检索结果-内蒙古大学图书馆

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Yu, Erxin Li, Jing Xu, Chunpu Department of Computing The Hong Kong Polytechnic University Hong Kong Research Centre for Data Science & Artificial Intelligence Hong Kong

ISBN: (纸本)9782493814104

Social media platforms are daily exhibiting millions of events. To preliminarily predict the mainstream public reaction to these events, we study trendy response prediction to automatically generate top-liked user replies to social media events. While previous works focus on generating responses without factoring in popularity, we propose Popularity-Aligned Language Models (PopALM) to distinguish responses liked by a larger audience through reinforcement learning. Recognizing the noisy labels from user "likes", we tailor-make curriculum learning in proximal policy optimization (PPO) to help models capture the essential samples for easy-to-hard training. In experiments, we build a large-scale Weibo dataset for trendy response prediction, and its results show that PopALM can help boost the performance of advanced language models. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Correcting Pronoun Homophones with Subtle Semantics in Chinese Speech Recognition 30

Correcting Pronoun Homophones with Subtle Semantics in Chine...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Zhang, Zhaobo Gan, Rui Yuan, Pingpeng Jin, Hai National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Laboratory Cluster and Grid Computing Laboratory Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9782493814104

Speech recognition is becoming prevalent in daily life. However, due to the similar semantic context of the entities and the overlap of Chinese pronunciation, the pronoun homophone, especially "他/她/它 (he/she/it)", (their pronunciation is "Tā") is usually recognized incorrectly. It poses a challenge to automatically correct them during the post-processing of Chinese speech recognition. In this paper, we propose three models to address the common confusion issues in this domain, tailored to various application scenarios. We implement the language model, the LSTM model with semantic features, and the rule-based assisted Ngram model, enabling our models to adapt to a wide range of requirements, from high-precision to low-resource offline devices. The extensive experiments show that our models achieve the highest recognition rate for "Tā" correction with improvements from 70% in the popular voice input methods up to 90%. Further ablation analysis underscores the effectiveness of our models in enhancing recognition accuracy. Therefore, our models improve the overall experience of Chinese speech recognition of "Tā" and reduce the burden of manual transcription corrections. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Soft-GNN:towards robust graph neural networks via self-adaptive data utilization

引用

Frontiers of Computer Science 2025年第4期19卷 1-12页

作者： Yao WU Hong HUANG Yu SONG Hai JIN National Engineering Research Center for Big Data Technology and System Service Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China College of Information and Communication National University of Defense TechnologyWuhan 430019China Department of Computer Science and Operations Research Universitéde MontréalMontreal H3C 3J7Canada

Graph neural networks(GNNs)have gained traction and have been applied to various graph-based data analysis tasks due to their high ***,a major concern is their robustness,particularly when faced with graph data that has been deliberately or accidentally polluted with *** presents a challenge in learning robust GNNs under noisy *** address this issue,we propose a novel framework called Soft-GNN,which mitigates the influence of label noise by adapting the data utilized in *** approach employs a dynamic data utilization strategy that estimates adaptive weights based on prediction deviation,local deviation,and global *** better utilizing significant training samples and reducing the impact of label noise through dynamic data selection,GNNs are trained to be more *** evaluate the performance,robustness,generality,and complexity of our model on five real-world datasets,and our experimental results demonstrate the superiority of our approach over existing methods.

关键词： graph neural networks node classification label noise robustness

来源：评论

学校读者我要写书评

暂无评论

Aerial Image-Based Semantic Segmentation for Forest Fire Identification

Aerial Image-Based Semantic Segmentation for Forest Fire Ide...

引用

2023 International Conference on Artificial Intelligence Robotics, Signal and Image Processing, AIRoSIP 2023

作者： Salma, Nadilla Asyifa Sulistiyo, Mahmud Dwi Risnandar Sthevanie, Febryanti Wulandari, Gia Septiana Telkom University School of Computing Bandung Indonesia Telkom University Research Center for Data and Information Sciences Brin School of Computing Bandung Indonesia

ISBN: (纸本)9798350327472

Fire is a serious disaster because it can endanger the safety of living things and cause great losses. Detection of forest fires using sensor-based devices or through analysis of weather data becomes less efficient because it is not real-time, its scope depends on sensor deployment, and sometimes it misses small fire spreads that are potentially dangerous. The key idea in this paper is to utilize a semantic segmentation approach to precisely detect forest fires and thus prevent the spread of larger fires. The proposed method uses aerial images since it is a practical way to tackle problems in fire monitoring and detection. Since similar research is still limited, let alone necessary to be implemented in countries potentially susceptible to forest fires, this study demonstrates deep learning-based semantic segmentation methods as preliminary research for identifying forest fires. We analyzed the implementation of the well-known FCN and U-Net models with some backbone options and used the FLAME dataset to train the models and evaluate them quantitatively. Based on the experimental results, FCN with VGG-16 backbone became the model with the highest Mean IoU value of 0.825. We also tested the best model on several aerial images arbitrarily taken from the internet to see the qualitative performance and analyze its possibility of being applied to situations outside the research dataset. © 2023 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Copy-Move Forgery Detection Optimization Using Harmony Search with Clonal Selection Algorithm 6

Copy-Move Forgery Detection Optimization Using Harmony Searc...

引用

6th IEEE International Conference on Artificial Intelligence in Engineering and Technology, IICAIET 2024

作者： Hijazi, Mohd Hanafi Ahmad Josmin, Ezlyn Sherlyn Data Technology and Applications Research Group Creative Advanced Machine Intelligence Research Center Faculty of Computing and Informatics Universiti Malaysia Sabah Kota Kinabalu Malaysia

ISBN: (纸本)9798350389692

In today's world, where technology is advancing rapidly, the extensive use of digital images on social media brings up concerns about their authenticity. One common form of deception is image forgery, especially copy-move forgery, where parts of an image are duplicated and inserted elsewhere within the same image. Traditional detection methods, like randomized search algorithms, often struggle with adaptability. This study presents a new approach that uses the Harmony Search with Clonal Selection Algorithm (HSCSA) to improve the detection of copy-move forgeries by fine -tuning the hyperparameters of Convolutional Neural Network (CNN) models. Our method involves preprocessing the CoMoFoD dataset, optimizing essential hyperparameters using HSCSA, and comparing the performance of the optimized model with standard CNN models. The results showed a notable improvement, with accuracy rising from 67.72% to 78.20%. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Evaluating RISC-V Vector Instruction Set Architecture Extension with Computer Vision Workloads

引用

Journal of Computer Science & Technology 2023年第4期38卷 807-820页

作者：李若时彭平邵志远金海郑然 National Engineering Research Center for Big Data Technology and System Huazhong University of Science and Technology Wuhan 430074China Services Computing Technology and System Laboratory Huazhong University of Science and TechnologyWuhan 430074 China Cluster and Grid Computing Lab Huazhong University of Science and TechnologyWuhan 430074China

Computer vision(CV)algorithms have been extensively used for a myriad of applications *** the multimedia data are generally well-formatted and regular,it is beneficial to leverage the massive parallel processing power of the underlying platform to improve the performances of CV *** Instruction Multiple data(SIMD)instructions,capable of conducting the same operation on multiple data items in a single instruction,are extensively employed to improve the efficiency of CV *** this paper,we evaluate the power and effectiveness of RISC-V vector extension(RV-V)on typical CV algorithms,such as Gray Scale,Mean Filter,and Edge *** our examinations,we show that compared with the baseline OpenCV implementation using scalar instructions,the equivalent implementations using the RV-V(version 0.8)can reduce the instruction count of the same CV algorithm up to 24x,when processing the same input ***,the actual performances improvement measured by the cycle counts is highly related with the specific implementation of the underlying RV-V *** our evaluation,by using the vector co-processor(with eight execution lanes)of Xuantie C906,vector-version CV algorithms averagely exhibit up to 2.98x performances speedups compared with their scalar counterparts.

关键词： RISC-V vector extension single instruction multiple data(SIMD) computer vision OpenCV

来源：评论

学校读者我要写书评

暂无评论

InDNI: An Infection Time Independent Method for Diffusion Network Inference 1

引用

28th China Conference on Information Retrieval, CCIR 2022

作者： Chen, Guoxin Wang, Yongqing Shao, Jiangli Shi, Boshen Shen, Huawei Cheng, Xueqi Data Intelligence System Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (数字)9783031247552

ISBN: (纸本)9783031247545

Diffusion network inference aims to reveal the message propagation process among users and has attracted many research interests due to the fundamental role it plays in some real applications, such as rumor-spread forecasting and epidemic controlling. Most existing methods tackle the task with exact node infection time. However, collecting infection time information is time-consuming and labor-intensive, especially when information flows are huge and complex. To combat the problem, we propose a new diffusion network inference algorithm that only relies on infection states. The proposed method first encodes several observation states into a node infection matrix and then obtains the node embedding via the variational autoencoder (VAE). Nodes with the least Wasserstein distance of embeddings are predicted for existing propagation edges. Meanwhile, to reduce the complexity, a novel clustering-based filtering strategy is designed for selecting latent propagation edges. Extensive experiments show that the proposed model outperforms the state-of-the-art infection time independent models while demonstrating comparable performance over infection time based models. © 2023, Springer Nature Switzerland AG.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Optimizing ASReview Simulations:A generic Multiprocessing Solution for“Light-data'and“Heavy-data'Users

引用

data Intelligence 2024年第2期6卷 320-343页

作者： Sergei Romanov Abel Soares Siqueira Jonathan de Bruin Jelle Teijema Laura Hofstee Rens van de Schoot Applied Data Science Department of Information and Computing ScienceFaculty of ScienceUtrecht University Netherlands eScienceCenter AmsterdamNL Department of Research and Data Management Services Information Technology ServicesUtrecht UniversityUtrechtthe Netherlands Department of Methodology and Statistics Faculty of Social and Behavioral SciencesUtrecht University

Active learning can be used for optimizing and speeding up the screening phase of systematic *** simulation studies mimicking the screening process can be used to test the performance of different machine-learning models or to study the impact of different training *** paper presents an architecture design withamultiprocessing computational strategyforrunningmanysuch simulation studiesinparallel,using the ASReview Makita workflow generator and Kubernetes software for deployment with cloud *** provide a technical explanation of the proposed cloud architecture and its *** addition to that,we conducted 1140 simulations investigating the computational time using various numbers of CPUs and RAM *** analysis demonstrates the degree to which simulations can be accelerated with multiprocessing computing *** parallel computation strategy and the architecture design that was developed in the present paper can contribute to future research with more optimal simulation time and,at the same time,ensure the safe completion of the needed processes.

关键词： Active learning Systematic review Simulation study Multiprocessing Cloud architecture

来源：评论

学校读者我要写书评

暂无评论

Massively parallel algorithms for fully dynamic all-pairs shortest paths

引用

Frontiers of Computer Science 2024年第4期18卷 201-203页

作者： Chilei WANG Qiang-Sheng HUA Hai JIN Chaodong ZHENG National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China State Key Laboratory for Novel Software Technology Nanjing UniversityNanjing 210023China

1 Introduction In recent years,the Massively Parallel Computation(MPC)model has gained significant ***,most of distributed and parallel graph algorithms in the MPC model are designed for static graphs[1].In fact,the graphs in the real world are constantly *** size of the real-time changes in these graphs is smaller and more *** graph algorithms[2,3]can deal with graph changes more efficiently[4]than the corresponding static graph ***,most studies on dynamic graph algorithms are limited to the single machine ***,a few parallel dynamic graph algorithms(such as the graph connectivity)in the MPC model[5]have been proposed and shown superiority over their parallel static counterparts.

关键词： dynamic shortest gained

来源：评论

学校读者我要写书评

暂无评论

TIGA: Towards Efficient Near data Processing in SmartNICs-based Disaggregated Memory Systems 24

TIGA: Towards Efficient Near Data Processing in SmartNICs-ba...

引用

61st ACM/IEEE Design Automation Conference, DAC 2024

作者： Duan, Zhuohui Yu, Zelin Liu, Haikun Liao, Xiaofei Jin, Hai Zheng, Shijie Wu, Sihan National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9798400706011

Memory disaggregation, facilitated by Smart Network Interface Cards (SmartNICs), has emerged as a cost-effective approach for sharing memory resources in data centers. However, current SoC-based SmartNICs face several challenges for supporting near-data processing (NDP) in disaggregated memory (DM) systems effectively, such as inefficient resource allocation for SmartNICs employed in NDP, and the lack of collaboration between SmartNICs on data nodes and CPUs on compute nodes. To address these issues, we propose TIGA, an efficient NDP framework for SmartNICs-based disaggregated memory systems. We propose an adaptive resource allocator to fully utilize the SoC cores among NDP engines automatically, and a SmartNIC-CPU cooperative computing mechanism to schedule NDP tasks among CPUs and SmartNICs. We prototype TIGA with FPGAs and evaluate it with several typical workloads. Experimental results show that TIGA significantly improves the efficiency of NDP tasks in DM systems compared with state-of-the-art SmartNIC-based co-processing schemes. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Storage allocation (computer)

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：