检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Furumai, Kazuaki Legaspi, Roberto Vizcarra, Julio Yamazaki, Yudai Nishimura, Yasutaka Semnani, Sina J. Ikeda, Kazushi Shi, Weiyan Lam, Monica S. Human-Centered AI Laboratories KDDI Research Inc. Saitama Japan Computer Science Department Stanford University Stanford CA United States

Persuasion plays a pivotal role in a wide range of applications from health intervention to the promotion of social good. Persuasive chatbots employed responsibly for social good can be an enabler of positive individual and social change. Existing methods rely on fine-tuning persuasive chatbots with task-specific training data which is costly, if not infeasible, to collect. Furthermore, they employ only a handful of pre-defined persuasion strategies. We propose PersuaBot, a zero-shot chatbot based on Large Language Models (LLMs) that is factual and more persuasive by leveraging many more nuanced strategies. PersuaBot uses an LLM to first generate natural responses, from which the strategies used are extracted. To combat hallucination of LLMs, Persuabot replace any unsubstantiated claims in the response with retrieved facts supporting the extracted strategies. We applied our chatbot, PersuaBot, to three significantly different domains needing persuasion skills: donation solicitation, recommendations, and health intervention. Our experiments on simulated and human conversations show that our zero-shot approach is more persuasive than prior work, while achieving factual accuracy surpassing state-of-the-art knowledge-oriented chatbots. © 2024, CC BY.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Modeling Hierarchical Reasoning Chains by Linking Discourse Units and Key Phrases for Reading Comprehension 29

Modeling Hierarchical Reasoning Chains by Linking Discourse ...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Chen, Jialin Zhang, Zhuosheng Zhao, Hai School of Mathematical Sciences Shanghai Jiao Tong University China Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China

Machine reading comprehension (MRC) poses new challenges over logical reasoning, which aims to understand the implicit logical relations entailed in the given contexts and perform inference over them. Due to the complexity of logic, logical relations exist at different granularity levels. However, most existing methods of logical reasoning individually focus on either entity-aware or discourse-based information but ignore the hierarchical relations that may even have mutual effects. In this paper, we propose a holistic graph network (HGN) which deals with context at both discourse level and word level, as the basis for logical reasoning, to provide a more fine-grained relation extraction. Specifically, node-level and type-level relations, which can be interpreted as bridges in the reasoning process, are modeled by a hierarchical interaction mechanism to improve the interpretation of MRC systems. Experimental results on logical reasoning QA datasets (ReClor and LogiQA) and natural language inference datasets (SNLI and ANLI) show the effectiveness and generalization of our method, and in-depth analysis verifies its capability to understand complex logical relations. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing STEM Education with ChatGPT: A Case Study on Developing Practice Assessments for C Programming 13

Enhancing STEM Education with ChatGPT: A Case Study on Devel...

引用

13th IEEE International Conference on Engineering Education, ICEED 2024

作者： Ismail, Shereen Lynch, Jenice Alghazo, Runna University of Michigan Merit Network Inc. MI48108 United States School of Electrical Engineering and Computer Science University of North Dakota ND58202 United States College of Education & Human Development University of North Dakota Department of Education Health & Behavioral Studies ND58202 United States

ISBN: (纸本)9798350367416

ChatGPT has proven its effectiveness as an assistance tool in the learning process for students. In this paper, an experiment was designed using ChatGPT to generate practice problems aligned with specific course objectives for a computer science (CS) introductory programming course, focusing on assessment questions in the form of short answer questions (SAQ) and multiple choice questions (MCQ). The paper aims to investigate how ChatGPT can assist educators in generating high quality assessment questions that align with course objectives. The evaluation is done by specialized educators. The findings demonstrate that ChatGPT offers valuable support for teachers in establishing coherent practice exam items that align with course objectives;however, caution must be used when utilizing ChatGPT to create assessment questions to ensure they are error-free and match the evaluation rubric. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Conversational Product Recommendation using LLM

Conversational Product Recommendation using LLM

引用

Electronic Communications, Internet of Things and Big Data (ICEIB), International Conference on

作者： Ting-Jui Chang Lydia Hsiao-Mei Lin Richard Tzong-Han Tsai Department of Computer Science and Information Engineering National Central University Taoyuan Taiwan Department of Interaction Design National Taipei University of Technology Taipei Taiwan Research Center for Humanities and Social Sciences Academia Sinica Taipei Taiwan

ISBN: (数字)9798350360721

ISBN: (纸本)9798350360738

It is expected to deploy chatbots as sales assistants on e-commerce platforms soon. In recent years, the capabilities demonstrated by large language models (LLMs) indicate their suitability for this role. However, a dialogue process is not fully established. Most existing works concentrate on searching for ideal products, such as Retrieval-Augmented Generation (RAG) and product search. Many proposed methods rely on product reviews. However, in the case of some e-commerce platform products, valuable reviews are often lacking, rendering these approaches impractical. Thus, we studied how to assist users and select a set of candidate products. Accordingly, we simulated sales conversations based on the product features provided by the seller, using LLM and reliable content while addressing the cold-start problem. Specifically, we used product features to generate customer persona for user simulation. LLM was used to play the role of sales assistant in giving recommendations. The experimental results showed that practical conversation was created between customers and chatbots in Traditional Chinese. The code and results are available at: https://***/terryobe-ncu/CPR_LLM

关键词： Reviews Large language models Oral communication Chatbots Rendering (computer graphics) Question generation Safety

来源：评论

学校读者我要写书评

暂无评论

To Mask or Not To Mask? A Machine Learning Approach to Covid News Coverage Attitude Prediction Based on Time Series and Text Content

To Mask or Not To Mask? A Machine Learning Approach to Covid...

引用

IEEE International Conference on Computational science and Engineering, CSE

作者： Jingtian Zhao Will Zhao Yimin Yang Amin Safaei Ruizhong Wei Department of Computer Science Lakehead University Canada Stratford School of Interaction Design and Business University of Waterloo Canada Department of Electrical and Computer Engineering University of Western Ontario Canada

In the past few decades, with the explosion of information, a large number of computer scientists have devoted themselves to analyzing collected data and applying these findings to many disciplines. Natural language processing (NLP) has been one of the most popular areas for data analysis and pattern recognition. A significantly large amount of data is obtained in text format due to the ease of access nowadays. Most modern techniques focus on exploring large sets of textual data to build forecasting models; they tend to ignore the importance of temporal information which is often the main ingredient to determine the performance of analysis, especially in the public policy view. The contribution of this paper is two-fold. First, a dataset called COVID-News is collected from three news agencies, which consists of article segments related to wearing masks during the COVID-19 pandemic. Second, we propose a long-short term memory (LSTM)-based learning model to predict the attitude of the articles from the three news agencies towards wearing a mask with both temporal and textural information. Experimental results on COVID-News dataset show the effectiveness of the proposed LSTM-based algorithm.

关键词： COVID-19 Training Analytical models Scientific computing Time series analysis Machine learning Predictive models

来源：评论

学校读者我要写书评

暂无评论

Shared Bodily Fusion: Leveraging Inter-Body Electrical Muscle Stimulation for Social Play

Shared Bodily Fusion: Leveraging Inter-Body Electrical Muscl...

引用

2024 ACM Designing Interactive Systems Conference, DIS 2024

作者： Patibanda, Rakesh Overdevest, Nathalie Nisal, Shreyas Saini, Aryan Elvitigala, Don Samitha Knibbe, Jarrod van den Hoven, Elise Mueller, Florian Exertion Games Lab Department of Human-Centred Computing Monash University Melbourne Australia School of Electrical Engineering and Computer Science Faculty of Engineering The University of Queensland St LuciaQLD Australia Materialising Memories & Visualisation Institute University of Technology Sydney Sydney Australia Eindhoven University of Technology Eindhoven Netherlands

ISBN: (纸本)9798400705830

Traditional games like "Tag" rely on shared control via inter-body interactions (IBIs) – touching, pushing, and pulling – that foster emotional and social connection. Digital games largely limit IBIs, with players using their bodies as input to control virtual avatars instead. Our "Shared Bodily Fusion" approach addresses this by fusing players’ bodies through a mediating computer, creating a shared input and output system. We demonstrate this approach with "Hidden Touch", a game where a novel social electrical muscle stimulation system transforms touch (input) into muscle actuations (output), facilitating IBIs. Through a study (n=27), we identifed three player experience themes. Informed by these fndings and our design process, we mapped their trajectories across our three experiential spaces – threshold, tolerance, and precision – which collectively form our design framework. This framework facilitates the creation of future digital games where IBIs are intrinsic, ultimately promoting the many benefts of social play. © 2024 Copyright held by the owner/author(s).

关键词： Muscle

来源：评论

学校读者我要写书评

暂无评论

Robust Phishing Detection in Consumer IoT Devices with ANOVA F-Test and Satin Bowerbird Optimization of Deep Learning Model

Robust Phishing Detection in Consumer IoT Devices with ANOVA...

引用

2025 IEEE International Conference on Consumer Electronics, ICCE 2025

作者： Gupta, Brij B. Gaurav, Akshat Chui, Kwok Tai Department of Computer Science and Information Engineering Asia University Taichung413 Taiwan University of Economics and Human Science Warsaw Poland Ronin Institute MontclairNJ United States Hong Kong

ISBN: (纸本)9798331521165

Combining ANOVA F-Test for feature selection with Satin Bowerbird Optimization (SBO) for hyperparameter tuning of a deep learning model, our proposed model delivers a strong phishing detection model for consumer IoT devices. In terms of accuracy and loss, the suggested CNN model, optimized using SBO, outfits GRU, LSTM, and RNN models. With a significant loss decrease, the model had a high accuracy of 92% and proved effective in spotting phishing attempts. Comprehensive assessments including feature selection, correlation analysis, and performance comparisons indicate the model's excellence in both training and testing stages, therefore providing an efficient means of improving security in IoT systems. This solution offers a scalable and effective means of phishing detection for smart home appliances. © 2025 IEEE.

关键词： Analysis of variance (ANOVA)

来源：评论

学校读者我要写书评

暂无评论

Beyond a One-Size-Fits-All Approach: Towards Personalizing Multi-device Setups in Crowdwork

Beyond a One-Size-Fits-All Approach: Towards Personalizing M...

引用

Adjunct Proceedings of the 2022 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the 2022 ACM International Symposium on Wearable computers

作者： Senjuti Dutta Rhema Linder Scott Ruoti Alex Williams Anastasia Kuzminykh Department of Electrical Engineering and Computer Science University of Tennessee Knoxville United States Department of Electrical Engineering and Computer Science The University of Tennessee United States Electrical Engineering and Computer Science The University of Tennessee United States Human-in-the-Loop and Machine Learning Amazon United States Faculty of Information University of Toronto Canada

ISBN: (纸本)9781450394239

Non-workstation devices provide mobility in the sense that they enable work and play in less constrained environments and configurations. Workers have different needs and preferences in terms of work practices that impact work-life balance. One way to increase mobility is to allow for more choices in both workstation and non-workstation devices. This paper investigates whether workers’ preferences for using different devices are distinct. To understand whether these differences in preference exist, we use data from an exploratory qualitative survey of 150 crowdworkers from Amazon Mechanical Turk. We first identify the aspects that influence crowdworkers’ preferences in using non-workstation devices. Next, our thematic analysis of open-ended data indicates that different workers have different preferences for multi-device configuration. Finally, this leads to a discussion of how people have different preferences which would require different non-workstation devices.

关键词： Crowdwork human Intelligence Tasks Personalizing multi-device

来源：评论

学校读者我要写书评

暂无评论

To Understand the Critical Measures of Enhanced Security in Cloud Computing for Creating Better Data Protection 2

To Understand the Critical Measures of Enhanced Security in ...

引用

2nd International Conference on Advance Computing and Innovative Technologies in Engineering, ICACITE 2022

作者： Lourens, Melanie Neela, V. Jambukesh, H.J. Khan, Huma Pant, Bhasker Durban University of Technology Department of Human Resources Management South Africa School of Computing and Information Technology Reva University Bengaluru India Government Engineering College Electronics and Communication Haveri India CSE Rcet Bhilai India Jazan University Computer Science Department Jizan Saudi Arabia Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun India

ISBN: (纸本)9781665437899

Today, the use of cloud computing for better data protection has been increased to a great extent. One of the essential reasons for using cloud computing as a means of data protection is that users can easily access relevant data with the proper security protocols. However, various sectors such as healthcare, finance, automotive, education, manufacturing, etc. have experienced a lot of challenges regarding large and confidential data protection in the past few decades. With the advent of Cloud-computing in recent times, all the issues related to data security and information protection have been easier than before. Researchers have conducted an effective quantitative data collection approach by performing primary analysis through surveys. With a probability sampling technique, researchers have asked around 60 participants from different industrial fields about their opinions regarding the research topic. As per research findings around 60% of people have supported that cloud computing is essential for maximizing data protection. Around 30% people agreed with the 24 times 7 information monitoring and data encryption challenges can be solved with cloud computing. On the other hand, around 10% of participants have placed their positive opinion over the error reduction in data protection by using cloud computing. Researchers in this particular research paper are going to explain the importance of using cloud computing as a data security tool. In order to create better data protection systems across various industrial departments, cloud computing can be used in the future research as well. © 2022 IEEE.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

CauSkelNet: Causal Representation Learning for human Behaviour Analysis

arXiv

引用

arXiv 2024年

作者： Gu, Xingrui Jiang, Chuyi Wang, Erte Wu, Zekun Cui, Qiang Tian, Leimin Wu, Lianlong Song, Siyang Yu, Chuang EECS University of California Berkeley BerkeleyCA United States Department of Electrical Engineering Columbia University New YorkNY United States Department of Computer Science University College London London United Kingdom Holistic AI University College London London United Kingdom The Future Laboratory Tsinghua University Beijing China School of Electrical and Computer Systems Engineering Monash University Melbourne Australia Department of Computer Science Oxford University Oxford United Kingdom Department of Computer Science University of Exeter Exeter United Kingdom UCL Interaction Centre University College London London United Kingdom

Constrained by the lack of model interpretability and a deep understanding of human movement in traditional movement recognition machine learning methods, this study introduces a novel representation learning method based on causal inference to better understand human joint dynamics and complex behaviors. We propose a two-stage framework that combines the Peter-Clark (PC) algorithm and Kullback-Leibler (KL) divergence to identify and quantify causal relationships between joints. Our method effectively captures interactions and produces interpretable, robust representations. Experiments on the EmoPain dataset show that our causal GCN outperforms traditional GCNs in accuracy, F1 score, and recall, especially in detecting protective behaviors. The model is also highly invariant to data scale changes, enhancing its reliability in practical applications. Our approach advances human motion analysis and paves the way for more adaptive intelligent healthcare solutions. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

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：