检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Luo, Linhao Vu, Thuy-Trang Phung, Dinh Haffari, Gholamreza Department of Data Science AI Faculty of Information Technology Monash University Australia

Previous studies have relied on existing question-answering benchmarks to evaluate the knowledge stored in large language models (LLMs). However, this approach has limitations regarding factual knowledge coverage, as it mostly focuses on generic domains which may overlap with the pretraining data. This paper proposes a framework to systematically assess the factual knowledge of LLMs by leveraging knowledge graphs (KGs). Our framework automatically generates a set of questions and expected answers from the facts stored in a given KG, and then evaluates the accuracy of LLMs in answering these questions. We systematically evaluate the state-of-the-art LLMs with KGs in generic and specific domains. The experiment shows that ChatGPT is consistently the top performer across all domains. We also find that LLMs performance depends on the instruction finetuning, domain and question complexity and is prone to adversarial context.1 Copyright © 2023, The Authors. All rights reserved.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

data Evidence-Based Aircraft Continuing Airworthiness Management Assistant System and Applications 4

Data Evidence-Based Aircraft Continuing Airworthiness Manage...

引用

4th IEEE International Conference on Civil Aviation Safety and Information technology, ICCASIT 2022

作者： Miao, Jiahe Zhang, Chen Jiao, Yang Zhang, Xinyue Li, Qian China Academy of Civil Aviation Science &technology Big Data Analysis and Application Center Beijing China China Academy of Civil Aviation Science &technology Eng. and Technical Research Center of Civil Aviation Safety Analysis and Prevention of Beijing Beijing China

ISBN: (数字)9781665467667

ISBN: (纸本)9781665467667

This paper proposes and introduces the construction scheme of the aircraft continuing airworthiness management assistant system based on data evidence. The system can deeply integrate aircraft fault/event cases, usage information and actual operational airborne QAR data to achieve classified management of fault data, normal data, new aircraft data, and full life cycle data, thereby enhancing the role of data evidence and data intelligence in continuing airworthiness management. QAR data can be used as direct evidence for fault case analysis and investigation. Statistical rules obtained and model trained from historical data can serve as indirect evidence for fleet health management. Taking engine health management as an example, the article introduces the construction and management of engine typical fault case sets based on system database, and shows the real fault cases in actual operation and the application of related engine condition monitoring technologies based on QAR data, including threshold monitoring, dual-engine difference monitoring and trend monitoring. The system can serve not only the supervision of regulators, but also the fleet health management of airlines and manufacturers, which helps all parties improve their continuing airworthiness management capabilities, discover design and manufacturing defects in a timely manner during operation, and continuously track and ensure aircraft airworthiness status. © 2022 IEEE.

关键词： Aircraft

来源：评论

学校读者我要写书评

暂无评论

Decompose, Enrich, and Extract! Schema-aware Event Extraction using LLMs.

arXiv

引用

arXiv 2024年

作者： Shiri, Fatemeh Nguyen, Van Moghimifar, Farhad Yoo, John Haffari, Gholamreza Li, Yuan-Fang Department of Data Science AI Faculty of Information Technology Monash University Australia Information Sciences Division Defence Science and Technology Group Australia

Large Language Models (LLMs) demonstrate significant capabilities in processing natural language data, promising efficient knowledge extraction from diverse textual sources to enhance situational awareness and support decision-making. However, concerns arise due to their susceptibility to hallucination, resulting in contextually inaccurate content. This work focuses on harnessing LLMs for automated Event Extraction, introducing a new method to address hallucination by decomposing the task into Event Detection and Event Argument Extraction. Moreover, the proposed method integrates dynamic schema-aware augmented retrieval examples into prompts tailored for each specific inquiry, thereby extending and adapting advanced prompting techniques such as Retrieval-Augmented Generation. Evaluation findings on prominent event extraction benchmarks and results from a synthesized benchmark illustrate the method’s superior performance compared to baseline approaches. © 2024, CC BY.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Infinite-Horizon Graph Filters: Leveraging Power Series to Enhance Sparse Information Aggregation

arXiv

引用

arXiv 2024年

作者： Zhang, Ruizhe Jiang, Xinke Fang, Yuchen Luo, Jiayuan Xu, Yongxin Zhu, Yichen Chu, Xu Zhao, Junfeng Wang, Yasha Ministry of Education School of Computer Science Peking University China University of Toronto Canada The Big Data Technology Research Center Nanhu Laboratory Jiaxing314002 China

Graph Neural Networks (GNNs) have shown considerable effectiveness in a variety of graph learning tasks, particularly those based on the message-passing approach in recent years. However, their performance is often constrained by a limited receptive field, a challenge that becomes more acute in the presence of sparse graphs. In light of the power series, which possesses infinite expansion capabilities, we propose a novel Graph Power Filter Neural Network (GPFN) that enhances node classification by employing a power series graph filter to augment the receptive field. Concretely, our GPFN designs a new way to build a graph filter with an infinite receptive field based on the convergence power series, which can be analyzed in the spectral and spatial domains. Besides, we theoretically prove that our GPFN is a general framework that can integrate any power series and capture long-range dependencies. Finally, experimental results on three datasets demonstrate the superiority of our GPFN over state-of-the-art baselines. © 2024, CC BY.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

A Multimodal Interviewee Evaluation Approach for Candidates Facing Video Interviews 13

A Multimodal Interviewee Evaluation Approach for Candidates ...

引用

13th International Conference on Computing Communication and Networking Technologies, ICCCNT 2022

作者： Randika, W.G. Yasiru Maddumage, T.A.R. Liyanage, K.L.O.G. Karunasena, A. Weerasinghe, K.M.L.P. Specializes in Data Science Sri Lanka Institute of Information Technology Department of Information Technology Malabe Sri Lanka Sri Lanka Institute of Information Technology Department of Information Technology Malabe Sri Lanka

ISBN: (数字)9781665452625

ISBN: (纸本)9781665452625

Automated video interview evaluation is an area that is becoming trending because of the significant usage of video interviews for candidates' hiring processes. Though there is much research on video interviews, there are a smaller number of studies on the automated evaluation process in video interviews. Still, many entities use more human interaction for selecting candidates through video interviews. This study proposes a set of methodologies to evaluate the candidate by considering five aspects which are knowledge level, mindset, confidence, personality, behavior, and English language fluency. This paper proposes an answer evaluation using feature engineering and Siamese LSTM architecture where BERT is used as the encoding layer. The CNN-based approach is proposed for behavior and personality analysis. For language fluency and confidence, NLP techniques and machine learning methods are proposed in this study. Through the methodologies propose in this study, overall, all the evaluations yield around 85% - 90% accuracy. The approach suggested in this study will help organizations to do their talent acquisition process more smoothly. © 2022 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Identification of the Video Level for Video Communication in a Resource-Constrained Network

Identification of the Video Level for Video Communication in...

引用

2022 International Conference on Artificial Intelligence and data Engineering, AIDE 2022

作者： Bijur, Gururaj Ramakrishna, M. Karunakar, A.K. Manipal Institute of Technology Department of Computer Science & Engineering MAHE Manipal Karnataka Udupi India Manipal Institute of Technology Department of Data Science & Computer Applications MAHE Manipal Karnataka Udupi India

ISBN: (纸本)9781665493048

HEVC, which employs layered video coding techniques, is an extension of H.264 Advanced Video Coding. Layered video coding creates a valid bitstream by removing layers. Video streaming via wireless networks is made possible by this capability. The elements that affect the quality of video communication include node mobility, the kind of routing protocols, communication distance, etc. The video adaptation method calculates the number of video levels that will be lost and then extracts at Media Aware Network Elements in accordance with terminal capabilities and resource availability. Building the information needed to select the extraction point or adaption level is the goal of this work. The extraction points for streaming Multi-level Video over the resource constrained network have been calculated in this article. © 2022 IEEE.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

AI based Analysis of Hyperspectral Images with Spectacular Efficacy in Video Analytics

AI based Analysis of Hyperspectral Images with Spectacular E...

引用

2024 International Conference on Intelligent and Innovative Practices in Engineering and Management, IIPEM 2024

作者： Jadhav, Samarth Yogesh More, Rutuja Rajatam Tingare, Bhagyashree Ashok Lakshmi, G. Prasanna Kolse, Shivam Darwante, N.K. Sanjivani College of Engineering Department of Information Technology MH Kopargaon India D Y Patil College of Engineering Akurdi Department of Artificial Intelligence and Data Science Pune India Sandip University School of Computer Science and Engineering Maharashtra Nashik India Sanjivani College of Engineering Department of Electronics and Computer Engineering MH Kopargaon India

ISBN: (纸本)9798350390049

Hyperspectral imaging and artificial intelligence (AI) have transformed imaging and data processing through their ability to capture and analyze detailed spectral information. This paper explores the integration of hyperspectral imaging with AI, focusing on its impact on video analytics. Hyperspectral imaging provides comprehensive, multi-dimensional data by capturing a wide range of spectral wavelengths, enabling precise material identification and environmental monitoring beyond traditional RGB imaging. The synergy between hyperspectral imaging and AI enhances real-time analysis and decision-making by leveraging deep learning algorithms for pattern recognition and anomaly detection. This study introduces a novel AI-based hyperspectral image analysis approach for video analytics, utilizing convolutional neural networks (CNNs) and hybrid CNN-attention models to improve object recognition and classification. The methodology is validated through experiments that measure classification accuracy, processing speed, and resilience to varying conditions. Results demonstrate significant improvements in accuracy and efficiency over traditional methods, highlighting the potential for advanced applications in surveillance, environmental monitoring, and industrial quality control. © 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

A Sketch-Based Generation Model for Diverse Ceramic Tile Images Using Generative Adversarial Network

引用

Intelligent Automation & Soft Computing 2023年第9期37卷 2865-2882页

作者： Jianfeng Lu Xinyi Liu Mengtao Shi Chen Cui Mahmoud Emam School of Computer Science and Technology Hangzhou Dianzi UniversityHangzhou310018China Key Laboratory of Public Security Information Application Based on Big-Data Architecture Ministry of Public SecurityZhejiang Police CollegeHangzhou310000China Faculty of Artificial Intelligence Menoufia UniversityShebin El-Koom32511Egypt

Ceramic tiles are one of the most indispensable materials for interior *** ceramic patterns can’t match the design requirements in terms of diversity and interactivity due to their natural *** this paper,we propose a sketch-based generation method for generating diverse ceramic tile images based on a hand-drawn sketches using Generative Adversarial Network(GAN).The generated tile images can be tailored to meet the specific needs of the user for the tile *** proposed method consists of four ***,a dataset of ceramic tile images with diverse distributions is created and then pre-trained based on ***,for each ceramic tile image in the dataset,the corresponding sketch image is generated and then the mapping relationship between the images is trained based on a sketch extraction network using ResNet Block and jump connection to improve the quality of the generated ***,the sketch style is redefined according to the characteristics of the ceramic tile images and then double cross-domain adversarial loss functions are employed to guide the ceramic tile generation network for fitting in the direction of the sketch style and to improve the training ***,we apply hidden space perturbation and interpolation for further enriching the output textures style and satisfying the concept of“one style with multiple faces”.We conduct the training process of the proposed generation network on 2583 ceramic tile images *** measure the generative diversity and quality,we use Frechet Inception Distance(FID)and Blind/Referenceless Image Spatial Quality Evaluator(BRISQUE)*** experimental results prove that the proposed model greatly enhances the generation results of the ceramic tile images,with FID of 32.47 and BRISQUE of 28.44.

关键词： Ceramic tile pattern design cross-domain learning deep learning GAN generative adversarial networks ResNet Block

来源：评论

学校读者我要写书评

暂无评论

A construction technology of automatic reasoning system based on knowledge graph

A construction technology of automatic reasoning system base...

引用

2022 International Symposium on Artificial Intelligence Control and Application technology, AICAT 2022

作者： Wu, Guobin Liang, Jian Jin, Xi Wang, Xiao Zhang, Zhewen DiDi Technology Ecosystem and Development Didi Chuxing Beijing China Data Science and Artificial Intelligence Department Draweast Tech Beijing China

ISBN: (纸本)9781510656710

With the rapid development of artificial intelligence, the research on perceptual intelligence is becoming more and more mature. For the next stage of cognitive intelligence research, knowledge graph (KG) is one of the key directions. Knowledge reasoning is an important part of KG and has a wide range of application requirements. At present, knowledge reasoning methods in large-scale KG still have problems of poor interpretability, low reasoning accuracy and efficiency. Knowledge reasoning methods based on deep reinforcement learning have better interpretability and stronger reasoning ability. This paper introduces the research progress of knowledge reasoning based on KG, and makes an analysis of the current knowledge reasoning methods based on knowledge representation, relational path and deep reinforcement learning. At the same time, this paper conducts link prediction and fact prediction experiments on related knowledge reasoning methods on NELL-995 and FB15K-237 datasets, and summarizes the datasets, evaluation methods and indicators involved in these experiments. In conclusion, the proposed future knowledge reasoning model is based on the fusion knowledge representation, relational path with deep reinforcement learning methods. © 2022 SPIE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Word Translation using CrossLingual Word Embedding: Case of Sanskrit to Hindi translation 2

Word Translation using CrossLingual Word Embedding: Case of ...

引用

2nd International Conference on Artificial Intelligence and Signal Processing, AISP 2022

作者： Kumar, Rashi Sahula, Vineet Department of AI and Data Science Samrat Ashok Technological Institute Vidisha India Department of ECE Malaviya National Institute of Technology Jaipur Jaipur India

ISBN: (纸本)9781665442909

Sanskrit is a low resource language for which large parallel data sets are not available. Large parallel data sets are required for Machine Translation. CrossLingual word embedding helps to learn the meaning of words across languages in a shared vector space. In the present work, we propose a translation technique between Sanskrit and Hindi words without a parallel corpusbase. Here, fastText pretrained word embedding for Sanskrit and Hindi are used and are aligned in the same vector space using Singular Value Decomposition and a Quasi bilingual dictionary. A Quasi bilingual dictionary is generated from similar character string words in the monolingual word embeddings of both languages. Translations for the test dictionary are evaluated on the various retrieval methods e.g. Nearest neighbor, Inverted Sofmax approach, and Crossdomain Similarity Local Scaling, in order to address the issue of hubness that arises due to the high dimensional space of the vector embeddings. The results are compared with the other Unsupervised approaches at 1, 10, and 20 neighbors. While computing the Cosine similarity, we observed that the similarity between the expected and the translated target words is either close to unity or equal to unity for the cases that were even not included in the Quasi bilingual dictionary that was used to generate the orthogonal mapping. A test dictionary was developed from the Wikipedia SanskritHindi Shabdkosh to test the translation accuracy of the system. The proposed method is being extended for sentence translation. © 2022 IEEE.

关键词： Singular value decomposition

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：