检索结果-内蒙古大学图书馆

Research on Construction of Corpus for Move Structures in Abstracts of English Scientific Research Articles 23

23rd Chinese National Conference on Computational Linguistics, CCL 2024

作者： Li, Hongzheng Wang, Ruojin Feng, Chong Liu, Fang School of Foreign Languages Key Laboratory of Language Cognition and Computation Ministry of Industry and Information Technology Beijing Institute of Technology No.9 Liangxiang East Road Fangshan District Beijing China School of Computer Science Beijing Institute of Technology No.5 Zhongguancun South St. Haidian District Beijing China

ISBN: (纸本)9780000000002

Move structures are discourse units in research articles (RA) and is of great value in move analysis, essay writing, etc. Although there is abundant research on move structures in academic articles, there are still relatively few move annotation data resources. This research developed and constructed a specific corpus for annotating move structures in English RA abstracts. Currently, nearly 34,000 Move structures have been annotated, covering the fields of Natural Language Processing (NLP), computer Vision (CV), Communication Engineering and Mechanical Engineering. We also presented annotation statistics and analysis. The first stage of corpus construction relies on manual annotation to form high-quality corpus data. In the second and main stage, an automatic recognition and annotation model based on BERT is adopted, which can improve the annotation speed and expand the annotation scale while ensuring the annotation quality. We conducted move structure recognition experiments based on the constructed corpus, and compared the performance of our model with large language models(LLM) including ChatGPT and Claude3. The experimental results show that the F1 scores of move structure recognition achieved by our model outperformed those of LLM, indicating the effectiveness of the proposed model. This corpus is currently publicly available and can provide necessary data resources for NLP related tasks such as scientific paper information extraction and English writing intelligent assistance, it is also beneficial to foreign language teaching and research such as English for Academic Purposes, it can effectively promote the digital transformation of foreign language education. © 2024 China National Conference on Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

An Auto-Parallel Method for Deep Learning Models Based on Genetic Algorithm

An Auto-Parallel Method for Deep Learning Models Based on Ge...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Yan Zeng ChengChuang Huang YiJie Ni ChunBao Zhou JiLin Zhang Jue Wang MingYao Zhou MeiTing Xue YunQuan Zhang School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Key Laboratory for Modeling and Simulation of Complex Systems Ministry of Education Hangzhou China Data Security Governance Zhejiang Engineering Research Center Hangzhou China School of ITMO Joint Institute Hangzhou Dianzi University Hangzhou China Institute of Computer Network Information Center of the Chinese Academy of Sciences Beijing China HuaWei State Key Laboratory of Computer Architecture Institute of Computing Technology of the Chinese Academy of Sciences Beijing China

As the size of datasets and neural network models increases, automatic parallelization methods for models have become a research hotspot in recent years. The existing auto-parallel methods based on machine learning or graph algorithms still have issues with search efficiency and applicability. This paper proposes an automatic parallel method based on a dual-population genetic algorithm, TGA, which transforms model partitioning and placement into an integer linear programming problem and constructs a cost model to evaluate the solution. The solution space is built using the neural network’s dataflow graph and device cluster’s topology, and the dual-population genetic algorithm is used to search for the optimal model parallel strategy. Experiments with various models show that the proposed method can improve single-step execution time by up to 42% compared to the Baechi method and up to 37.7% compared to the Hierarchical method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ad Hoc File Systems for High-Performance Computing

引用

Journal of computer science & Technology 2020年第1期35卷 4-26页

作者： AndréBrinkmann Kathryn Mohror Weikuan Yu Philip Carns Toni Cortes Scott A.Klasky Alberto Miranda Franz-Josef Pfreundt Robert B.Ross Marc-AndréVef Zentrum für Datenverarbeitung Johannes Gutenberg University MainzMainz 55128Germany Center for Applied Scientific Computing Lawrence Livermore National LaboratoryLivermoreCA 94550U.S.A Department of Computer Science Florida State UniversityTallahasseeFL 32306U.S.A Mathematics and Computer Science Division Argonne National LaboratoryLemontIL 60439U.S.A Department of Computer Architecture Universitat Politecnica de CatalunyaBarcelona 08034Spain Computer Science and Mathematics Division Oak Ridge National LaboratoryOak RidgeTN 37831U.S.A Computer Science Department Barcelona Supercomputing CenterBarcelona 08034Spain Fraunhofer Institute for Industrial Mathematics ITWM Fraunhofer-Platz 1Kaiserslautern 67663Germany

Storage backends of parallel compute clusters are still based mostly on magnetic disks,while newer and faster storage technologies such as flash-based SSDs or non-volatile random access memory(NVRAM)are deployed within compute *** these new storage technologies into scientific workflows is unfortunately today a mostly manual task,and most scientists therefore do not take advantage of the faster storage *** approach to systematically include nodelocal SSDs or NVRAMs into scientific workflows is to deploy ad hoc file systems over a set of compute nodes,which serve as temporary storage systems for single applications or longer-running *** paper presents results from the Dagstuhl Seminar 17202"Challenges and Opportunities of User-Level File Systems for HPC"and discusses application scenarios as well as design strategies for ad hoc file systems using node-local storage *** discussion includes open research questions,such as how to couple ad hoc file systems with the batch scheduling environment and how to schedule stage-in and stage-out processes of data between the storage backend and the ad hoc file *** presented are strategies to build ad hoc file systems by using reusable components for networking and how to improve storage device *** interfaces and semantics are presented,for example those used by the three ad hoc file systems BeeOND,GekkoFS,and *** presentation covers a range from file systems running in production to cutting-edge research focusing on reaching the performance limits of the underlying devices.

关键词： parallel architectures distributed file system high-performance computing burst buffer POSIX(portable operating system interface)

来源：评论

学校读者我要写书评

暂无评论

A Case for Adaptive Resource Management in Alibaba Datacenter Using Neural Networks

引用

Journal of computer science & Technology 2020年第1期35卷 209-220页

作者： Sa Wang Yan-Hai Zhu Shan-Pei Chen Tian-Ze Wu Wen-Jie Li Xu-Sheng Zhan Hai-Yang Ding Wei-Song Shi Yun-Gang Bao State Key Laboratory of Computer Architecture Institute of Computing TechnologyChinese Academy of Sciences Beijing 100190China University of Chinese Academy of Sciences Beijing 100049China Peng Cheng Laboratory Shenzhen 518055China Alibaba Inc. Hangzhou 311121China Department of Computer Science Wayne State UniversityMichiganMI 48202U.S.A

Both resource efficiency and application QoS have been big concerns of datacenter operators for a long time,but remain to be *** resource utilization increases the risk of resource contention between co-located workload,which makes latency-critical(LC)applications suffer unpredictable,and even unacceptable *** of prior work devotes the effort on exploiting effective mechanisms to protect the QoS of LC applications while improving resource *** this paper,we propose MAGI,a resource management runtime that leverages neural networks to monitor and further pinpoint the root cause of performance interference,and adjusts resource shares of corresponding applications to ensure the QoS of LC *** is a practice in Alibaba datacenter to provide on-demand resource adjustment for applications using neural *** experimental results show that MAGI could reduce up to 87.3%performance degradation of LC application when co-located with other antagonist applications.

关键词： resource management neural network resource efficiency tail latency

来源：评论

学校读者我要写书评

暂无评论

Continual Reinforcement Learning for Digital Twin Synchronization Optimization

arXiv

引用

arXiv 2025年

作者： Tong, Haonan Chen, Mingzhe Zhao, Jun Hu, Ye Yang, Zhaohui Liu, Yuchen Yin, Changchuan The Beijing Key Laboratory of Network System Architecture and Convergence The Beijing Advanced Information Network Laboratory Beijing University of Posts and Telecommunications Beijing China Singapore The Department of Electrical and Computer Engineering Frost Institute for Data Science and Computing University of Miami Coral GablesFL33146 United States The Department of Industrial and Systems Engineering University of Miami Coral GablesFL33146 United States The College of Information Science and Electronic Engineering Zhejiang University Zhejiang Hangzhou310027 China The Department of Computer Science North Carolina State University RaleighNC27695 United States The Beijing Key Laboratory of Network System Architecture and Convergence China The Beijing Advanced Information Network Laboratory Beijing University of Posts and Telecommunications Beijing100876 China

This article investigates the adaptive resource allocation scheme for digital twin (DT) synchronization optimization over dynamic wireless networks. In our considered model, a base station (BS) continuously collects factory physical object state data from wireless devices to build a real-time virtual DT system for factory event analysis. Due to continuous data transmission, maintaining DT synchronization must use extensive wireless resources. To address this issue, a subset of devices is selected to transmit their sensing data, and resource block (RB) allocation is optimized. This problem is formulated as a constrained Markov process (CMDP) problem that minimizes the long-term mismatch between the physical and virtual systems. To solve this CMDP, we first transform the problem into a dual problem that refines RB constraint impacts on device scheduling strategies. We then propose a continual reinforcement learning (CRL) algorithm to solve the dual problem. The CRL algorithm learns a stable policy across historical experiences for quick adaptation to dynamics in physical states and network capacity. Simulation results show that the CRL can adapt quickly to network capacity changes and reduce normalized root mean square error (NRMSE) between physical and virtual states by up to 55.2%, using the same RB number as traditional methods. © 2025, CC BY-NC-SA.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Human-like conceptual representations emerge from language prediction

arXiv

引用

arXiv 2025年

作者： Xu, Ningyu Zhang, Qi Du, Chao Luo, Qiang Qiu, Xipeng Huang, Xuanjing Zhang, Menghan School of Computer Science Fudan University Shanghai China Institute of Modern Languages and Linguistics Fudan University Shanghai China Shanghai Key Laboratory of Intelligent Information Processing Shanghai China Research Institute of Intelligent Complex Systems Fudan University Shanghai China Shanghai Collaborative Innovation Center of Intelligent Visual Computing Shanghai China Ministry of Education Key Laboratory of Contemporary Anthropology Fudan University Shanghai China

People acquire concepts through rich physical and social experiences and use them to understand the world. In contrast, large language models (LLMs), trained exclusively through next-token prediction over language data, exhibit remarkably human-like behaviors. Are these models developing concepts akin to humans, and if so, how are such concepts represented and organized? To address these questions, we reframed the classic reverse dictionary task to simulate human concept inference in context and investigated the emergence of human-like conceptual representations within LLMs. Our results demonstrate that LLMs can flexibly derive concepts from linguistic descriptions in relation to contextual cues about other concepts. The derived representations converged towards a shared, context-independent structure that effectively predicted human behavior across key psychological phenomena, including computation of similarities, categories and semantic scales. Moreover, these representations aligned well with neural activity patterns in the human brain, even in response to visual rather than linguistic stimuli, providing evidence for biological plausibility. These findings establish that structured, human-like conceptual representations can naturally emerge from language prediction without real-world grounding. More broadly, our work positions LLMs as promising computational tools for understanding complex human cognition and paves the way for better alignment between artificial and human intelligence. Copyright © 2025, 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

Aware: Adaptive Distributed Training with Computation, Communication and Position Awareness for Deep Learning Model

Aware: Adaptive Distributed Training with Computation, Commu...

引用

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

作者： Yan Zeng Guangzheng Yi Yuyu Yin Jiyang Wu Meiting Xue Jilin Zhang Jian Wan Yunquan Zhang School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China School of Cyberspace Hangzhou Dianzi University Hangzhou China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing China

The accuracy of the neural networks can usually be improved by increasing the size of the dataset and the layers or operators of the network, as it has strong composability. But, it makes a challenge to train these models efficiently, due to the limited resources of a single device, such as memory, computational resource and so on. For this challenge, it has become an inevitable trend to automatically implement model parallelism across multiple devices. This paper proposes Aware, an adaptive distributed parallel training method, to search distributed parallel strategy automatically for deep learning model. It firstly proposes an operator fusion strategy with computation and communication awareness to simplify the computational graph of deep learning model. And then, it introduces position-aware graph embedding algorithm to extract the structural features of models, which can make the searched parallel strategies to transplant to other networks with similar structures. On this basis, we use reinforcement learning algorithm to search distributed parallel strategy automatically. This paper makes experiments with neural networks such as Inception V3, NMT, GNM, NasNet and ResNet, and uses CIFAR10 and PTB datasets to compare the two methods of Hierarchical and Placeto. The results show that compared with Placeto, Aware achieves up to 5% reductions in runtime. Aware achieves more than 8% reductions in runtime compared with Hierarchical. Moreover, it has better transplantation and generalization capabilities, and supports pre-training for large-scale network parallel strategy search and accelerates convergence.

关键词： Deep learning Training Adaptation models Runtime Computational modeling Neural networks Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Deep-sea Nodule Mineral Image Segmentation Algorithm Based on Pix2PixHD

引用

computers, Materials & Continua 2022年第10期73卷 1449-1462页

作者： Wei Song Haolin Wang Xinping Zhang Jianxin Xia Tongmu Liu Yuxi Shi School of Information and Engineering Minzu University of ChinaBeijing100081China Key Laboratory of Marine Environmental Survey Technology and Application Ministry of Natural ResourceGuangzhou510300China National Language Resource Monitoring&Research Center of Minority Languages Beijing100081China School of Ocean Science China University of GeosciencesBeijing100191China Department of Buoy Engineering South China Sea Marine Survey and Technology CenterGuangzhou510300China Department of Electrical and Computer Engineering New Jersey Institute of TechnologyNewarkNew Jersey07102USA

Deep-sea mineral image segmentation plays an important role in deep-sea mining and underwater mineral resource monitoring and *** application of artificial intelligence technology to deep-sea mining projects can effectively improve the quality and efficiency of *** existing deep learning-based underwater image segmentation algorithms have problems such as the accuracy rate is not high enough and the running time is slightly *** order to improve the segmentation performance of underwater mineral images,this paper uses the Pix2PixHD(Pixel to Pixel High Definition)algorithm based on Conditional Generative Adversarial Network(CGAN)to segment deep-sea mineral *** model uses a coarse-to-fine generator composed of a global generation network and two local enhancement networks,and multiple multi-scale discriminators with same network structures but different input pictures to generate highquality *** test results on the deep-sea mineral datasets show that the Pix2PixHD algorithm can identify more target minerals under certain other *** evaluation index shows that the Pix2PixHD algorithm effectively improves the accuracy rate and the recall rate of deep-sea mineral image segmentation compared with the CGAN algorithm and the U-Net *** is important for expanding the application of deep learning techniques in the field of deep-sea exploration and mining.

关键词： Deep-sea mineral image segmentation generative adversarial network

来源：评论

学校读者我要写书评

暂无评论

A unified generative framework for various NER subtasks 59

A unified generative framework for various NER subtasks

引用

Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021

作者： Yan, Hang Gui, Tao Dai, Junqi Guo, Qipeng Zhang, Zheng Qiu, Xipeng Shanghai Key Laboratory of Intelligent Information Processing Fudan University China School of Computer Science Fudan University China Institute of Modern Languages and Linguistics Fudan University China New York University United States Pazhou Lab Guangzhou China

ISBN: (纸本)9781954085527

Named Entity Recognition (NER) is the task of identifying spans that represent entities in sentences. Whether the entity spans are nested or discontinuous, the NER task can be categorized into the flat NER, nested NER, and discontinuous NER subtasks. These subtasks have been mainly solved by the token-level sequence labelling or span-level classification. However, these solutions can hardly tackle the three kinds of NER subtasks concurrently. To that end, we propose to formulate the NER subtasks as an entity span sequence generation task, which can be solved by a unified sequence-to-sequence (Seq2Seq) framework. Based on our unified framework, we can leverage the pre-trained Seq2Seq model to solve all three kinds of NER subtasks without the special design of the tagging schema or ways to enumerate spans. We exploit three types of entity representations to linearize entities into a sequence. Our proposed framework is easy-to-implement and achieves state-of-the-art (SoTA) or near SoTA performance on eight English NER datasets, including two flat NER datasets, three nested NER datasets, and three discontinuous NER datasets. © 2021 Association for Computational Linguistics

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Digital Over-the-Air Federated Learning in Multi-Antenna Systems

arXiv

引用

arXiv 2023年

作者： Wang, Sihua Chen, Mingzhe Shen, Cong Yin, Changchuan Brinton, Christopher G. The Beijing Laboratory of Advanced Information Network The Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Beijing100876 China The Department of Electrical and Computer Engineering Institute for Data Science and Computing University of Miami Coral GablesFL33146 United States The Charles L. Brown Department of Electrical and Computer Engineering University of Virginia CharlottesvilleVA United States The School of Electrical and Computer Engineering Purdue University West LafayetteIN United States

In this paper, the performance optimization of federated learning (FL), when deployed over a realistic wireless multiple-input multiple-output (MIMO) communication system with digital modulation and over-the-air computation (AirComp) is studied. In particular, a MIMO system is considered in which edge devices transmit their local FL models (trained using their locally collected data) to a parameter server (PS) using beamforming to maximize the number of devices scheduled for transmission. The PS, acting as a central controller, generates a global FL model using the received local FL models and broadcasts it back to all devices. Due to the limited bandwidth in a wireless network, AirComp is adopted to enable efficient wireless data aggregation. However, fading of wireless channels can produce aggregate distortions in an AirComp-based FL scheme. To tackle this challenge, we propose a modified federated averaging (FedAvg) algorithm that combines digital modulation with AirComp to mitigate wireless fading while ensuring the communication efficiency. This is achieved by a joint transmit and receive beamforming design, which is formulated as an optimization problem to dynamically adjust the beamforming matrices based on current FL model parameters so as to minimize the transmitting error and ensure the FL performance. To achieve this goal, we first analytically characterize how the beamforming matrices affect the performance of the FedAvg in different iterations. Based on this relationship, an artificial neural network (ANN) is used to estimate the local FL models of all devices and adjust the beamforming matrices at the PS for future model transmission. The algorithmic advantages and improved performance of the proposed methodologies are demonstrated through extensive numerical experiments. Copyright © 2023, The Authors. All rights reserved.

关键词： Beamforming

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：