检索结果-内蒙古大学图书馆

Findings of the 62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024

作者： Liu, Jinxin Cao, Shulin Shi, Jiaxin Zhang, Tingjian Nie, Lunyiu Hu, Linmei Hou, Lei Li, Juanzi Department of Computer Science and Technology BNRist China THU - Siemens Ltd. China Joint Research Center for Industrial Intelligence and IoT Tsinghua University Beijing China Huawei Cloud Computing Technologies Co. Ltd. China School of Computer Science and Technology Beijing Institute of Technology China

ISBN: (纸本)9798891760998

Knowledge Base Question Answering (KBQA) aims to answer natural language questions based on facts in knowledge bases. A typical approach to KBQA is semantic parsing, which translates a question into an executable logical form in a formal language. Recent works leverage the capabilities of large language models (LLMs) for logical form generation to improve performance. However, although it is validated that LLMs are capable of solving some KBQA problems, there has been little discussion on the differences in LLMs' proficiency in formal languages used in semantic parsing. In this work, we propose to evaluate the understanding and generation ability of LLMs to deal with differently structured logical forms by examining the inter-conversion of natural and formal language through in-context learning of LLMs. Extensive experiments with models of different sizes show that state-of-the-art LLMs can understand formal languages as well as humans, but generating correct logical forms given a few examples remains a challenge. Most importantly, our results also indicate that LLMs exhibit considerable sensitivity. In general, the formal language with a lower formalization level, i.e., the more similar it is to natural language, is more friendly to LLMs. Code and data can be found at https://***/Matthewlliu/structure_probe. © 2024 Association for Computational Linguistics.

关键词： Formal languages

来源：评论

学校读者我要写书评

暂无评论

ML-based Modeling to Predict I/O Performance on Different Storage Sub-systems 31

ML-based Modeling to Predict I/O Performance on Different St...

引用

31st Annual IEEE International Conference on High Performance computing, Data, and Analytics, HiPC 2024

作者： Xu, Yiheng Sivaraman, Pranav Devarajan, Hariharan Mohror, Kathryn Bhatele, Abhinav Palantir Technologies Inc. Denver United States Department of Computer Science University of Maryland College Park United States Center for Applied Scientific Computing Lawrence Livermore National Laboratory Livermore United States

ISBN: (纸本)9798331509095

Parallel applications can spend a significant amount of time performing I/O on large-scale supercomputers. Fast near-compute storage accelerators called burst buffers can reduce the time a processor spends performing I/O and mitigate I/O bottlenecks. However, determining if a given application could be accelerated using burst buffers is not straightforward even for storage experts. The relationship between an application’s I/O characteristics (such as I/O volume, processes involved, etc.) and the best storage sub-system for it can be complicated. As a result, adapting parallel applications to use burst buffers efficiently is a trial-and-error process. In this work, we present a Python-based tool called PrismIO that enables programmatic analysis of I/O traces. Using PrismIO, we identify performance bottlenecks when using burst buffers and parallel file systems, and explain why certain I/O patterns perform poorly. Further, we use machine learning to model the relationship between I/O characteristics and file system selections. We use IOR, an I/O benchmark to gather performance data for training the machine learning model. Our model can predict the better performing storage system for unseen IOR scenarios with an accuracy of 94.47% and for four real applications with an accuracy of 95.86%. © 2024 IEEE.

关键词： Supercomputers

来源：评论

学校读者我要写书评

暂无评论

Improving Text-guided Object Inpainting with Semantic Pre-inpainting

arXiv

引用

arXiv 2024年

作者： Chen, Yifu Chen, Jingwen Pan, Yingwei Li, Yehao Yao, Ting Chen, Zhineng Mei, Tao School of Computer Science Fudan University China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China HiDream.ai Inc.

Recent years have witnessed the success of large text-to-image diffusion models and their remarkable potential to generate high-quality images. The further pursuit of enhancing the editability of images has sparked significant interest in the downstream task of inpainting a novel object described by a text prompt within a designated region in the image. Nevertheless, the problem is not trivial from two aspects: 1) Solely relying on one single U-Net to align text prompt and visual object across all the denoising timesteps is insufficient to generate desired objects;2) The controllability of object generation is not guaranteed in the intricate sampling space of diffusion model. In this paper, we propose to decompose the typical single-stage object inpainting into two cascaded processes: 1) semantic pre-inpainting that infers the semantic features of desired objects in a multi-modal feature space;2) high-fieldity object generation in diffusion latent space that pivots on such inpainted semantic features. To achieve this, we cascade a Transformer-based semantic inpainter and an object inpainting diffusion model, leading to a novel CAscaded Transformer-Diffusion (CAT-Diffusion) framework for text-guided object inpainting. Technically, the semantic inpainter is trained to predict the semantic features of the target object conditioning on unmasked context and text prompt. The outputs of the semantic inpainter then act as the informative visual prompts to guide high-fieldity object generation through a reference adapter layer, leading to controllable object inpainting. Extensive evaluations on OpenImages-V6 and MSCOCO validate the superiority of CAT-Diffusion against the state-of-the-art methods. Code is available at https://***/Nnn-s/CATdiffusion. Copyright © 2024, 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

HODI at EVALITA 2023: Overview of the first Shared Task on Homotransphobia Detection in Italian 8

HODI at EVALITA 2023: Overview of the first Shared Task on H...

引用

8th Evaluation Campaign of Natural Language Processing and Speech Tools for Italian. Final Workshop, EVALITA 2023

作者： Nozza, Debora Cignarella, Alessandra Teresa Damo, Greta Caselli, Tommaso Patti, Viviana Department of Computing Sciences Bocconi University Milan Italy Department of Computer Science University of Turin Turin Italy aequa-tech Turin Italy Center for Language and Cognition University of Groningen Groningen Netherlands

HODI is a new shared task for the automatic detection of homotransphobia in Italian presented at EVALITA 2023. The challenge is organized into two subtasks: Subtask A focuses on the binary textual classification of homotransphobic tweets, while Subtask B is concerned with the identification of"rationales" for explainability in the form of textual spans of text. We have received a total of 19 runs for Subtask A and 5 runs for Subtask B from a total of 8 participating teams from 6 different countries. We present here an overview of the HODI shared task, the datasets, the evaluation methodology, the results obtained by the participants, and a discussion of the methodology adopted by the teams. © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Text processing

来源：评论

学校读者我要写书评

暂无评论

Towards a Unified User Interface for visual Analysis of Retinal Data in Ophthalmology

arXiv

引用

arXiv 2023年

作者： Röhlig, Martin Nonnemann, Lars Schulz, Hans-Jörg Stachs, Oliver Schumann, Heidrun Institute for Visual and Analytic Computing University of Rostock Germany Department of Computer Science Aarhus University Denmark Department of Ophthalmology Rostock University Medical Center Germany

The visual analysis of retinal data contributes to the understanding of a wide range of eye diseases. For the evaluation of cross-sectional studies, ophthalmologists rely on workflows and toolsets established in their work environment. That is, they know what tools and data are needed at each step of their workflow. Yet, manually operating the various tools, including activation, data handling, or view arrangement, can be cumbersome and time-consuming. We thus introduce a new visualization-supported toolchaining approach that combines workflow, tools, and data. First, we provide access to the tools required for each step of the workflow. Second, we handle the exchange of data between these tools. Third, we organize the views of the tools on screen using suitable layouts. Fourth, we visualize the connection between workflow, tools, and data to support the data analysis. We demonstrate our approach with a use case in ophthalmic research and report on initial feedback from experts. © 2023, CC BY.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Binary Grey Wolf Optimizer for Mapping Real Time Applications on MPSOCs Architecture 7

Binary Grey Wolf Optimizer for Mapping Real Time Application...

引用

7th International Conference on Informatics and Applied Mathematics, IAM 2024

作者： Boumaza, Farid Zouache, Djaafar Belazzoug, Mouhoub Hadji, Atmane Aroui, Abdelkader Computer Science Department University of Mohamed El Bachir El Ibrahimi Bordj Bou Arreridj34030 Algeria Laboratory of Parallel Embedded architectures and Intensive Computing University of Oran1 Oran31000 Algeria LISI Laboratory Computer Science Department University Center A. Boussouf Mila Mila43000 Algeria Center for Space Techniques Palestine Avenue Arzew Oran31200 Algeria

With the growing complexity of real-time applications, Multi-Processor Systems-on-Chip (MPSoCs) have become a vital solution for meeting stringent performance, power, and scalability requirements. Efficient task mapping plays a crucial role in optimizing the performance of such systems, particularly for real-time applications that demand strict timing constraints. Traditional mapping techniques, including static and dynamic strategies, struggle with balancing execution time, energy efficiency, and communication overhead in heterogeneous MPSoC architectures. In this paper, we propose a novel approach for optimizing task mapping in MPSoCs, based on the Grey Wolf Optimizer (GWO), a bio-inspired metaheuristic renowned for its effectiveness in solving complex optimization problems. This methodology aims to minimize task execution times and communication delays by intelligently mapping real-time tasks onto heterogeneous processing elements (PEs), while also adhering to real-time constraints and reducing energy consumption. The results confirm that the improved GWO algorithm is a powerful tool for addressing the challenges of real-time task mapping in MPSoCs, providing a robust and scalable solution for future embedded systems. © 2024 Copyright for this paper by its authors.

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

iSTIMULI: Prescriptive Stimulus Design for Eye Movement Analysis of Patients with Parkinson’s Disease 16th

iSTIMULI: Prescriptive Stimulus Design for Eye Movement Ana...

引用

16th International Conference on Multi-disciplinary Trends in Artificial Intelligence, MIWAI 2023

作者： Akshay, S. Amudha, J. Kulkarni, Nilima Prashanth, L.K. Department of Computer Science School of Computing Amrita Vishwa Vidyapeetham Karnataka Mysuru India Department of Computer Science and Engineering School of Computing Amrita Vishwa Vidyapeetham Karnataka Bengaluru India Department of Computer Science and Engineering MIT SOC MIT Art Design and Technology University Pune India Parkinson’s and Movement Disorders Clinic Karnataka Bengaluru India Center for Parkinson’s Disease and Movement Disorders Manipal Hospital Miller’s road Bangalore India

ISBN: (纸本)9783031364013

With an increase in eye-tracking applications, there is a need for eye gaze data analytics to widen its scope to provide customized solutions. However, among several types of analytics such as predictive, descriptive, diagnostic, and prescriptive analytics providing insight into it is quite challenging. This work presents the need and role of prescriptive data analysis that can be carried out on eye gaze data pertaining to a specific study of research on the diagnosis of Parkinson’s disease patients during visual search and visual attention tasks. We further look at the various aspects like the image stimulus used, a task performed by the viewer, and its relation to the viewer’s eye movement behavior. iSTIMULI includes the design of the image stimuli used to classify the eye movements of Parkinson’s disease patients from healthy controls. visualizations of eye movements on the image stimulus designed are presented. A machine learning analysis is also provided that substantiates the significance of the stimuli with the highest f-measure of 73%. iSTIMULI establishes a relation between image stimulus and viewer behavior. As a prescriptive analysis model, iSTIMULI calculates the risk based on eye movements and recommends actions to be taken in the future to improve the ability of the participant. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Eye movements

来源：评论

学校读者我要写书评

暂无评论

Pose Estimation of Spacecraft Using Dual Transformers and Efficient Bayesian Hyperparameter Optimization

引用

International Journal of Advanced computer science and Applications 2025年第4期16卷 629-644页

作者： Raja, N. Kannaiya Ramesh, Janjhyam Venkata Naga El-Ebiary, Yousef A. Baker Muniyandy, Elangovan Reddy, N. Konda Kumar, Vanipenta Ravi Devarasetty, Prasad School of Computing Science and Engineering VIT Bhopal University Madhya Pradesh Bhopal466114 India Department of CSE Graphic Era Hill University Dehradun248002 India Department of CSE Graphic Era Deemed To Be University Uttarakhand Dehradun248002 India Faculty of Informatics and Computing UniSZA University Malaysia Department of Biosciences Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai602 105 India Applied Science Research Center Applied Science Private University Amman Jordan Department of Engineering Mathematics K L University Greenfields Guntur Dist Andhra Pradesh Vaddeswaram522302 India Department of Mathematics Annamacharya University New Boyanapalli Rajampet India Department of Computer Science and Engineering DVR & Dr HS MIC College of Technology Andhra Pradesh Kanchikacherla India

Spacecraft pose estimation is an essential contribution to facilitating central space mission activities like autonomous navigation, rendezvous, docking, and on-orbit servicing. Nonetheless, methods like Convolutional Neural Networks (CNNs), Simultaneous Localization and Mapping (SLAM), and Particle Filtering suffer significant drawbacks when implemented in space. Such techniques tend to have high computational complexity, low domain generalization capacity for varied or unknown conditions (domain generalization problem), and accuracy loss with noise from the space environment causes such as fluctuating lighting, sensor limitations, and background interference. In order to overcome these challenges, this study suggests a new solution through the combination of a Dual-Channel Transformer Network with Bayesian Optimization methods. The innovation is at the center with the utilization of EfficientNet, augmented with squeeze-and-excitation attention modules, to extract feature-rich representations without sacrificing computational efficiency. The dual-channel architecture dissects satellite pose estimation into two dedicated streams—translational data prediction and orientation estimation via quaternion-based activation functions for rotational precision. Activation maps are transformed into transformer-compatible sequences via 1×1 convolutions, allowing successful learning in the transformer's encoder-decoder system. To maximize model performance, Bayesian Optimization with Gaussian Process Regression and the Upper Confidence Bound (UCB) acquisition function makes the optimal hyperparameter selection with fewer queries, conserving time and resources. This entire framework, used here in Python and verified with the SLAB Satellite Pose Estimation Challenge dataset, had an outstanding Mean IOU of 0.9610, reflecting higher accuracy compared to standard models. In total, this research sets a new standard for spacecraft pose estimation, by marrying the versatility of deep le

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Communicative robot signals: Presenting a new typology for human-robot interaction 23

Communicative robot signals: Presenting a new typology for h...

引用

18th Annual ACM/IEEE International Conference on Human-Robot Interaction, HRI 2023

作者： Holthaus, Patrick Schulz, Trenton Lakatos, Gabriella Soma, Rebekka University of Hertfordshire School of Physics Engineering and Computer Science Hatfield United Kingdom Norwegian Computing Center Department of Applied Research in Ict Oslo Norway University of Oslo Department of Informatics Oslo Norway

ISBN: (纸本)9781450399647

We present a new typology for classifying signals from robots when they communicate with humans. For inspiration, we use ethology, the study of animal behaviour and previous efforts from literature as guides in defining the typology. The typology is based on communicative signals that consist of five properties: the origin where the signal comes from, the deliberateness of the signal, the signal's reference, the genuineness of the signal, and its clarity (i.e., how implicit or explicit it is). Using the accompanying worksheet, the typology is straightforward to use to examine communicative signals from previous human-robot interactions and provides guidance for designers to use the typology when designing new robot behaviours. © 2023 Copyright held by the owner/author(s).

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Publish/Subscribe for Edge Intelligence: Systematic Review and Future Prospects

SSRN

引用

SSRN 2024年

作者： Saleh, Alaa Tarkoma, Sasu Pirttikangas, Susanna Lovén, Lauri Center for Ubiquitous Computing University of Oulu Finland Department of Computer Science University of Helsinki Finland

The growth of the Internet of Things (IoT) has been exponential, resulting in billions of devices generating vast amounts of data. Given the varied and resource-limited nature of these IoT devices, there's a significant dependence on the device-edge-cloud computing continuum for *** data exchange paradigm typically used for these transmissions is the publish/subscribe (pub/sub) model, primarily because of its scalability and flexibility. In this review, we offer a comprehensive examination of pub/sub systems in the computing continuum, outlining their advantages, highlighting pivotal discoveries, identifying gaps, and suggesting future improvements that align with modern application demands. Our process starts with an analysis of existing surveys to pinpoint areas that require deeper exploration. Subsequently, we delve into diverse pub/sub paradigms, protocols, and message brokers, addressing their pros, cons, and potential enhancements. Unique to our paper is an in-depth exploration of the role of pub/sub systems in EdgeOps and their applications in real-time scenarios — topics previously untouched in other surveys. Additionally, we provide a summary of applications that have reaped the benefits of pub/sub systems. In conclusion, we highlight several unresolved challenges that could shape the future of the pub/sub model. We also suggest leveraging artificial intelligence and machine learning to introduce more adaptability and autonomy. © 2024, The Authors. All rights reserved.

关键词： Internet of things

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：