检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Rabinovich, Ella Xu, Yang Stevenson, Suzanne Department of Computer Science Cognitive Science Program University of Toronto

Lexical semantic typology has identified important crosslinguistic generalizations about the variation and commonalities in polysemy patterns—how languages package up meanings into words. Recent computational research has enabled investigation of lexical semantics at a much larger scale, but little work has explored lexical typology across semantic domains, nor the factors that influence cross-linguistic similarities. We present a novel computational framework that quantifies semantic affinity, the cross-linguistic similarity of lexical semantics for a concept. Our approach defines a common multilingual semantic space that enables a direct comparison of the lexical expression of concepts across languages. We validate our framework against empirical findings on lexical semantic typology at both the concept and domain levels. Our results reveal an intricate interaction between semantic domains and extra-linguistic factors, beyond language phylogeny, that co-shape the typology of polysemy across languages. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Channel-aware Decoupling Network for Multi-turn Dialogue Comprehension

arXiv

引用

arXiv 2023年

作者： Zhang, Zhuosheng Zhao, Hai Liu, Longxiang The 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 MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China China

Training machines to understand natural language and interact with humans is one of the major goals of artificial intelligence. Recent years have witnessed an evolution from matching networks to pre-trained language models (PrLMs). In contrast to the plain-text modeling as the focus of the PrLMs, dialogue texts involve multiple speakers and reflect special characteristics such as topic transitions and structure dependencies between distant utterances. However, the related PrLM models commonly represent dialogues sequentially by processing the pairwise dialogue history as a whole. Thus the hierarchical information on either utterance interrelation or speaker roles coupled in such representations is not well addressed. In this work, we propose compositional learning for holistic interaction across the utterances beyond the sequential contextualization from PrLMs, in order to capture the utterance-aware and speaker-aware representations entailed in a dialogue history. We decouple the contextualized word representations by masking mechanisms in Transformer-based PrLM, making each word only focus on the words in current utterance, other utterances, and two speaker roles (i.e., utterances of sender and utterances of the receiver), respectively. In addition, we employ domain-adaptive training strategies to help the model adapt to the dialogue domains. Experimental results show that our method substantially boosts the strong PrLM baselines in four public benchmark datasets, achieving new state-of-the-art performance over previous methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Identification of Specific Human Behaviours from Cortisol profiles using a Neural Network Based Ensemble Classifier

Identification of Specific Human Behaviours from Cortisol pr...

引用

Delhi Section Conference (DELCON), IEEE

作者： Ankita Mohapatra Timothy Trinh Pulin Agrawal Stevan Pecic Computer Engineering Program California State University Fullerton Fullerton CA Natural Science and Mathematics California State University Fullerton Fullerton CA

Many vital bodily functions like stress response, immune response, blood pressure monitoring, etc. are controlled by the hormone cortisol. Variations in this hormone are related to various disorders physiological and psychological disorders. Therefore, there is a need to understand the impact of daily activities on this hormone. In this work, we designed a neural network-based classifier ensemble model that attempts to identify if the subject engaged in a particular activity in the past 48 hours, when provided with the cortisol levels measured in the same duration. The activities/behavior we focused on in this preliminary study is caffeine, nicotine and other (non calorie rich) food consumption. We were able to obtain f-score of 0.74, 0.71 and 0.68 respectively. The initial study results seem to demonstrate a predictive correlation between various daily habits and cortisol, and a possibility of isolating specific past activities that impacted the measured values of cortisol. This lays the foundation of exploring other such correlations in depth, that can lead to regulation of cortisol and other hormones.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Algorithms for Natural Language Processing Tasks: A Case of COVID-19 Twitter data (Thailand)

Machine Learning Algorithms for Natural Language Processing ...

引用

International Conference on Computational science and Computational Intelligence (CSCI)

作者： Kunyanuth Kularbphettong Rujijan Vichivanives Pannawat Kanjanaprakarn Jaruwan Chutrtong Nareenart Ruksuntorn Computer Science Program Suan Sunandha Rajabhat University Bangkok Thailand Faculty of Science and Technology Suan Sunandha Rajabhat University Bangkok Thailand Robotics Engineering program Faculty of Industrial Technology Suan Sunandha Rajabhat University Bangkok Thailand

This paper presents the use of natural language processing for the problem of information extraction and sentiment analysis. The dataset is from Twitter that has the information of people mentioning about COVID-19, this study has two tasks: (i) classification approach for information extraction task and (ii) deep learning approach for sentiment analysis task. In information extraction task, the data was gathered from twitter that related to COVID-19 information, and the sequence labelling method applied to classify text before giving it to classification algorithms (K-NN, Naïve Bayes, Decision Tree, Random Forest, and SVM). In sentiment analysis task, data was classified by convert the word into index and using word embedding, then to process deep learning algorithm (Bi-directional GRU). The accuracy of two tasks are 98% and 79% respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sasirangan Cloth Recognition and Shopping Experience Simulation Based on Virtual Reality Game with Non-Player Character Integration

Sasirangan Cloth Recognition and Shopping Experience Simulat...

引用

HCI and UX Conference in Indonesia (CHIuXiD), International

作者： Subandi Subandi Aulia Akhrian Syahidi Siti Zakiah Kiyoshi Kiyokawa Ahmad Riyadi M. Helmy Noor Smart City Information System Applied Undergraduate Program Politeknik Negeri Banjarmasin Banjarmasin Indonesia Informatics Engineering Undergraduate Program Faculty of Computer Science Universitas Brawijaya Malang Indonesia Cybernetics and Reality Engineering Laboratory Nara Institute of Science and Technology Ikoma Japan Informatics Engineering Diploma Program Politeknik Negeri Banjarmasin Banjarmasin Indonesia

ISBN: (纸本)9781665476652

Sasirangan cloth is one of the traditional cloths owned by Indonesia and is a typical cloth originating from the province of South Kalimantan. This Sasirangan cloth has many motifs and is unique. Sasirangan cloth is also one of the potentials that can attract local and foreign tourists to visit South Kalimantan. However, in recent years, tourist visits to South Kalimantan have decreased due to the impact of the COVID-19 pandemic. Then it also has an impact on the delay in the implementation of the Banjarmasin Sasirangan Festival which is usually held annually. The next impact is a decrease in turnover and interest in shopping for Sasirangan cloth, so that employees who work for Sasirangan cloth craftsmen are dismissed and reduce people's income. So the purpose of this study is to report the results of the development of a Virtual Reality Game application called VR-SasiranganKu by integrating the interaction of Non-Player Character (NPC) behavior with the type of narrative in the simulation genre game. VR-SasiranganKu is recommended to introduce and at the same time promote Sasirangan cloth to users, then justify the reaction to knowledge and shopping experience, and evaluate user experience using the UX Honeycomb method. Respondents involved as many as 100 people who are local and national tourists. The results show that the interaction of NPC behavior can provide good direction to users regarding the introduction of Sasirangan cloth by presenting an appropriate interaction design based on the narrative and the theme of the NPC that has been adopted, the results of justification using VR-SasiranganKu can provide knowledge reaction and very good shopping experience, and based on user experience evaluation that VR-SasiranganKu has adopted a very good UX with an average score of 4.91.

关键词： Human computer interaction COVID-19 Solid modeling Pandemics Games Virtual reality User experience

来源：评论

学校读者我要写书评

暂无评论

Modeling Misinformation With Q-Learning, Nim, and Multi-Agents

Modeling Misinformation With Q-Learning, Nim, and Multi-Agen...

引用

IEEE MIT Undergraduate Research Technology Conference (URTC)

作者： Elijah Huang Phil Mui Donald Bren School of Information and Computer Sciences University of California Irvine Fremont USA Department of Computer Science & Engineering Aspiring Scholars Directed Research Program Fremont USA

Misinformation or so called ”fake news” has become a pressing issue around the world. This research proposes modeling the spread of misinformation through Q-learning, the game of Nim, and multi-agent simulations. Through analyzing theoretical properties of the model and studying factors in how misinformation affects it, we show how the model reflects the real-life impact of fake news. The scalability of the framework and its emulation of real-human behavior make it versatile and believable. Through further study of this model, our hope is to shed light on effective tactics for combating fake news in the real world.

关键词： Analytical models Q-learning Social networking (online) Scalability Emulation Pressing Games

来源：评论

学校读者我要写书评

暂无评论

A Systematic Integrated Literature Review of Clinical Data Management Platforms of HL7 FHIR

A Systematic Integrated Literature Review of Clinical Data M...

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Franz Frederik Walter Viktor Walter-Tscharf Department of Information Engineering and Computer Science Fondazione Bruno Kessler University of Trento European Institute of Innovation and Technology Doctoral Program Industrial Innovation

This study is dedicated to a critical investigation of the existing approaches toward a data visualization management platform based on Fast Health Interoperability Resources (FHIR). Despite the growing popularity of FHIR, the available evidence provides a compelling reason to believe that its use is still accompanied by a significant number of technical challenges. Therefore, the development of tools to ensure its convenient visualization remains a pressing need for a variety of stakeholders operating in the healthcare industry. Results of the systematic literature review that included 26 studies provide valuable information about the most popular instruments in this area, such as the OpenEHR CKM approach. The review offers a critical discussion of the most important advantages and disadvantages of different approaches. It provides valuable recommendations for further research as well as practical recommendations concerning the best ways to utilize data visualization platforms based on FHIR. It defines the tradeoff of functionality versus the ease of dissemination as one of the most important problems facing most platforms and suggests avenues for developing additional tooling support for visualizing FHIR. The results of the research could be useful both for scientists and practitioners.

关键词： Industries Systematics Bibliographies Instruments Data visualization Pressing Medical services

来源：评论

学校读者我要写书评

暂无评论

The Wilhelm Tell Dataset of Affordance Demonstrations 25

The Wilhelm Tell Dataset of Affordance Demonstrations

引用

ACM/IEEE International Conference on Human-Robot Interaction (HRI)

作者： Rachel Ringe Mihai Pomarlan Nikolaos Tsiogkas Stefano De Giorgis Maria Hedblom Rainer Malaka Digital Media Lab University of Bremen Bremen Germany Applied Linguistics University of Bremen Bremen Germany Department of Computer Science KU Leuven Leuven Belgium National Research Council Institute of Cognitive Sciences and Technologies Catania Italy Department of Computing JÖnkÖping School of Engineering JÖnkÖping Sweden

ISBN: (数字)9798350378931

ISBN: (纸本)9798350378948

Affordances - i.e. possibilities for action that an environment or objects in it provide - are important for robots operating in human environments to perceive. Existing approaches train such capabilities on annotated static images or shapes. This work presents a novel dataset for affordance learning of common household tasks. Unlike previous approaches, our dataset consists of video sequences demonstrating the tasks from first- and third-person perspectives, along with metadata about the affordances that are manifested in the task, and is aimed towards training perception systems to recognize affordance manifestations. The demonstrations were collected from several participants and in total record about seven hours of human activity. The variety of task performances also allows studying preparatory maneuvers that people may perform for a task, such as how they arrange their task space, which is also relevant for collaborative service robots.

关键词： Training Service robots Shape Affordances Video sequences Human-robot interaction Collaboration Metadata

来源：评论

学校读者我要写书评

暂无评论

Demonstration of Ga2O3 trigate transistors on (100) silicon substrates

Demonstration of Ga2O3 trigate transistors on (100) silicon ...

引用

International Conference on Emerging Electronics (ICEE)

作者： Saravanan Yuvaraja Vishal Khandelwal Shibin Krishna Yi Lu Zhiyuan Liu Mritunjay Kumar Dhanu Chettri Xiao Tang Glen Issac Maciel Garcia Che-Hao Liao Xiaohang Li Advanced Semiconductor Laboratory Electrical and Computer Engineering Program CEMSE division King Abdullah University of Science and Technology (KAUST) Thuwa Saudi Arabia

In this paper we demonstrated the UWBG Ga 2 O 3 trigate transistors heterogeneously integrated on silicon substrate. This trigate transistor operates in depletion mode having decent Ion/Ioff ratio (10 5 ) and high transconductance (1 μS). Followed by the mobility is around 1.2 cm 2 /V. s. This work suggests that the ultrawide bandgap oxide transistors can be fabricated on various heterogenous substrates to achieve highly integrated, low cost, and robust electronics.

关键词： Performance evaluation Costs Photonic band gap Silicon Transistors Substrates Transconductance

来源：评论

学校读者我要写书评

暂无评论

Preferences for Using Canva Apps as a Presentation Media Creation Tool Among Gen Z Students: SEM Analysis with TAM and UTAUT2 Approaches

Preferences for Using Canva Apps as a Presentation Media Cre...

引用

International Seminar on Intelligent Technology and Its Applications (ISITIA)

作者： Fairuz Iqbal Maulana Dian Lestari Agung Purnomo Rahman Arifuddin Vandha Pradwiyasma Widartha Puput Dani Prasetyo Adi Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Faculty of Medicine Airlangga Surabaya 60132 Indonesia Surabaya Indonesia Entrepreneurship Department BINUS Business School Undergraduate Program Bina Nusantara University Jakarta Indonesia Department of Electrical Engineering University of Merdeka Malang Malang Indonesia Information System of Industrial Engineering Faculty Telkom University Bandung Indonesia Research Center for Telecommunication National Research and Innovation Agency (BRIN) Bandung Indonesia

ISBN: (数字)9798350378573

ISBN: (纸本)9798350378580

The purpose of this study is to find out what makes Generation Z students accept and use Canva as a tool for making presentation materials. The conceptual framework of this study is the combination of "Technology Acceptance Model (TAM)" and the "Unified Theory of Acceptance and Use of Technology (UTAUT2)". "Structural Equation Modeling (SEM)" used for data analyzation. This research aims to understand the dynamics of Canva acceptance among students. The findings show that enjoyment, fun, and pleasure in using Canva, combined with its creative tools and design-centric approach, significantly resonate with Gen Z's preference for aesthetics. This research highlights that Canva is favored by students for creating engaging presentations.

关键词： Seminars Analytical models Technology acceptance model Accuracy Numerical analysis Media Mathematical models

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：