检索结果-内蒙古大学图书馆

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Scheible, Raphael Frei, Johann Thomczyk, Fabian He, Henry Tippmann, Patric Knaus, Jochen Jaravine, Victor Kramer, Frank Boeker, Martin Institute for AI and Informatics in Medicine University Hospital rechts der Isar Technical University Munich Germany IT-Infrastructure for Translational Medical Research Faculty of Applied Computer Science University of Augsburg Germany Data Integration Center Faculty of Medicine University of Freiburg Germany School of Computation Information and Technology Technical University Munich Germany Institute of Medical Biometry and Statistics Medical Center Faculty of Medicine University of Freiburg Germany Freiburg Center for Data Analysis and Modeling University of Freiburg Germany Hengrui Europe Biosciences Zurich Switzerland

ISBN: (纸本)9798891761643

Pre-trained language models have significantly advanced natural language processing (NLP), especially with the introduction of BERT and its optimized version, RoBERTa. While initial research focused on English, single-language models can be advantageous compared to multilingual ones in terms of pre-training effort, overall resource efficiency or downstream task performance. Despite the growing popularity of prompt-based LLMs, more compute-efficient BERT-like models remain highly relevant. In this work, we present the first German single-language RoBERTa model, GottBERT, pre-trained exclusively on the German portion of the OSCAR dataset. Additionally, we investigated the impact of filtering the OSCAR corpus. GottBERT was pre-trained using fairseq and standard hyperparameters. We evaluated its performance on two Named Entity Recognition (NER) tasks (Conll 2003 and GermEval 2014) and three text classification tasks (GermEval 2018 fine and coarse, and 10kGNAD) against existing German BERT models and two multilingual models. Performance was measured using the F1 score and accuracy. The GottBERT base and large models showed competitive performance, with GottBERT leading among the base models in 4 of 6 tasks. Contrary to our expectation, the applied filtering did not significantly affect the results. To support the German NLP research community, we are releasing the GottBERT models under the MIT license. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Urban Waterlogging Prediction Based on Feature Extraction and Transfer 2nd

Urban Waterlogging Prediction Based on Feature Extraction an...

引用

2nd International Conference on Frontiers of Energy and Environmental Engineering, CFEEE 2023

作者： Zhang, Zongjia Jian, Xinyao Chen, Yiye Huang, Zhejun Yang, Lili School of Public Management/Emergency Management Jinan University GD 20 Guangzhou China Department of Biostatistics Epidemiology and Informatics Perelman School of Medicine University of Pennsylvania PhiladelphiaPA19104-6021 United States Department of Statistics and Data Science Southern University of Science and Technology GD 755 Shenzhen China Shenzhen Technology Institute of Urban Public Safety and Key Laboratory of Urban Safety Risk Monitoring and Early Warning Ministry of Emergency Management GD 755 Shenzhen China

ISBN: (纸本)9789819703715

In waterlogging prediction, all or part of the real-time waterlogging data may be missing due to sensor failure, too sparse sampling interval setting, or sensor sensitivity problems, resulting in the failure of waterlogging prediction. In this study, we propose an urban waterlogging depth prediction method based on the transfer of waterlogging point feature extraction. The method quantifies the relationship between rainfall and waterlogging depth by extracting and constructing rainfall features at waterlogging points. Using only current or future rainfall data as model input to achieve future waterlogging depth prediction, it can effectively overcome the limitations of sparse distribution of monitoring stations and insufficient current real-time waterlogging data and can achieve more accurate medium-term waterlogging prediction and transfer prediction of water level at potential waterlogging-prone points. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Model LEGO: creating models like disassembling and assembling building blocks 24

Model LEGO: creating models like disassembling and assemblin...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Jiacong Hu Jing Gao Jingwen Ye Yang Gao Xingen Wang Zunlei Feng Mingli Song College of Computer Science and Technology Zhejiang University and State Key Laboratory of Blockchain and Data Security Zhejiang University Robotics Institute School of Computer Science Carnegie Mellon University Electrical and Computer Engineering National University of Singapore Bangsheng Technology Co. Ltd. College of Computer Science and Technology Zhejiang University and Bangsheng Technology Co. Ltd. School of Software Technology Zhejiang University and State Key Laboratory of Blockchain and Data Security Zhejiang University and Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain College of Computer Science and Technology Zhejiang University and State Key Laboratory of Blockchain and Data Security Zhejiang University and Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security

ISBN: (纸本)9798331314385

With the rapid development of deep learning, the increasing complexity and scale of parameters make training a new model increasingly resource-intensive. In this paper, we start from the classic convolutional neural network (CNN) and explore a paradigm that does not require training to obtain new models. Similar to the birth of CNN inspired by receptive fields in the biological visual system, we draw inspiration from the information subsystem pathways in the biological visual system and propose Model Disassembling and Assembling (MDA). During model disassembling, we introduce the concept of relative contribution and propose a component locating technique to extract task-aware components from trained CNN classifiers. For model assembling, we present the alignment padding strategy and parameter scaling strategy to construct a new model tailored for a specific task, utilizing the disassembled task-aware components. The entire process is akin to playing with LEGO bricks, enabling arbitrary assembly of new models, and providing a novel perspective for model creation and reuse. Extensive experiments showcase that task-aware components disassembled from CNN classifiers or new models assembled using these components closely match or even surpass the performance of the baseline, demonstrating its promising results for model reuse. Furthermore, MDA exhibits diverse potential applications, with comprehensive experiments exploring model decision route analysis, model compression, knowledge distillation, and more. For more information, please visit https://***/.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on The Method of Constructing Knowledge Graph of Affective Disorder Based on Multi-Source data Fusion 22

Research on The Method of Constructing Knowledge Graph of Af...

引用

Proceedings of the 5th International Conference on Information Technologies and Electrical Engineering

作者： Yang Wang Weihong Yang School of Artificial Intelligence and Big Data Luzhou Vocational and Technical College China School of Computer Science and Technology Harbin Institute of Technology China

ISBN: (纸本)9781450396806

Affective disorder (Depression) has the characteristics of high incidence rate, low recognition rate, high disability and death rate, and has become a serious public health problem that needs to be solved urgently. It is particularly important to use machine learning and big data mining technology to build a complete knowledge graph of affective disorders. In this paper, multi-source data fusion is used to construct the original corpus of the knowledge graph of affective disorders. In the information extraction stage, we designed a machine learning algorithm based on Hidden Markov Model (HMM). The algorithm can extract entities and entity mapping relationships from corpus to form entity database and triplet relationship database. In the knowledge fusion stage, multi-source heterogeneous knowledge fusion algorithm is used to complete entity alignment and relationship deduction. Finally, the open-source graphic database Neo4j is used as the underlying storage structure, so as to realize the visualization of the knowledge graph of affective disorders.

关键词： Multi-source data Knowledge Graph Affective Disorder Knowledge Fusion Information Extraction

来源：评论

学校读者我要写书评

暂无评论

Laser diode transmission characteristics management for high optical fiber coupling system stability with various spectral wavelength windows

引用

Journal of Optical Communications 2025年

作者： Prabu, Ramachandran Thandaiah Murugesh, Madhini Siddharthan, Niranjana Prabu, Arulraj Simon Kumar, Chandran Ramesh Prathima, Chilukuri Orabi, Orabi Salem Department of ECE Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences SIMATS Saveetha University Tamilnadu Chennai India Department of ECE S.A. Engineering College Tamilnadu Chennai India Department of Artificial Intelligence and Data Science Rajalakshmi Institute of Technology Tamilnadu Chennai India Department of ECE St. Joseph's College of Engineering OMR Tamilnadu Chennai India Department of ECE Panimalar Engineering College Tamilnadu Chennai India Department of Data Science School of Computing Mohan Babu University Andhra Pradesh Tirupati India Light Institute of Engineering Giza Egypt

This paper demonstrated the laser diode transmission characteristics management for high optical fiber coupling system stability with various spectral wavelength windows. Laser beam focus diameter and laser depth of field variations are clarified versus both beam lens diameter and lens focal length at the different spectral operating wavelength windows. Aperture transmission and transmitted power variations are demonstrated versus laser beam aperture diameter and laser power variations at aperture diameter of 1â€¯mm. First and second fiber mode diameter variations are measured versus spectral fiber transmission wavelength for identical and nonidentical two fibers core diameter and numerical aperture. Fiber splice losses are clarified against both lateral offset and angular misalignment for identical and nonidentical fibers core diameter and numerical aperture. Fundamental mode field diameter and V parameter are indicated versus spectral fiber transmission wavelength and numerical aperture variations at fiber core radius of 5â€¯μm. © 2025 Walter de Gruyter GmbH, Berlin/Boston 2025.

关键词： Laser beams

来源：评论

学校读者我要写书评

暂无评论

PIAVE: A Pose-Invariant Audio-Visual Speaker Extraction Network

arXiv

引用

arXiv 2023年

作者： Liu, Qinghua Ge, Meng Wu, Zhizheng Li, Haizhou Shenzhen Research Institute of Big Data Shenzhen China School of Data Science The Chinese University of Hong Kong Shenzhen China Department of Electrical and Computer Engineering National University of Singapore Singapore

It is common in everyday spoken communication that we look at the turning head of a talker to listen to his/her voice. Humans see the talker to listen better, so do machines. However, previous studies on audio-visual speaker extraction have not effectively handled the varying talking face. This paper studies how to take full advantage of the varying talking face. We propose a Pose-Invariant Audio-Visual Speaker Extraction Network (PIAVE) that incorporates an additional pose-invariant view to improve audio-visual speaker extraction. Specifically, we generate the pose-invariant view from each original pose orientation, which enables the model to receive a consistent frontal view of the talker regardless of his/her head pose, therefore, forming a multi-view visual input for the speaker. Experiments on the multi-view MEAD and in-the-wild LRS3 dataset demonstrate that PIAVE outperforms the state-of-the-art and is more robust to pose variations. © 2023, CC BY.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Enhanced Tile Defect Detection with Optimized Cascade R-CNN for Efficient Quality Control

Enhanced Tile Defect Detection with Optimized Cascade R-CNN ...

引用

Pattern Recognition, Machine Vision and Intelligent Algorithms (PRMVIA), International Conference on

作者： Guangya Wang Hanmao Wu Sipeng Wu School of Software South China Normal University Foshan China Aberdeen Institute of Data Science and Artificial Intelligence South China Normal University Foshan China

ISBN: (数字)9798350389746

ISBN: (纸本)9798350389753

With the need for high-speed production in the ceramic tile manufacturing industry, automated quality control becomes critical for enhancing efficiency and reducing costs. Addressing this urgent demand, we have devised a new detection method based on Cascade R-CNN. We improved the model's structure and training methods to match the needs of tile defect detection. Regarding the architecture, we chose ResNeSt as the backbone to enhance feature extraction capabilities, introduced DCN to increase the model's adaptability to target shapes, and integrated a recursive feature pyramid to improve the model's extraction of multi-scale features. In terms of training strategies, we implemented data augmentation and multi-scale training/testing to improve the model's generalization ability and robustness. In addition, online hard example mining was applied during training to address the imbalance between positive and negative samples. Finally, we proved the improvements' effectiveness through ablation and comparative experiments. Compared to Cascade R-CNN, we achieved a 9.0% improvement in mAP, providing reliable and efficient technical support for quality control in the tile manufacturing industry.

关键词： Training Manufacturing industries Adaptation models Shape Tiles Quality control Feature extraction

来源：评论

学校读者我要写书评

暂无评论

CC-GNN: A Community and Contraction-based Graph Neural Network

CC-GNN: A Community and Contraction-based Graph Neural Netwo...

引用

IEEE International Conference on data Mining (ICDM)

作者： Zhiyuan Li Xun Jian Yue Wang Lei Chen The Hong Kong University of Science and Technology Shenzhen Institute of Computing Sciences Data Science and Analytics Thrust The Hong Kong University of Science and Technology (Guangzhou)

Graph Neural Networks (GNNs) have attracted much research interest due to their successful applications on graph-structured data. Despite the effectiveness, due to the data dependency, GNNs are confronted with the neighborhood explosion and over-smoothing problems. Many sampling-based and level-down methods have been proposed to solve the neighborhood explosion problem to boost efficiency. However, they suffer from either poor accuracy or considerable runtime overheads. Moreover, the over-smoothing problem prevents GNNs from exploring more distant neighborhoods effectively. In this paper, we present a Community-and-Contraction-based Graph Neural Network (CC-GNN), which leverages community and contraction to boost the time and space efficiency of GNNs. Specifically, CC-GNN first performs contraction and retrieves the communities as super nodes, and connects them using a tailored similarity function to obtain an informative community contracted graph (CC-Graph). CC-GNN then learns the representations of the super nodes in the CC-Graph, which are used to reconstruct the representations of the original nodes. Finally, CC-GNN explores more distant neighborhoods without additional convolution layers, implicitly alleviating the over-smoothing problem. Since CC-GNN conducts the costly training on a much smaller contracted graph, the efficiency is boosted significantly. Most importantly, we have proved that the information loss of node representations caused by the CC-Graph is bounded. Extensive experimental studies verify the efficiency boost and the effectiveness.

关键词： Training Runtime Convolution Graph neural networks Explosions data mining

来源：评论

学校读者我要写书评

暂无评论

Robust and Interpretable Vector Borne Disease Prediction in IoT-Enabled Edge Networks

Robust and Interpretable Vector Borne Disease Prediction in ...

引用

IEEE Region 10 Symposium

作者： Khushbu Doulani Samarth Sharma Mainak Adhikari Y. Vijayalata Department of Computer Science Indian Institute of Information Technology Lucknow Lucknow India Department of Computer Science and Artificial Intelligence Indian Institute of Information Technology Lucknow Lucknow India School of Data Science Indian Institute of Science Education and Research Thiruvananthapuram Thiruvananthapuram India Department of Computer Science and Engineering Vardhaman College of Engineering Hyderabad India

ISBN: (数字)9798350364866

ISBN: (纸本)9798350364873

Vector-borne diseases have created critical world-wide public health hazards that require innovative approaches for prevention and management. Within the context of IoT-enabled edge networks, this study offers a unique framework to build a reliable and straightforward distant prediction model for vector-borne diseases. The suggested strategy incorporates the use of edge computing capabilities to predict the onset and spread of diseases caused by vectors by using real-time data streams from mobile applications. Employing widely used techniques from machine learning, including interpretable models, our system not only achieves high prediction accuracy but also provides insight into the most important factors influencing the spread of disease. Moreover, this approach overcomes the resource constraints essential to edge networks, ensuring the prediction model's dependability and scalability.

关键词： Accuracy Computational modeling Image edge detection Predictive models Real-time systems data models Vectors Mobile applications Monitoring Diseases

来源：评论

学校读者我要写书评

暂无评论

Focus on the Stability of Large Systems: Toward Automatic Prediction and Analysis of Vulnerability Threat Intelligence 6

Focus on the Stability of Large Systems: Toward Automatic Pr...

引用

6th IEEE International Conference on data science in Cyberspace, DSC 2021

作者： Song, Shiwen Wu, Qiong Zheng, Xin Wang, Peng Dou, Yuchen Li, Zhongwen Zhai, Lidong Institute Of Information Engineering Chinese Academy Of Sciences BeiJing China Bag Data Academy Zhongke Beijing China Institute Of Computing Technology Chinese Academy Of Sciences Cas Key Laboratory Of Network Data Science And Technology Beijing China

ISBN: (纸本)9781665418157

With the increase in the number of users and business volume, the business systems of Internet companies are becoming more and more complex, resulting in a surge in the number of alarms. A large number of dirty alarms add a huge workload to security operations, which indirectly pose a large number of threats to business systems. At present, most systems use the method of accessing third-party Threat Intelligence to assist operators to realize automatic handling of alarms. However, this method has lagging and accuracy problems, making this work always difficult to meet the requirements of fast and accurate. This article proposes a new method for gathering vulnerability Threat Intelligence, which can obtain vulnerability information in advance of security announcements issued by security vendors. By analyzing the vulnerability disclosure process, this method obtains vulnerability information from the original source submitted by open source mail group, of developers. We used NLP technology and XGBoost model to automatically analyze the vulnerability information, and finally generate FINTEL. The experimental result shows that this method has an accuracy of 93%, and can obtain vulnerability information 10h to 7 days before security vendors release. The scope of application covers all open source code repositories and some closed source repositories. © 2021 IEEE.

关键词： Open source software

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：