检索结果-内蒙古大学图书馆

7th IEEE International Conference on Cloud Computing and Intelligence Systems, CCIS 2021

作者： Xu, Yuan Shi, Shumin Huang, Heyan Beijing Institute of Technology School of Computer Science and Technology Beijing China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Beijing China

ISBN: (纸本)9781665441490

Multi-choice Machine Reading Comprehension (MRC) requires the model to select the correct answer from a set of answer candidates given the corresponding passage and question. Previous studies mainly focus on complex matching networks to model the relationship among options, passage and question. However, these models obtain little improvement over the powerful Pre-trained Language Models (PLMs). In this paper, we propose a simple method to incorporate option knowledge from PLMs and introduce out-of-domain knowledge by multi-task learning skillfully. Our approach obtains state-of-the-art results on Chinese multi-choice MRC dataset ReCO and also effectively improves the performance on C3. © 2021 IEEE.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

Image Registration with Learned Regularization

Image Registration with Learned Regularization

引用

Chinese Automation Congress (CAC)

作者： Xinjie Lai Wan Yang Lvda Wang Shihui Ying Qian Weichang Academy Shanghai University Department of Mathematics College of Science Shanghai University Beijing Institute of Computer Technology and Applications

Image registration is one of the important tasks in medical image processing. The accuracy of image registration greatly affects the subsequently intelligent analysis. In this paper, we focus on the medical image registration via deep learning, and propose the unsupervised deep learning framework based on model decoupling and regularization learning. Specifically, as a highly ill-posed inverse problem, we first decompose the image registration into two simpler sub-problems to reduce the complexity of model solving. Further, two light neural networks are constructed to approximate the solutions of the two subproblems, where the training strategy of alternative iteration is used. Secondly, we introduce regularization learning module to form an end-to-end deep learning architecture. Here, we approximate the regularization term via the ISTA net, and make the regularization constraints more consistent with the actual data distribution. It reduces the registration errors caused by the deviation between the pre-set prior knowledge and the actual data distribution, and then realizes a higher accurate and data adaptive registration approach. Finally, to validate the performance of the proposed algorithm, we compare it with the VoxelMorph algorithms on brain MRI images dataset LPBA40 and lung CT image dataset DIRLAB. The experimental results show that the proposed algorithms obtain the best performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Consistency analysis of UML models 29

Consistency analysis of UML models

引用

29th International DMS Conference on Visualization and Visual Languages, DMSVIVA 2023

作者： Tang, Guo-Fu Jiang, Jian-Min Wen, Hao Automatic Software Generation and Intelligence Service Key Laboratory of Sichuan Province China Chengdu University of Information Technology Chengdu610103 China Chengdu Institute of Computer Applications Chinese Academy of Sciences Chengdu610103 China University of Chinese Academy of Sciences Beijing101408 China

ISBN: (纸本)1891706578

The inconsistencies of UML models (diagrams) during the software development process may cause errors in documents or programs. Massive consistency rules have been proposed by researchers to detect inconsistencies in existing works. However, the approaches of consistency analysis have not been addressed adequately in literature. In this paper, we propose a new approach for analyzing consistencies between UML models. We formally specify UML models and define the consistency relation between UML models. Based on the consistency definition, we first discuss the composition and decomposition of consistencies, and then explore the equivalence of consistencies. Copyright © 2023 by KSI Research Inc. and Knowledge Systems institute, USA.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

A CLASS OF SHORT-TERM RECURRENCE ANDERSON MIXING METHODS AND THEIR applications 10

A CLASS OF SHORT-TERM RECURRENCE ANDERSON MIXING METHODS AND...

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Wei, Fuchao Bao, Chenglong Liu, Yang Department of Computer Science and Technology Tsinghua University China Institute for AI Industry Research Tsinghua University China Yau Mathematical Sciences Center Tsinghua University China Yanqi Lake Beijing Institute of Mathematical Sciences and Applications China

Anderson mixing (AM) is a powerful acceleration method for fixed-point iterations, but its computation requires storing many historical iterations. The extra memory footprint can be prohibitive when solving high-dimensional problems in a resource-limited machine. To reduce the memory overhead, we propose a novel class of short-term recurrence AM methods (ST-AM). The ST-AM methods only store two previous iterations with cheap corrections. We prove that the basic version of ST-AM is equivalent to the full-memory AM in strongly convex quadratic optimization, and with minor changes it has local linear convergence for solving general nonlinear fixed-point problems. We further analyze the convergence properties of the regularized ST-AM for nonconvex (stochastic) optimization. Finally, we apply ST-AM to several applications including solving root-finding problems and training neural networks. Experimental results show that ST-AM is competitive with the long-memory AM and outperforms many existing optimizers. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Mixing

来源：评论

学校读者我要写书评

暂无评论

Measurement of atmospheric nanoparticles:Bridging the gap between gas-phase molecules and larger particles

引用

Journal of Environmental Sciences 2023年第1期123卷 183-202页

作者： Chao Peng Chenjuan Deng Ting Lei Jun Zheng Jun Zhao Dongbin Wang Zhijun Wu Lin Wang Yan Chen Mingyuan Liu Jingkun Jiang Anpei Ye Maofa Ge Weigang Wang State Key Laboratory for Structural Chemistry of Unstable and Stable Species Beijing National Laboratory for Molecular Sciences(BNLMS)CAS Research/Education Center for Excellence in Molecular SciencesInstitute of ChemistryChinese Academy of SciencesBeijing 100190China State Key Joint Laboratory of Environment Simulation and Pollution Control School of EnvironmentTsinghua UniversityBeijing 100084China School of Environment Science and Engineering Nanjing University of Information Science&TechnologyNanjing 210044China School of Atmospheric Sciences Sun Yat-sen UniversityZhuhaiGuangdong 519082China State Key Joint Laboratory of Environmental Simulation and Pollution Control College of Environmental Sciences and EngineeringPeking UniversityBeijing 100871China Shanghai Key Laboratory of Atmospheric Particle Pollution and Prevention(LAP3) Department of Environmental Science&EngineeringFudan UniversityShanghai 200433China Key Laboratory for the Physics and Chemistry of Nanodevices Department of ElectronicsSchool of Electronics Engineering and Computer SciencePeking UniversityBeijing 100871China University of Chinese Academy of Sciences Beijing 100049China

Atmospheric nanoparticles are crucial components contributing to fine particulate matter(PM_(2.5)),and therefore have significant effects on visibility,climate,and human *** to the unique role of atmospheric nanoparticles during the evolution process from gas-phase molecules to larger particles,a number of sophisticated experimental techniques have been developed and employed for online monitoring and characterization of the physical and chemical properties of atmospheric nanoparticles,helping us to better understand the formation and growth of new *** this paper,we firstly review these state-of-the-art techniques for investigating the formation and growth of atmospheric nanoparticles(e.g.,the gas-phase precursor species,molecular clusters,physicochemical properties,and chemical composition).Secondly,we present findings from recent field studies on the formation and growth of atmospheric nanoparticles,utilizing several advanced ***-more,perspectives are proposed for technique development and improvements in measuring atmospheric nanoparticles.

关键词： Nanoparticle Measurement techniques Size distributions Physical properties Chemical composition

来源：评论

学校读者我要写书评

暂无评论

Key Techniques on Unified Identity Authentication in OpenMBEE Integration 4

Key Techniques on Unified Identity Authentication in OpenMBE...

引用

4th IEEE International Conference on Electronics and Communication Engineering, ICECE 2021

作者： Xue, Junjie Zhou, Junhua Shi, Guoqiang Feng, Chaoqun Liu, Penghua Quan, Hongyan Beijing Complex Product Advanced Manufacturing Engineering Research Center Beijing Simulation Center Beijing China State Key Laboratory of Intelligent Manufacturing System Technology Beijing China Institute of Electronic System Engineering Beijing China Beijing Complex Product Advanced Manufacturing Engineering Research Center Beijing Simulation Center Beijing China Science and Technology on Space System Simulation Laboratory Beijing Simulation Center Beijing China School of Computer Science and Technology East China Normal University Shanghai China

ISBN: (纸本)9781728194226

In order to make full use of the concept of model-based systems engineering (MBSE) and the collaborative design capability of the open model-based engineering environment (OpenMBEE) in establishing complex product development platform, we propose an effective method to solve the problem of unified identity authentication in OpenMBEE integration. The proposed method is based on the Model View Controller(MVC) architecture in OpenMBEE, which has the characteristics strong plasticity and can be benefit for expanding the function in the controller layer. In our research, we make full use of the Software Development Kit (SDK) of OpenMBEE to expand the existing functions in the controller layer, and increase the function of communicating with the application development platform, then realize the function of sharing user authentication information between the development platform and OpenMBEE. After expansion, the system includes three modules, including the Front-end Service Module(FSM), MQ based Information Receiving Service Module(IFRSM), and the OpenMBEE Back-end Server Module(BSM). The effectiveness of the proposed strategies is verified by some practical instances, which verifies that our study can provide an effective design idea for the identity authentication in OpenMBEE integration. ©2021 IEEE

关键词： Integration

来源：评论

学校读者我要写书评

暂无评论

Exploiting Knowledge Embedding to Improve the Description for Image Captioning 5th

Exploiting Knowledge Embedding to Improve the Description fo...

引用

5th China Conference on Knowledge Graph, and Semantic Computing, CCKS 2020

作者： Song, Dandan Peng, Cuimei Yang, Huan Liao, Lejian Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Beijing Key Laboratory of Intelligent Information Technology School of Computer Science and Technology Beijing Institute of Technology Beijing China

ISBN: (纸本)9789811619632

Most existing methods for image captioning are based on the encoder-decoder framework which directly translates visual features into sentences, without exploiting commonsense knowledge available in the form of knowledge graph. Inspired by the success of information retrieval and question answering systems that leverage prior knowledge, we explore a knowledge embedding approach for image captioning. In this paper, we propose a Knowledge Embedding with Attention on Attention (KE-AoA) method for image captioning, which judges whether or how well the objects are related and augments semantic correlations and constraints between them. The KE-AoA method combines knowledge base method (TransE) and text method (Skip-gram), adding external knowledge graph information (triplets) into the language model to guide the learning of word vectors as the regularization term. Then it employs the AoA module to model the relations among different objects. As more inherent relations and commonsense knowledge are learned, the model can generate better image descriptions. The experiments on MSCOCO data sets achieve a significant improvement on the existing methods and validate the effectiveness of our prior knowledge-based approach. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

iTourSPOT:a context-aware framework for next POI recommendation in location-based social networks

引用

International Journal of Digital Earth 2022年第1期15卷 1614-1636页

作者： Lin Wan Han Wang Yuming Hong Ran Li Wei Chen Zhou Huang School of Computer Science China University of GeosciencesWuhanPeople's Republic of China Institute of Remote Sensing and Geographical Information Systems Peking UniversityBeijingPeople's Republic of China Beijing Key Lab of Spatial Information Integration & Its Applications Peking UniversityBeijingPeople's Republic of China Information Center Hubei Geological Environment StationWuhanPeople's Republic of China College of Geoscience and Surveying Engineering China University of Mining & TechnologyBeijingPeople's Republic of China

The rising prosperity of Location-based Social Networks(LBSNs)witnessed an explosion in the availability of geo-tagged social media data,which enables tremendous location-aware online services,especially next point of interest(POI)***,previous next POI recommendation studies usually adopt fix-length time windows for user check-in sequence modeling,leading to a limited capacity in capturing fine-grained user temporal preferences that easily change over ***,existing methods often directly leverage multi-modal contexts as auxiliary to alleviate the data sparsity issue,which fails to fully exploit the sequential patterns of contextual information for inferring user interest *** address the above challenges,we propose a novel framework named iTourSPOT which extends traditional collaborative filtering methods with a context-aware POI embedding *** enhancing temporal interests modeling capacity,we associate the context feature extraction with varying-length sessions and incorporate check-in frequencies of POIs as prior knowledge to instruct the session representation learning of our ***,a collaborative sequence transduction model is designed for joint context sequence modeling and session-based POI *** results on a real-world geo-tagged photo dataset clearly demonstrate the effectiveness of the proposed framework when compared with state-of-the-art baseline methods,especially in both sparse and cold-start scenarios.

关键词： Next POI recommendation context-aware recommendation location-based social network geo-tagged photos

来源：评论

学校读者我要写书评

暂无评论

Reducing Length Bias in Scoring Neural Machine Translation via a Causal Inference Method 20

Reducing Length Bias in Scoring Neural Machine Translation v...

引用

20th China National Conference on Computational Linguistics, CCL 2021

作者： Shi, Xuewen Huang, Heyan Jian, Ping Tang, Yi-Kun School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Beijing100081 China

ISBN: (纸本)9783030841850

Neural machine translation (NMT) usually employs beam search to expand the searching space and obtain more translation candidates. However, the increase of the beam size often suffers from plenty of short translations, resulting in dramatical decrease in translation quality. In this paper, we handle the length bias problem through a perspective of causal inference. Specifically, we regard the model generated translation score S as a degraded true translation quality affected by some noise, and one of the confounders is the translation length. We apply a Half-Sibling Regression method to remove the length effect on S, and then we can obtain a debiased translation score without length information. The proposed method is model agnostic and unsupervised, which is adaptive to any NMT model and test dataset. We conduct the experiments on three translation tasks with different scales of datasets. Experimental results and further analyses show that our approaches gain comparable performance with the empirical baseline methods. © 2021, Springer Nature Switzerland AG.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

AttenWalker: Unsupervised Long-Document Question Answering via Attention-based Graph Walking

arXiv

引用

arXiv 2023年

作者： Nie, Yuxiang Huang, Heyan Wei, Wei Mao, Xian-Ling School of Computer Science and Technology Beijing Institute of Technology China Beijing Engineering Research Center High Volume Language Information Processing and Cloud Computing Applications China Beijing Institute of Technology Southeast Academy of Information Technology China Huazhong University of Science and Technology China

Annotating long-document question answering (long-document QA) pairs is time-consuming and expensive. To alleviate the problem, it might be possible to generate long-document QA pairs via unsupervised question answering (UQA) methods. However, existing UQA tasks are based on short documents, and can hardly incorporate long-range information. To tackle the problem, we propose a new task, named unsupervised long-document question answering (ULQA), aiming to generate high-quality long-document QA instances in an unsupervised manner. Besides, we propose AttenWalker, a novel unsupervised method to aggregate and generate answers with long-range dependency so as to construct long-document QA pairs. Specifically, AttenWalker is composed of three modules, i.e., span collector, span linker and answer aggregator. Firstly, the span collector takes advantage of constituent parsing and reconstruction loss to select informative candidate spans for constructing answers. Secondly, by going through the attention graph of a pre-trained long-document model, potentially interrelated text spans (that might be far apart) could be linked together via an attention-walking algorithm. Thirdly, in the answer aggregator, linked spans are aggregated into the final answer via the mask-filling ability of a pre-trained model. Extensive experiments show that AttenWalker outperforms previous methods on Qasper and NarrativeQA. In addition, AttenWalker also shows strong performance in the few-shot learning setting. Copyright © 2023, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：