检索结果-内蒙古大学图书馆

2021 Student Research Workshop, SRW 2021 at the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021

作者： Tokarchuk, Evgeniia Thulke, David Wang, Weiyue Dugast, Christian Ney, Hermann Informatics Institute University of Amsterdam Netherlands Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University Germany

ISBN: (纸本)9781954085558

Data processing is an important step in various natural language processing tasks. As the commonly used datasets in named entity recognition contain only a limited number of samples, it is important to obtain additional labeled data in an efficient and reliable manner. A common practice is to utilize large monolingual unlabeled corpora. Another popular technique is to create synthetic data from the original labeled data (data augmentation). In this work, we investigate the impact of these two methods on the performance of three different named entity recognition tasks. © 2021 Association for Computational Linguistics.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

Position: Social Choice Should Guide AI Alignment in Dealing with Diverse human Feedback 41

Position: Social Choice Should Guide AI Alignment in Dealing...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Conitzer, Vincent Freedman, Rachel Heitzig, Jobst Holliday, Wesley H. Jacobs, Bob M. Lambert, Nathan Mossé, Milan Pacuit, Eric Russell, Stuart Schoelkopf, Hailey Tewolde, Emanuel Zwicker, William S. Foundations of Cooperative AI Lab Computer Science Department Carnegie Mellon University Pittsburgh United States Institute for Ethics in AI University of Oxford Oxford United Kingdom Center for Human-Compatible AI Department of Electrical Engineering and Computer Sciences University of California Berkeley United States Potsdam Institute for Climate Impact Research Brandenburg Potsdam Germany Department of Philosophy University of California Berkeley United States Department of Philosophy and Moral Sciences Ghent University Ghent Belgium Allen Institute for AI BerkeleyCA United States Department of Philosophy University of Maryland College Park United States EleutherAI United States Department of Mathematics Union College Schenectady United States Murat Sertel Center for Advanced Economic Studies Istanbul Bilgi University Istanbul Turkey

Foundation models such as GPT-4 are fine-tuned to avoid unsafe or otherwise problematic behavior, such as helping to commit crimes or producing racist text. One approach to fine-tuning, called reinforcement learning from human feedback, learns from humans' expressed preferences over multiple outputs. Another approach is constitutional AI, in which the input from humans is a list of high-level principles. But how do we deal with potentially diverging input from humans? How can we aggregate the input into consistent data about "collective" preferences or otherwise use it to make collective choices about model behavior? In this paper, we argue that the field of social choice is well positioned to address these questions, and we discuss ways forward for this agenda, drawing on discussions in a recent workshop on Social Choice for AI Ethics and Safety held in Berkeley, CA, USA in December 2023. Copyright 2024 by the author(s)

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

SentinelMet: Enhancing Metaverse Security through Deep Learning Techniques in 6G

SentinelMet: Enhancing Metaverse Security through Deep Learn...

引用

International Symposium on Advanced Networks and Telecommunication Systems (ANTS)

作者： Dikshant Rajput Sunil K. Singh Sudhakar Kumar Harshit Vashisht Kwok Tai Chui Brij B. Gupta Chandigarh College of Engineering and Technology Chandigarh India Hong Kong Metropolitan University (HKMU) Hong Kong Department of Computer Science and Information Engineering Asia University Taichung Taiwan University of Economics and Human Science Warsaw Poland

ISBN: (数字)9798350391725

ISBN: (纸本)9798350391732

With the increasing demand for robust security in the rapidly expanding metaverse within 6 G networks, advanced intrusion detection systems (IDS) are becoming essential. This paper introduces a novel hybrid intrusion detection framework that combines Gaussian Mixture Clustering with Random Forest classifiers and KMeans Clustering with Random Forest classifiers. These models are evaluated for their effectiveness in identifying complex intrusion patterns. The hybrid approaches demonstrated high detection rates, with the Gaussian Mixture Clustering ensemble achieving a detection rate of 99.5-99.6%, while the KMeans clustering model achieved a detection rate of $\mathbf{9 8 - 9 9 \%}$. Comparative analysis shows that these models enhance detection performance while maintaining robustness in a dynamic and diverse metaverse landscape.

关键词： Deep learning Analytical models Accuracy Metaverse Intrusion detection Robustness Telecommunications Security Random forests Resilience

来源：评论

学校读者我要写书评

暂无评论

UDON: Unsupervised Data SelectiON for Biomedical Entity Recognition 2021

UDON: Unsupervised Data SelectiON for Biomedical Entity Reco...

引用

2021 4th International Conference on Computing and Big Data

作者： Arda Akdemir Tetsuo Shibuya Department of Computer Science Division of Medical Data InformaticsHuman Genome CenterUniversity of Tokyo Japan

ISBN: (纸本)9781450387194

High-quality training datasets are critical for building successful Machine Learning (ML) based NLP systems. However, these datasets are not always available in low-resource contexts such as the biomedical domain. Here, selecting relevant training data is as important as the choice of the ML model. In this study we propose UDON: Unsupervised Data selectiON for biomedical entity recognition using domain-specific pretrained Language Models (LMs). We first show that pretrained LMs succeed at implicitly learning the differences between datasets without any supervision, and then use these models to select relevant data instances. Next, we evaluate the proposed methods for entity recognition on seven biomedical datasets and one news domain dataset using four LMs and three selection methods. Our results show that using pretrained domain-specific LMs for data selection outperforms all other approaches. Finally, we use domain classification as an auxiliary task for pretraining the neural network on the in-domain dataset and show this yields further improvements.

关键词： biomedical entity recognition data selection deep learning language model named entity recognition natural language processing

来源：评论

学校读者我要写书评

暂无评论

Revisiting Checkpoint Averaging for Neural Machine Translation

arXiv

引用

arXiv 2022年

作者： Gao, Yingbo Herold, Christian Yang, Zijian Ney, Hermann Human Language Technology and Pattern Recognition Group Computer Science Department RWTH Aachen University Germany

Checkpoint averaging is a simple and effective method to boost the performance of converged neural machine translation models. The calculation is cheap to perform and the fact that the translation improvement almost comes for free, makes it widely adopted in neural machine translation research. Despite the popularity, the method itself simply takes the mean of the model parameters from several checkpoints, the selection of which is mostly based on empirical recipes without many justifications. In this work, we revisit the concept of checkpoint averaging and consider several extensions. Specifically, we experiment with ideas such as using different checkpoint selection strategies, calculating weighted average instead of simple mean, making use of gradient information and fine-tuning the interpolation weights on development data. Our results confirm the necessity of applying checkpoint averaging for optimal performance, but also suggest that the landscape between the converged checkpoints is rather flat and not much further improvement compared to simple averaging is to be obtained. Copyright © 2022, The Authors. All rights reserved.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

iFBI: Lightweight Breed and Individual Recognition for Cats and Dogs

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Zhang, Yuanze Zhang, Yimeng Li, Kexu Luo, Jinpeng Liu, Gang Pan, Rong Xidian University Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province School of Computer Science and Technology Xi’an 710126 China

As the pet industry develops, fine-grained breed recognition and individual recognition have emerged as essential components in biometric measurement systems for intelligent pet monitoring, aiming to identify the specific breed of a pet in an image and to recognize the same individual across multiple images. These capabilities lay the foundation for downstream tasks such as posture estimation and emotion analysis, supporting a wide range of real-world applications. Despite the substantial advancements achieved in existing research, two critical issues remain to be solved: the diversity of object poses affects representation in complex scenarios, and the conflict between model complexity and performance hinders application in resource-constrained conditions. To address the above issues, we propose an integrated Face-and-Body Information for Lightweight Breed and Individual Recognition (iFBI) scheme that integrates multiple pose information by a lightweight model. Specifically, a Face Alignment (FA) module and a Body Posture-Guided (BPG) module are proposed to separate face and body information from the input images, fully capturing the posture details while suppressing background areas. To further maximize the discrimination between individual samples, we design a Multi-level Representation Recognition (MRR) module that dynamically integrates complementary semantic features of face and body, consequently generating more discriminative features. In addition, a Dynamic Convolutional Model Compression (DCMC) method is implemented with an improved dual-branch backbone that significantly reduces computational costs while enhancing model performance. Extensive experiments on two self-built datasets, Pet with Fine-grained Breed Dataset (Pet-FB) and Pet with Diverse Posture Dataset (Pet-DP), and four public datasets indicate that iFBI yields superior performance in both fine-grained breed recognition and individual recognition tasks. The source code and self-built datasets—P

关键词： Face alignment Fine-grained breed recognition Individual recognition Lightweight

来源：评论

学校读者我要写书评

暂无评论

Correction to: Object search by a concept-conditioned object detector (Neural Computing and Applications, (2024), 36, 26, (16001-16021), 10.1007/s00521-024-09914-5)

引用

Neural Computing and Applications 2025年 1-2页

作者： Rigoni, Davide Serafini, Luciano Sperduti, Alessandro Department of Mathematics "Tullio Levi-Civita" University of Padova Via Trieste 63 PD Padua35131 Italy Human Inspired Technology Research Centre University of Padova Via Luzzatti 4 PD Padua35121 Italy Augmented Intelligence Center Bruno Kessler Foundation Via Sommarive 18 TN Povo38123 Italy Department of Pharmaceutical and Pharmacological Sciences University of Padova Via Marzolo 5 PD Padua35131 Italy Department of Information Engineering and Computer Science University of Trento Via Sommarive 9 TN Povo38123 Italy

Correction To: Neural Computing and Applications (2024) 36:16001–16021 https://***/10.1007/s00521-024-09914-5 In this article, the sentence ‘The models conditioned with the concepts are highlighted with the dove gray color’ in the footnote of Tables 1, 4 and 5 should be removed. Similarly, the sentence ‘Concept-conditioned models are highlighted with the dove gray color’ in the footnote of Tables 2 and 3 should be removed. In the section ‘Standard vs. concept-conditioned object detectors before filtering’, the sentence ‘Models conditioned with the concepts are highlighted with the dove gray color’ should be removed. The original article has been corrected. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Shallow Hierarchical CNN-LSTM for Activity Recognition to Integrate Postural Transition States

Shallow Hierarchical CNN-LSTM for Activity Recognition to In...

引用

IEEE SENSORS

作者： Douglas Tilley Uriel Martinez-Hernandez Department of Computer Science University of Bath Bath UK EEE Department ART-AI Multimodal Interaction and Robot Active Perception (inte-R-action) Lab University of Bath UK Department of Electronic and Electrical Engineering University of Bath Bath UK

This paper presents an approach to enhance classification accuracy of human Activity Recognition (HAR) datasets using a shallow hierarchical method, comprised of 2 Convolutional layers and 1 LSTM Layer, to identify transition tasks. The designed model was tested on the human Activity and Postural Transition (HAPT) dataset from the University of California, Irvine, achieving an accuracy of 93 %, demonstrating it's efficacy in correctly identifying a variety of human activities, including the postural transition states. An F1 score of 85 % was attained, highlighting a reliable method of reducing false positives on an unbalanced dataset. The performance on these metrics showcases the model's reliability and proficiency in classifying activities within unbalanced datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design Safety Training Using Extended Reality Tracking Tools in Semiconductor Fabrication Laboratory Furnace 11th

Design Safety Training Using Extended Reality Tracking Tools...

引用

11th International Conference on Robotics, Vision, Signal Processing and Power Applications, RoViSP 2021

作者： Alnagrat, Ahmed Jamah Ahmed Ismail, Rizalafande Che Idrus, Syed Zulkarnain Syed Faculty of Applied and Human Sciences Universiti Malaysia Perlis Perlis Arau Malaysia Department of Computer Science and Information Technology Higher Institute of Science and Technology Wadi al-Shati Fezzan Libya School of Computing and Informatics Albukhary International University Kedah Alor Setar Malaysia

ISBN: (纸本)9789811681288

Due to the possibilities provided by such technologies to provide people with live immersive virtual worlds, Extended Reality (XR) technologies such as virtual (VR), augmented (AR), and mixed reality (MR) have grown. The role of XR has a highly effective and efficient technology in virtual laboratories (VL) as experiments can be performed almost anywhere. During the laboratory activities, students are facing the issue of dealing with dangerous equipment such as Semiconductor fabrication furnace, which has a high temperature. In recent years, modern sensors such as Leap Motion Controller can track human movements and analyses the accuracy. This work presents a novelty approach of design training that can tracks body movements. Moreover, it provides warring alerts to trainer when it comes closer to dangerous places. While she/he is making wrong hand/body movement. When user do the experiment a semiconductor furnace training is operation in a VL. To illustrate more, this training enables the trainee to prevent his/her burning during the experiment according to safety and social distancing standards as well. Thus, Unity 3D has the capability to measure the following: accuracy, quality and efficiency of the system. XR training is significantly considering as safe technology to avoid user’s accidents. To conclude, in the field of human-computer interaction (HCI), the analysis has been improved the training movement in terms of accuracy and interactivity respectively. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Exploring Uni-manual Around Ear Off-Device Gestures for Earables

arXiv

引用

arXiv 2024年

作者： Shimon, Shaikh Shawon Arefin Neshati, Ali Sun, Junwei Xu, Qiang Zhao, Jian School of Computer Science University of Waterloo 200 University Ave W WaterlooON Canada Ontario Tech University 2000 Simcoe St N OshawaONL1G 0C5 Canada Huawei Human-Machine Interaction Lab 19 Allstate Pkwy MarkhamON Canada School of Computer Science University of Waterloo 200 University Ave W WaterlooONN2L 3G1 Canada

Small form factor limits physical input space in earable (i.e., ear-mounted wearable) devices. Off-device earable inputs in alternate mid-air and on-skin around-ear interaction spaces using uni-manual gestures can address this input space limitation. Segmenting these alternate interaction spaces to create multiple gesture regions for reusing off-device gestures can expand earable input vocabulary by a large margin. Although prior earable interaction research has explored off-device gesture preferences and recognition techniques in such interaction spaces, supporting gesture reuse over multiple gesture regions needs further exploration. We collected and analyzed 7560 uni-manual gesture motion data from 18 participants to explore earable gesture reuse by segmentation of on-skin and mid-air spaces around the ear. Our results show that gesture performance degrades significantly beyond 3 mid-air and 5 on-skin around-ear gesture regions for different uni-manual gesture classes (e.g., swipe, pinch, tap). We also present qualitative findings on most and least preferred regions (and associated boundaries) by end-users for different uni-manual gesture shapes across both interaction spaces for earable devices. Our results complement earlier elicitation studies and interaction technologies for earables to help expand the gestural input vocabulary and potentially drive future commercialization of such devices. © 2024, CC BY.

关键词： Digital storage

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：