检索结果-内蒙古大学图书馆

IEEE Workshop on Automatic Speech Recognition and Understanding

作者： Yuhao Liang Mohan Shi Fan Yu Yangze Li Shiliang Zhang Zhihao Du Qian Chen Lei Xie Yanmin Qian Jian Wu Zhuo Chen Kong Aik Lee Zhijie Yan Hui Bu Audio Speech and Language Processing Group (ASLP@NPU) School of Computer Science Northwestern Polytechnical University China Speech Lab of DAMO Academy Alibaba Group China NERC-SLIP University of Science and Technology of China (USTC) China SpeechLab Department of Computer Science and Engineering Shanghai Jiao Tong University China ICT Cluster Singapore Institute of Technology Singapore Institute for Infocomm Research A*STAR Singapore Beijing Shell Shell Technology Co. Ltd. Beijing China

With the success of the first Multi-channel Multi-party Meeting Transcription challenge (M2MeT), the second M2MeT challenge (M2MeT 2.0) held in ASRU2023 particularly aims to tackle the complex task of speaker-attributed ASR (SAASR), which directly addresses the practical and challenging problem of “who spoke what at when” at typical meeting scenario. We particularly established two sub-tracks. The fixed training condition sub-track, where the training data is constrained to predetermined datasets, but participants can use any open-source pre-trained model. The open training condition sub-track, which allows for the use of all available data and models without limitation. In addition, we release a new 10-hour test set for challenge ranking. This paper provides an overview of the dataset, track settings, results, and analysis of submitted systems, as a benchmark to show the current state of speaker-attributed ASR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LOD-connected offensive language ontology and tagset enrichment

LOD-connected offensive language ontology and tagset enrichm...

引用

2021 Workshops and Tutorials - Language Data and Knowledge, LDK 2021

作者： Lewandowska-Tomaszczyk, Barbara Žitnik, Slavko Bączkowska, Anna Liebeskind, Chaya Mitrović, Jelena Oleskeviciene, Giedre Valunaite Department of Language and Communication State University of Applied Sciences Konin Poland University of Ljubljana Faculty for Computer and Information Science Večna pot 113 LjubljanaSI-1000 Slovenia Department of Glottodidactics and Natural Language Processing University of Gdansk Poland Department of Computer Science Jerusalem College of Technology Jerusalem Israel University of Passau Germany The Institute for Artificial Intelligence Research and Development of Serbia Serbia Institute of Humanities Mykolas Romeris University Ateities 20 VilniusLT-08303 Lithuania

The main focus of the paper is the definitional revision and enrichment of offensive language typology, making reference to publicly available offensive language datasets and testing them on available pre-trained lexical embedding systems. We review over 60 available corpora and compare tagging schemas applied there while making an attempt to explain semantic differences between particular concepts of the category OFFENSIVE in English. A finite set of classes that cover aspects of offensive language representation along with linguistically sound explanations is presented, based on the categories originally proposed by Zampieri et al. [1, 2] in terms of offensive language categorization schemata and tested by means of Sketch Engine tools on a large web-based corpus. The schemata are juxtaposed and discussed with reference to non-contextual word embeddings FastText, Word2Vec, and Glove. The methodology for mapping from existing corpora to a unified ontology as presented in this paper is provided. The proposed schema will enable further comparable research and effective use of corpora of languages other than English. It will also be applied in building an enriched tagset to be trained and used on new data, with the application of recently developed LLOD techniques [3]. © 2021 Copyright for this paper by its authors

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Combining Attractor Propagation with Differential Evolution for Three-echelon logistics distribution optimization

SSRN

引用

SSRN 2022年

作者： Zhang, Haifei Ge, Hongwei Yang, Jieming Su, Shuzhi Tong, Yubing School of Artificial Intelligence and Computer Science Jiangnan University Jiangsu Wuxi214122 China Key Laboratory of Advanced Process Control for Light Industry Jiangnan University Ministry of Education Wuxi214122 China School of Computer Science and Engineering Anhui University of Science & Technology Anhui Huainan232001 China Medical Image Processing Group Department of Radiology University of Pennsylvania PhiladelphiaPA19104 United States

In the process of urban logistics distribution, how to achieve efficiently and timely logistics distribution within the distribution time limit has become an urgent problem to be solved in logistics management. Three-echelon logistics distribution is considered to be an effective strategy to alleviate urban congestion, improve liquidity and reduce pollution. In this paper, a mathematical model of three-echelon logistics distribution problem considering time window constraint is established based on directed graph, and a double-tier intelligent algorithm coordinated by Distance Entropy-based Attractor Propagation (DEBAP) clustering algorithm - Crossover-and-Selection based Differential Evolution (CSBDE) is proposed. DEBAP is responsible for the optimization of region partitioning and facility allocation. The obtained region partitioning and facility allocation scheme are transmitted to CSBDE for path planning. CSBDE feeds back the optimized path planning scheme to DEBAP, and the two-tier intelligent algorithm cooperates to complete the optimization of three-echelon logistics distribution system. In addition, this paper proposes a search strategy based on reachable distribution region and a facility allocation optimization strategy based on path length as weight to improve the efficiency of the algorithm. The example calculation shows that the mathematical model and combined intelligent algorithm proposed in this paper can effectively solve 3-echelon logistics distribution problem(3E-LDP), provide theoretical and methodological guidance for multi-echelon logistics distribution, and can be well implemented in practice to help logistics operators reduce operation costs and improve customer service. © 2022, The Authors. All rights reserved.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Fourier-Reflexive Partitions and Group of Linear Isometries with Respect to Weighted Poset Metric

Fourier-Reflexive Partitions and Group of Linear Isometries ...

引用

IEEE International Symposium on Information Theory

作者： Yang Xu Haibin Kan Guangyue Han Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Department of Mathematics The University of Hong Kong Shanghai Engineering Research Center of Blockchain Yiwu Research Institute of Fudan University

ISBN: (数字)9781665421591

ISBN: (纸本)9781665421607

Let H be the cartesian product of a family of abelian groups indexed by a nonempty finite set Ω. A given poset P = (Ω, ≼ P ) and a map ω : Ω → ℝ + give rise to the (P, ω)-weight on H, which further leads to a partition $\mathcal{Q}\left( {{\text{H}},{\text{P}},\omega } \right)$ of H. For the case that H is finite, we give sufficient conditions for two codewords to belong to the same block of Λ, the dual partition of $\mathcal{Q}\left( {{\text{H}},{\text{P}},\omega } \right)$, and sufficient conditions for $\mathcal{Q}\left( {{\text{H}},{\text{P}},\omega } \right)$ to be Fourier-reflexive. By relating the involved partitions with certain polynomials, we show that such sufficient conditions are also necessary if P is hierarchical and ω is integer valued. With H further set to be a finite vector space over a finite field $\mathbb{F}$, from a partition perspective, we extend the property of "admitting MacWilliams identity" to arbitrary pairs of partitions of H, and prove that a pair of $\mathbb{F}$-invariant partitions (Λ, Γ) with |Λ| = |Γ| admits MacWilliams identity if and only if (Λ, Γ) is a pair of mutually dual Fourier-reflexive partitions. Such a result is applied to the partition $\mathcal{Q}\left( {{\text{H}},{\text{P}},\omega } \right)$. Finally, with H set to be a (possibly infinite) left module over a ring S, we show that each (P, ω)- weight isometry of H uniquely induces an order automorphism of P, which further leads to a group homomorphism from the group of (P, ω)-weight isometries to Aut (P), whose kernel consists of isometries preserving the P-support.

关键词： Measurement Sufficient conditions Kernel Galois fields Information theory

来源：评论

学校读者我要写书评

暂无评论

VELO: A Vector Database-Assisted Cloud-Edge Collaborative LLM QoS Optimization Framework

VELO: A Vector Database-Assisted Cloud-Edge Collaborative LL...

引用

IEEE International Conference on Web Services (ICWS)

作者： Zhi Yao Zhiqing Tang Jiong Lou Ping Shen Weijia Jia Institute of Artificial Intelligence and Future Networks Beijing Normal University Zhuhai China School of Artificial Intelligence Beijing Normal University Beijing China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Guangdong Key Lab of AI and Multi-Modal Data Processing BNU-HKBU United International College Zhuhai China

ISBN: (数字)9798350368550

ISBN: (纸本)9798350368567

The Large Language Model (LLM) has gained significant popularity and is extensively utilized across various domains. Most LLM deployments occur within cloud data centers, where they encounter substantial response delays and incur high costs, thereby impacting the Quality of Services (QoS) at the network edge. Leveraging vector database caching to store LLM request results at the edge can substantially mitigate response delays and cost associated with similar requests, which has been overlooked by previous research. Addressing these gaps, this paper introduces a novel Vector database-assisted cloud-Edge collaborative LLM QoS Optimization (VELO) framework. Firstly, we propose the VELO framework, which ingeniously employs vector database to cache the results of some LLM requests at the edge to reduce the response time of subsequent similar requests. Diverging from direct optimization of the LLM, our VELO framework does not necessitate altering the internal structure of LLM and is broadly applicable to diverse LLMs. Subsequently, building upon the VELO framework, we formulate the QoS optimization problem as a Markov Decision Process (MDP) and devise an algorithm grounded in Multi-Agent Reinforcement Learning (MARL) to decide whether to request the LLM in the cloud or directly return the results from the vector database at the edge. Moreover, to enhance request feature extraction and expedite training, we refine the policy network of MARL and integrate expert demonstrations. Finally, we implement the proposed algorithm within a real edge system. Experimental findings confirm that our VELO framework substantially enhances user satisfaction by concurrently diminishing delay and resource consumption for edge users utilizing LLMs.

关键词： Training Costs Databases Web services Collaboration Quality of service Feature extraction Vectors Delays Optimization

来源：评论

学校读者我要写书评

暂无评论

Automating Theory of Mind Assessment with a LLaMA-3-Powered Chatbot: Enhancing Faux Pas Detection in Autism

Automating Theory of Mind Assessment with a LLaMA-3-Powered ...

引用

International eConference on computer and Knowledge Engineering (ICCKE)

作者： Avisa Fallah Ali Keramati Mohammad Ali Nazari Fatemeh Sadat Mirfazeli School of Mathematics Statistics and Computer Science University of Tehran Tehran Iran National Brain Centre Iran University of Medical Sciences Tehran Iran School of Electrical and Computer Engineering University of Tehran Tehran Iran Department of Neuroscience Advanced Technologies in Medicine Iran University of Medical Sciences Image Brain Institute Tehran Iran Department of Psychiatry Mental Health Research Center Advanced Technologies in Medicine National Brain Centre School of Medicine Psychosocial Health Research InstituteIran University of Medical Sciences Tehran Iran

ISBN: (数字)9798331511272

ISBN: (纸本)9798331511289

The Theory of Mind (ToM) is critical for social interactions, enabling individuals to understand and predict others' mental states. Deficits in ToM, particularly in detecting faux pas, are common among individuals with Autism Spectrum Disorder (ASD). Traditional methods for assessing ToM, such as the Faux Pas Recognition Test (FPRT), require significant human involvement, which can limit accessibility and scalability. This study aims to explore how large language model (LLM)-powered chatbots, specifically utilizing the LLaMA-3 model, can enhance the assessment of ToM by automating and improving the administration of the FPRT. The methodology involved creating a dual-phase process where the chatbot first assesses user responses and then provides rehabilitative guidance to correct misunderstandings. Additionally, the system employs a scoring mechanism combining automated evaluation with human oversight to ensure accuracy and consistency, with system prompts crafted based on chain-of-thought prompting to enhance the depth and reliability of the assessments. Our findings demonstrate the effectiveness of LLM-powered chatbots in delivering dynamic and supportive ToM assessments, suggesting its potential for broader application for both artificial intelligence and psychological practices.

关键词： Autism Accuracy Target recognition Scalability Large language models Mental health Reliability theory Chatbots Real-time systems Testing

来源：评论

学校读者我要写书评

暂无评论

Minimal Length of Nontrivial Solutions of the Isometry Equation and MacWilliams Extension Property with Respect to Weighted Poset Metric

Minimal Length of Nontrivial Solutions of the Isometry Equat...

引用

IEEE International Symposium on Information Theory

ISBN: (数字)9781665421591

ISBN: (纸本)9781665421607

For $R \triangleq Ma{t_m}({\mathbb{F}})$, the ring of all m × m matrices over the finite field ${\mathbb{F}}$ with $|{\mathbb{F}}| = q$, and the left R-module $A \triangleq Ma{t_{m,k}}({\mathbb{F}})$ with m + 1 ⩽ k, by deriving the minimal length of solutions of the related isometry equation, Dyshko has proved in [3], [4] that the minimal code length n for A n not satisfying the MacWilliams extension property (MEP) with respect to Hamming weight is equal to $\prod\nolimits_{i = 1}^m {\left( {{q^i} + 1} \right)}$. In this paper, using the Möbius functions, we derive the minimal length of nontrivial solutions of the isometry equation for a finite lattice. For the finite vector space ${\mathbf{H}} \triangleq \prod\nolimits_{i \in \Omega } {{{\mathbb{F}}^{{k_i}}}}$, a poset P = (Ω, ≼ P ) and a map ω: Ω → ℝ + give rise to the (P, ω)-weight on H, which has been proposed by Hyun, Kim and Park in [18]. For such a weight, we study the relations between the MEP and other properties including admitting MacWilliams identity, Fourier-reflexivity of involved partitions and the Unique Decomposition Property (UDP) defined for (P, ω). We give necessary and sufficient conditions for H to satisfy the MEP with the additional assumption that either P is hierarchical or ω is identically 1, i.e., (P, ω)-weight coincides with P-weight, which further allow us to partly answer a conjecture proposed by Machado and Firer in [22].

关键词： Measurement Sufficient conditions Codes Lattices Hamming weight Galois fields

来源：评论

学校读者我要写书评

暂无评论

Foreword

Lecture Notes in Networks and Systems

引用

Lecture Notes in Networks and Systems 2023年 710 LNNS卷 v-vi页

作者： Biele, Cezary Kacprzyk, Janusz Kopeć, Wieslaw Owsiński, Jan W. Romanowski, Andrzej Sikorski, Marcin National Information Processing Institute Warsaw Poland Polish-Japanese Academy of Information Technology Warsaw Poland Institute of Applied Computer Science Lódż University of Technology Lódź Poland Polish Academy of Sciences Systems Research Institute Warsaw Poland Department of Informatics in Management Faculty of Management and Economics Gdańsk University of Technology Gdańsk Poland

来源：评论

学校读者我要写书评

暂无评论

Position: insights from survey methodology can improve training data 24

Position: insights from survey methodology can improve train...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Stephanie Eckman Barbara Plank Frauke Kreuter Social Data Science Center University of Maryland College Park MD Center for Information and Language Processing (CIS) LMU Munich Germany and Computer Science Department IT University of Copenhagen Denmark and Munich Center for Machine Learning (MCML) LMU Munich Germany Institute for Statistics and Munich Center for Machine Learning (MCML) LMU Munich Germany and Social Data Science Center and Joint Program in Survey Methodology University of Maryland College Park MD

Whether future AI models are fair, trustworthy, and aligned with the public's interests rests in part on our ability to collect accurate data about what we want the models to do. However, collecting high-quality data is difficult, and few AI/ML researchers are trained in data collection methods. Recent research in data-centric AI has show that higher quality training data leads to better performing models, making this the right moment to introduce AI/ML researchers to the field of survey methodology, the science of data collection. We summarize insights from the survey methodology literature and discuss how they can improve the quality of training and feedback data. We also suggest collaborative research ideas into how biases in data collection can be mitigated, making models more accurate and human-centric.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Recent Survey of Vision Transformers for Medical image Segmentation

arXiv

引用

arXiv 2023年

作者： Khan, Asifullah Rauf, Zunaira Khan, Abdul Rehman Rathore, Saima Khan, Saddam Hussain Shah, Sahar Farooq, Umair Asif, Hifsa Asif, Aqsa Zahoora, Umme Khalil, Rafi Ullah Qamar, Suleman Asif, Umme Hani Khan, Faiza Babar Majid, Abdul Gwak, Jeonghwan Pattern Recognition Lab Department of Computer & Information Sciences Pakistan Institute of Engineering & Applied Sciences Nilore Islamabad45650 Pakistan Pakistan Institute of Engineering & Applied Sciences Nilore Islamabad45650 Pakistan Center for Mathematical Sciences Pakistan Institute of Engineering & Applied Sciences Nilore Islamabad45650 Pakistan Avid Radio pharmaceuticals PhiladelphiaPA United States Eli Lilly and Company IndianapolisIN United States Swat Pakistan Air University E-9 Islamabad44230 Pakistan Digital Image Processing Lab Department of Computer Science Islamia College Peshawar Pakistan Pakistan Institute of Engineering & Applied Sciences Nilore Islamabad45650 Pakistan Department of Software Korea National University of Transportation Chungju27469 Korea Republic of

Medical image segmentation plays a crucial role in various healthcare applications, enabling accurate diagnosis, treatment planning, and disease monitoring. In recent years, Vision Transformers (ViTs) have emerged as a promising technique for addressing the challenges in medical image segmentation. In medical images, structures are usually highly interconnected and globally distributed. ViTs utilize their multi-scale attention mechanism to model the long-range relationships in the images. However, they do lack image-related inductive bias and translational invariance, potentially impacting their performance. Recently, researchers have come up with various ViT-based approaches that incorporate CNNs in their architectures, known as Hybrid Vision Transformers (HVTs) to capture local correlation in addition to the globa l information in the images. This survey paper provides a detailed review of the recent advancements in ViTs and HVTs for medical image segmentation. Along with the categorization of ViT and HVT-based medical image segmentation approaches we also present a detailed overview of their real-time applications in several medical image modalities. This survey may serve as a valuable resource for researchers, healthcare practitioners, and students in understanding the state-of-the-art approaches for ViT-based medical image segmentation. Copyright © 2023, The Authors. All rights reserved.

关键词： Diagnosis

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：