检索结果-内蒙古大学图书馆

22nd Chinese National Conference on computational Linguistics, CCL 2023

作者： Li, Juncai Yan, Zhichao Su, Xuefeng Ma, Boxiang Yang, Peiyuan Li, Ru School of Computer and Information Technology Shanxi University Shanxi Taiyuan030006 China Key Laboratory of Computational Intelligence and Chinese Information Processing Ministry of Education Shanxi University Shanxi Taiyuan030006 China School of Modern Logistics Shanxi Vocational University of Engineering Science and Technology Shanxi Jinzhong030609 China

ISBN: (纸本)9781713889908

The Chinese Frame Semantic Parsing Evaluation Task aims to enhance the machine models’ ability to understand fine-grained semantic information. The evaluation dataset consists of 20,000 annotated examples of frame semantic parsing and nearly 700 frame annotations. The evaluation task is divided into three subtasks: frame identification, argument identification, and role identification. This evaluation has attracted wide attention from both industry and academia, with a total of 55 teams participating, and 12 teams submitting their results. We selected models from 5 teams for result reproduction, and ultimately, Li Zuoheng from Sichuan ranked first with a score of 71.49. More information about this task, can be found on the website of the CCL-2023 Chinese Frame Semantic Parsing Evaluation Task. © 2023 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

A Null Instantiation Filling Method based Frame Semantic Scenario Graph 22

A Null Instantiation Filling Method based Frame Semantic Sce...

引用

22nd Chinese National Conference on computational Linguistics, CCL 2023

作者： Wang, Yuzhi Li, Ru Su, Xuefeng Yan, Zhichao Li, Juncai School of Computer and Information Technology Shanxi University Shanxi Taiyuan030006 China Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education Shanxi University Shanxi Taiyuan030006 China School of Modern Logistics Shanxi Vocational University of Engineering Science and Technology Shanxi Jinzhong030609 China

ISBN: (纸本)9781713876229

Null Instantiation Filling aims to find the corresponding filling content for the implicit semantic roles of a given sentence in the context of the discourse. Traditional Null Instantiation Filling methods use a pipeline model that could cause error propagation and ignore the importance of explicit semantic *** address these issues, this paper proposes an end-to-end Null Instantiation Filling method that combines the Chinese FrameNet information to construct a Frame Semantic Scenario Graph and uses GAT to model it. The proposed method obtains candidate filling item representations that integrate explicit frame element information, enhancing the model's ability to recognize implicit semantic components. Experimental results demonstrate that the proposed model compared to the baseline model, the F1 value has increased by 9.16%. © 2023 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

Accelerating evolutionary neural architecture search via multi-fidelity evaluation

arXiv

引用

arXiv 2021年

作者： Yang, Shangshang Tian, Ye Xiang, Xiaoshu Peng, Shichen Zhang, Xingyi Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Artificial Intelligence Anhui University Hefei230039 China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Institutes of Physical Science and Information Technology Anhui University Hefei230601 China

Evolutionary neural architecture search (ENAS) has recently received increasing attention by effectively finding high-quality neural architectures, which however consumes high computational cost by training the architecture encoded by each individual for complete epochs in individual evaluation. Numerous ENAS approaches have been developed to reduce the evaluation cost, but it is often difficult for most of these approaches to achieve high evaluation accuracy. To address this issue, in this paper we propose an accelerated ENAS via multifidelity evaluation termed MFENAS, where the individual evaluation cost is significantly reduced by training the architecture encoded by each individual for only a small number of epochs. The balance between evaluation cost and evaluation accuracy is well maintained by suggesting a multi-fidelity evaluation, which identifies the potentially good individuals that cannot survive from previous generations by integrating multiple evaluations under different numbers of training epochs. For high diversity of neural architectures, a population initialization strategy is devised to produce different neural architectures varying from ResNetlike architectures to Inception-like ones. Experimental results on CIFAR-10 show that the architecture obtained by the proposed MFENAS achieves a 2.39% test error rate at the cost of only 0.6 GPU days on one NVIDIA 2080TI GPU, demonstrating the superiority of the proposed MFENAS over state-of-the-art NAS approaches in terms of both computational cost and architecture quality. The architecture obtained by the proposed MFENAS is then transferred to CIFAR-100 and ImageNet, which also exhibits competitive performance to the architectures obtained by existing NAS approaches. The source code of the proposed MFENAS is available at https://***/DevilYangS/MFENAS/.MSC Codes 68W50, 68T07 © 2021, CC BY.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Short-Time Variational Mode Decomposition

arXiv

引用

arXiv 2025年

作者： Jia, Hao Cao, Pengfei Liang, Tong Caiafa, Cesar F. Sun, Zhe Kushihashi, Yasuhiro Grau, Antoni Bolea, Yolanda Duan, Feng Solé-Casals, Jordi School of Medicine Nankai University Tianjin China Tianjin Key Laboratory of Interventional Brain-Computer Interface and Intelligent Rehabilitation Tianjin China Universitat Politècnica de Catalunya Barcelona Spain Mechanical Systems Engineering Nippon Institute of Technology Saitama Japan Villa Elisa Argentina Computational Bioengineering Laboratory Faculty of Health Data Science Juntendo University Tokyo Japan Data and Signal Processing Research Group University of Vic-Central University of Catalonia Vic Spain

Variational mode decomposition (VMD) and its extensions like Multivariate VMD (MVMD) decompose signals into ensembles of band-limited modes with narrow central frequencies. These methods utilize Fourier transformations to shift signals between time and frequency domains. However, since Fourier transformations span the entire time-domain signal, they are suboptimal for non-stationary time series. We introduce Short-Time Variational Mode Decomposition (STVMD), an innovative extension of the VMD algorithm that incorporates the Short-Time Fourier transform (STFT) to minimize the impact of local disturbances. STVMD segments signals into short time windows, converting these segments into the frequency domain. It then formulates a variational optimization problem to extract band-limited modes representing the windowed data. The optimization aims to minimize the sum of the bandwidths of these modes across the windowed data, extending the cost functions used in VMD and MVMD. Solutions are derived using the alternating direction method of multipliers, ensuring the extraction of modes with narrow bandwidths. STVMD is divided into dynamic and non-dynamic types, depending on whether the central frequencies vary with time. Our experiments show that non-dynamic STVMD is comparable to VMD with properly sized time windows, while dynamic STVMD better accommodates non-stationary signals, evidenced by reduced mode function errors and tracking of dynamic central frequencies. This effectiveness is validated by steady-state visual-evoked potentials in electroencephalogram signals. Copyright © 2025, The Authors. All rights reserved.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

key-Elements Graph Constructed with Evidence Sentence Extraction for Gaokao Chinese 9th

Key-Elements Graph Constructed with Evidence Sentence Extrac...

引用

9th CCF International Conference on Natural Language processing and Chinese Computing, NLPCC 2020

作者： Wang, Xiaoyue Ji, Yu Li, Ru School of Computer and Information Technology Shanxi University Taiyuan China Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education Shanxi University Taiyuan China

ISBN: (纸本)9783030604561

Multiple choice questions from university admission exams (Gaokao in Chinese) is a challenging AI task since it requires effective representation to capture complicated semantic relations between sentences in the article and strong ability to handle long text. Face the above challenges, we propose a key-elements graph to enhance context semantic representation and a comprehensive evidence extraction method inspired by existing methods. Our model first extracts evidence sentences from a passage according to the corresponding question and options to reduce the impact of noise. Then combines syntactic analysis techniques with graph neural network to construct the key-elements graph bases on the extracted sentences. Finally, fusing the learned graph nodes representation into context representation to enhancing syntactic information. Experiments on Gaokao Chinese multiple-choice dataset demonstrate the proposed model obtains substantial performance gains over various neural model baselines in terms of accuracy. © 2020, Springer Nature Switzerland AG.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

2d Human Pose Estimation with Explicit Anatomical keypoints Structure Constraints

SSRN

引用

SSRN 2023年

作者： Ji, Zhangjian Wang, Zilong Zhang, Ming Chen, Yapeng Qian, Yuhua No.92 Wucheng Rd. Xiaodian District Taiyuan China School of Computer & Information Technology Shanxi University Taiyuan China Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education Shanxi University Taiyuan China Institute of Big Data Science and Industry Shanxi University Taiyuan China

Recently, human pose estimation mainly focuses on how to design a more effective and better deep network structure as human features extractor, and most designed feature extraction networks only introduce the position of each anatomical keypoint to guide their training process. However, we found that some human anatomical keypoints kept their topology invariance, which can help to localize them more accurately when detecting the keypoints on the feature map. But to the best of our knowledge, there is no literature that has specifically studied it. Thus, in this paper, we present a novel 2D human pose estimation method with explicit anatomical keypoints structure constraints, which introduces the topology constraint term that consisting of the differences between the distance and direction of the keypoint-to-keypoint and their groundtruth in the loss object. More importantly, our proposed model can be plugged in the most existing bottom-up or top-down human pose estimation methods and improve their performance. The extensive experiments on the benchmark dataset: COCO keypoint dataset, show that our methods perform favorably against the most existing bottom-up and topdown human pose estimation methods, especially for Lite-HRNet, when our model is plugged into it, its AP scores separately raise by 2.9% and 3.3% on COCO val2017 and test-dev2017 datasets. © 2023, The Authors. All rights reserved.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Connecting Disconnected Agents in Multiagent Systems via Federated Control

Connecting Disconnected Agents in Multiagent Systems via Fed...

引用

European Control Conference (ECC)

作者： Rongrong Qian Zhisheng Duan Yuan Qi Tao Peng Wenbo Wang School of Artificial Intelligence Beijing University of Posts and Telecommunications (BUPT) Beijing China State Key Laboratory for Turbulence and Complex Systems College of Engineering Peking University Beijing China School of Electronic Engineering Beijing University of Posts and Telecommunications (BUPT) Beijing China Wireless Signal Processing and Network Lab (Key Lab. of Universal Wireless Communication Ministry of Education) Beijing University of Posts and Telecommunications (BUPT) Beijing China

ISBN: (数字)9783907144107

ISBN: (纸本)9798331540920

This study develops a control technique, called federated control, to connect disconnected agents in multiagent systems aided by control stations. Specifically, we first use a federated architecture to model multiagent systems with control stations. Based on this architecture, a federated-control procedure is proposed for the task of connecting disconnected agents, together with an initialization procedure. Then, how the federated-control procedure connects disconnected agents by incorporating simple global coordination (i.e., global averaging) is analyzed. We derive the close-form expression of the time sufficient to connect disconnected agents, which possesses interesting properties including early computability and delay independence. The convergence of the formation of multiagent systems and the velocities of all agents can also be proved.

关键词： Robot kinematics Oceans Computer architecture Control systems Space-air-ground integrated networks Path planning Delays

来源：评论

学校读者我要写书评

暂无评论

Arfis: A Model for Regression with Heavy-Tailed Distribution

SSRN

引用

SSRN 2023年

作者： Su, Meihong Zhang, Jifu Guo, Yaqing Wang, Wenjian The School of Computer Science and Technology Taiyuan University of Science and Technology Shanxi Province Taiyuan030024 China The School of Computer and Information Technology Shanxi University Shanxi Province Taiyuan030006 China The Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education Shanxi University Shanxi Province Taiyuan030006 China

As heavy-tailed distribution are ubiquitous in many real applications, robust regression has been extensively applied in machine learning and perform the superiority in deal with heavy-tailed distribution. Current existing robust mehods for regression are based on independence assumption of features and ignore interaction between them, which may lead to poor generalization due to most datasets unsatisfying the assumption. One common solution for the assumption is to explicitly augment a feature vector with products of features, but does not consider robustness. In this paper, we propose a novel adaptive robust feature interaction selection model for regression with heavy tailed distribution,termed Adaptive Robust Feature Interaction Selection (ARFIS). Firstly, we consider pairwise feature interaction by augmenting a feature vector with product of features for regression with heavy tailed distribution. Secondly, we propose feature interaction selection models based on quantile loss with different regularizes to learn parameters. The consistency of the proposed model ARFIS is proved theoretically, and an efficient algorithm is presented for solving proposed model. In the end, experimental results on simulation data, UCI and real-world datasets validate good accuracy, interpretability and robustness of our proposed models. © 2023, The Authors. All rights reserved.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

Unified-modal Salient Object Detection via Adaptive Prompt Learning

arXiv

引用

arXiv 2023年

作者： Wang, Kunpeng Li, Chenglong Tu, Zhengzheng Liu, Zhengyi Luo, Bin Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Hefei230601 China The Institute of Physical Science and Information Technology Anhui University Hefei230601 China

Existing single-modal and multi-modal salient object detection (SOD) methods focus on designing specific architectures tailored for their respective tasks. However, developing completely different models for different tasks leads to labor and time consumption, as well as high computational and practical deployment costs. In this paper, we attempt to address both single-modal and multi-modal SOD in a unified framework called UniSOD, which fully exploits the overlapping prior knowledge between different tasks. Nevertheless, assigning appropriate strategies to modality variable inputs is challenging. To this end, UniSOD learns modality-aware prompts with task-specific hints through adaptive prompt learning, which are plugged into the proposed pre-trained baseline SOD model to handle corresponding tasks, while only requiring few learnable parameters compared to training the entire model. Each modality-aware prompt is generated from a switchable prompt generation block, which adaptively performs structural switching based on single-modal and multi-modal inputs without human intervention. Through end-to-end joint training, UniSOD achieves overall performance improvement on 14 benchmark datasets for RGB, RGB-D, and RGB-T SOD, which demonstrates that our method effectively and efficiently unifies single-modal and multi-modal SOD tasks. The code and results are available at https://***/Angknpng/UniSOD. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Dual hesitant fuzzy graphs with applications to multi-attribute decision making

引用

International Journal of Cognitive Computing in Engineering 2020年 1卷 18-26页

作者： Bai, Wenhui Ding, Juanjuan Zhang, Chao School of Computer and Information Technology Shanxi University Taiyuan 030006 Shanxi China Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education Shanxi University Taiyuan 030006 Shanxi China

In real world, there exist a kind of Multi-Attribute Decision Making (MADM) problems in which correlations and prioritization relationships of attributes can be found. The notion of Fuzzy Graphs (FGs) performs well when expressing correlations between attributes via edges between vertices in fuzzy information systems, which makes it possible for addressing correlational MADM problems. In addition, as a significant information depiction tool, Dual Hesitant Fuzzy Sets (DHFSs) generalize traditional Intuitionistic Fuzzy Sets (IFSs) to the context of hesitations, thus DHFSs excel in recording numerous imprecise and hesitant information. In this paper, we aim to investigate FGs in the Dual Hesitant Fuzzy (DHF) background and further explore efficient approaches to complicated MADM situations. Following the above motivation, we first develop the definition of Dual Hesitant Fuzzy Graphs (DHFGs). Then, some common operational laws and mapping relationships are put forward. Afterwards, we construct a two-stage MADM approach by means of DHFGs for addressing complicated MADM situations with correlations and prioritization relationships. At last, a realistic case study along with a comparative analysis is presented to show the applicability of the established methodology. The proposed model and approach are conducive to addressing DHF MADM problems that are characterized by correlations and prioritization relationships between attributes at the same time, and further enrich the family of DHF MADM methods to a large extent. © 2020 The Authors

关键词： Dual hesitant fuzzy graphs Dual hesitant fuzzy sets Fuzzy graphs Multi-attribute decision making

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：