a new context based on those occurrences. In this paper, we propose a strategy to forget some previous occurrences, and thus exploring which history are beneficial in constructing embeddings for a new context of a word. The proposed forgotten strategy is designed by accounting for a distance metric defined in this paper. Preliminary experiments on the WNUT-17 task show the effectiveness of our forgotten strategy, and uncover that embeddings that are diverse in terms of cosine similarity are helpful in forming an aggregated embedding.

关键词： Word Embedding learning Contextual string Embedding Representation learning

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共153页 << < 61 62 63 64 65 66 67 68 69 70 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：