检索结果-内蒙古大学图书馆

2024 Findings of the Association for Computational Linguistics: NAACL 2024

作者： Guo, Shasha Liao, Lizi Zhang, Jing Wang, Yanling Li, Cuiping Chen, Hong School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering of Ministry of Education China Singapore Management University Singapore Zhongguancun Laboratory China

ISBN: (纸本)9798891761193

knowledge base question generation (KBQG) aims to generate natural language questions from a set of triplet facts extracted from KB. Existing methods have significantly boosted the performance of KBQG via pre-trained language models (PLMs) thanks to the richly endowed semantic knowledge. With the advance of pre-training techniques, large language models (LLMs) (e.g., GPT-3.5) undoubtedly possess much more semantic knowledge. Therefore, how to effectively organize and exploit the abundant knowledge for KBQG becomes the focus of our study. In this work, we propose SGSH - a simple and effective framework to Stimulate GPT-3.5 with Skeleton Heuristics to enhance KBQG. The framework incorporates "skeleton heuristics", which provides more fine-grained guidance associated with each input to stimulate LLMs to generate optimal questions, encompassing essential elements like the question phrase and the auxiliary verb. More specifically, we devise an automatic data construction strategy leveraging ChatGPT to construct a skeleton training dataset, based on which we employ a soft prompting approach to train a BART model dedicated to generating the skeleton associated with each input. Subsequently, skeleton heuristics are encoded into the prompt to incentivize GPT-3.5 to generate desired questions. Extensive experiments demonstrate that SGSH derives the new state-of-the-art performance on the KBQG tasks. The code is now available on Github. © 2024 Association for Computational Linguistics.

关键词： knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

Rethinking-based Code Summarization with Chain of Comments 31

Rethinking-based Code Summarization with Chain of Comments

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Cao, Liuwen He, Hongkui Huang, Hailin Wang, Jiexin Cai, Yi School of Software Engineering South China University of Technology China Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China

ISBN: (纸本)9798891761964

Automatic code summarization aims to generate concise natural language descriptions (summary) for source code, which can free software developers from the heavy burden of manual commenting and software maintenance. Existing methods focus on learning a direct mapping from pure code to summaries, overlooking the significant heterogeneity gap between code and summary. Moreover, existing methods lack a human-like re-check process to evaluate whether the generated summaries match well with the code. To address these two limitations, we introduce RBCoSum, a novel framework that incorporates the generated Chain Of Comments (COC) as auxiliary intermediate information for the model to bridge the gap between code and summaries. Also, we propose a rethinking process where a learned ranker trained on our constructed ranking dataset scores the extent of matching between the generated summary and the code, selecting the highest-scoring summary to achieve a re-check process. We conduct extensive experiments to evaluate our approach and compare it with other automatic code summarization models as well as multiple code Large Language Models (LLMs). The experimental results show that RBCoSum is effective and outperforms baselines by a large margin. The human evaluation also proves the summaries generated with RBCoSum are more natural, informative, useful, and truthful. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

RGCNU: Recurrent Graph Convolutional Network With Uncertainty Estimation for Remaining Useful Life Prediction

引用

IEEE/CAA Journal of Automatica Sinica 2023年第7期10卷 1640-1642页

作者： Qiwu Zhu Qingyu Xiong Zhengyi Yang Yang Yu School of Big Data&Software Engineering Chongqing UniversityChongqing 400044 Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of EducationChongqing 400044China School of Biology and Engineering Guizhou Medical UniversityGuiyang 550025China

Dear Editor,This letter focuses on the problem of remaining useful life(RUL)prediction of equipment. Existing graph neural network(GCN)-based approaches merely provide the point estimation of RUL. However,the estimated RUL often varies widely due to the model parameters and the noise in data. It is important to know the uncertainty in predictions for reliable risk analysis and maintenance decision *** map the relationship between noisy condition monitoring data and RUL with uncertainty.

关键词： letter estimation prediction

来源：评论

学校读者我要写书评

暂无评论

Ongoing Compressional Tectonism and Regional Seismic Hazard Revealed by the 2023 Mw6.1 Jishishan Earthquake

引用

Journal of Earth Science 2025年第1期36卷 275-290页

作者： Xiaoning Hu Chen Yu Zhenjiang Liu Yingying Zhang Zhenhong Li Chuang Song Bingquan Han Haihui Liu Jie Li College of Geological Engineering and Geomatics Chang'an UniversityXi'an 710054China Key Laboratory of Loess Xi'an 710054China Big Data Center for Geosciences and Satellites Chang'an UniversityXi'an 710054China Key Laboratory of Western China's Mineral Resources and Geological Engineering Ministry of EducationXi'an 710054China China Earthquake Networks Center Beijing 100045China

On December 18,2023,a Mw6.1 earthquake struck Jishishan County,Gansu Province,China,marking the most significant earthquake in the northeastern edge of the Tibetan Plateau since *** its proximate to the Loess Plateau,which is extremely susceptible to geohazards,this earthquake raises awareness about the seismic hazard of several mega-cities such as Xi'an in Northwest *** this paper,we inferred that the rupture occurred on an east-dipping backthrust,resulting from the regional E-W contraction tectonic *** dynamic model through teleseismic waves and static model through radar displacement measurements together reveal a unilateral,along-strike rupture,encountering a slip barrier at one side of the main slip patch causing a cluster of *** also identified a high-dip structure,which is an early-stage backthrust fault whose dip becomes increasingly high due to regional compressional *** from the loaded fault segments,particularly on the fault linkage,which necessitate continuous examination,a detailed seismic hazard assessment of the west Qinling and Daotanghe-Linxia fault system identifies a seismic gap between Weiyuan and Dingxi with the potential for a Mw7.5 ***,these findings provide valuable insights into the seismic behavior of the seismogenic fault as well as guidance on hazard mitigation in its surrounding fault systems.

关键词： 2023 Jishishan Earthquake dynamic rupture process coseismic displacements seismic hazard assessment fault slips mechanics

来源：评论

学校读者我要写书评

暂无评论

Two efficient beamforming methods for hybrid IRS-aided AF relay wireless networks

引用

Science China(Information Sciences) 2025年第4期68卷 363-379页

作者： Xuehui WANG Qingbo LI Wen ZHU Feng SHU Mengxing HUANG Fuhui ZHOU Riqing CHEN Cunhua PAN Yongpeng WU Jiangzhou WANG School of Mathematics and Statistics Hainan Normal University Key Laboratory of Data Science and Smart Education Ministry of Education Hainan Normal University School of Information and Communication Engineering Hainan University Collaborative Innovation Center of Information Technology Hainan University School of Electronic and Optical Engineering Nanjing University of Science and Technology College of Electronic and Information Engineering Nanjing University of Aeronautics and Astronautics Digital Fujian Institute of Big Data for Agriculture Fujian Agriculture and Forestry University National Mobile Communications Research Laboratory Southeast University Shanghai Key Laboratory of Navigation and Location Based Services Shanghai Jiao Tong University School of Engineering University of Kent

Owing to its ability to mitigate the double-fading effect by amplifying the reflected signal, the active intelligent reflecting surface(IRS) has garnered significant attention. In this paper, an amplify-and-forward(AF) relay network assisted by a hybrid IRS consisting of both passive and active units is developed. A signal-to-noise ratio(SNR) maximization problem is formulated, where the AF relay beamforming matrix and the hybrid IRS reflecting coefficient matrices for two-time slots need to be optimized. To address the SNR maximization problem, this paper proposes both a high-performance(HP) method and a low-complexity(LC) method. The HP method is based on the semidefinite relaxation and fractional programming(SDR-FP)algorithm, with rank-1 solutions obtained through Gaussian randomization. For the LC method, the amplification coefficient of each active IRS element is assumed to be equal. The SNR maximization problem is then addressed using the whitening filter,generalized power iteration, and generalized Rayleigh-Ritz(WF-GPI-GRR) approach. Simulation results show that compared with the benchmarks, such as the passive IRS-aided AF relay network, the proposed HP-SDR-FP and WF-GPI-GRR methods achieve significant rate improvements. In particular, the HP-SDR-FP and WF-GPI-GRR methods yield more than a 135.0%rate gain when the transmit power Ps of the source is 10 dBm. Furthermore, the proposed HP-SDR-FP method outperforms the WF-GPI-GRR method in terms of rate performance.

关键词： double-fading intelligent reflecting surface active elements passive elements hybrid IRS AF relay

来源：评论

学校读者我要写书评

暂无评论

Lightweight Dual Grouped Large-Kernel Convolutions for Salient Object Detection Network 31st

Lightweight Dual Grouped Large-Kernel Convolutions for Sali...

引用

31st International Conference on Multimedia Modeling, MMM 2025

作者： Liu, Jiajie Zhang, Zhibin Engineering Research Center of Ecological Big Data Ministry of Education Beijing China Key Laboratory of Wireless Networks and Mobile Computing Inner Mongolia University Hohhot010021 China

ISBN: (纸本)9789819620609

Most existing Salient Object Detection (SOD) methods focus on achieving better performance, often resulting in models with a large number of parameters. However, there is limited research on lightweight models in this field. To address this gap, our goal is to maintain performance while reducing the number of network parameters. Thanks to the development of large-kernel convolutions in recent years, we have improved the U2Net as the base network by adding our lightweight dual large-kernel fusion module. Our module better utilizes the depth information of U2Net and, due to the large receptive field of large-kernel convolutions, better captures the relationships between image elements. This allows our network to remain lightweight while maintaining performance. We designed a large-kernel (DLK) fusion module and a lightweight dual grouped large-kernel Unet network (DGLKUNET). Our network uses SRUS (an improved Residual U-blocks module, RUS) to construct DGLKUNET that predicts image contours and labels. Compared to the base RUS network (U2Net), our network reduces the number of parameters by up to 70% and the computational cost by 40% while maintaining performance. Evaluation results on five datasets demonstrate the performance of our lightweight network. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

NI-GDBA: Non-Intrusive Distributed Backdoor Attack Based on Adaptive Perturbation on Federated Graph Learning 25

NI-GDBA: Non-Intrusive Distributed Backdoor Attack Based on ...

引用

34th ACM Web Conference, WWW 2025

作者： Li, Ken Shi, Bin Wei, Jiazhe Dong, Bo School of Computer Science and Technology Xi’an Jiaotong University Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi’an China School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an China School of Distance Education Xi’an Jiaotong University Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an China

ISBN: (纸本)9798400712746

Federated Graph Learning (FedGL) is an emerging Federated Learning (FL) framework that learns the graph data from various clients to train better Graph Neural Networks(GNNs) model. Owing to concerns regarding the security of such framework, numerous studies have attempted to execute backdoor attacks on FedGL, with a particular focus on distributed backdoor attacks. However, all existing methods posting distributed backdoor attack on FedGL only focus on injecting distributed backdoor triggers into the training data of each malicious client, which will cause model performance degradation on original task and is not always effective when confronted with robust federated learning defense algorithms, leading to low success rate of attack. What’s more, the backdoor signals introduced by the malicious clients may be smoothed out by other clean signals from the honest clients, which potentially undermining the performance of the attack. To address the above significant shortcomings, we propose a non-intrusive graph distributed backdoor attack(NI-GDBA) that does not require backdoor triggers to be injected in the training data. Our attack trains an adaptive perturbation trigger generator model for each malicious client to learn the natural backdoor from the GNN model downloading from the server with the malicious client’s local data. In contrast to traditional distributed backdoor attacks on FedGL via trigger injection in training data, our attack on different datasets such as Molecules and Bioinformatics have higher attack success rate, stronger persistence and stealth, and has no negative impact on the performance of the global GNN model. We also explore the robustness of NI-GDBA under different defense strategies, and based on our extensive experimental studies, we show that our attack method is robust to current federated learning defense methods, thus it is necessary to consider non-intrusive distributed backdoor attacks on FedGL as a novel threat that requires custom d

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Task Offloading Optimization Based on Position Prediction in Pedestrian- Robot Mixed Traffic Flows 8

Task Offloading Optimization Based on Position Prediction in...

引用

8th IEEE International Conference on Computer and Communications, ICCC 2022

作者： Zheng, Dawen Wang, Lusheng Kai, Caihong Peng, Min Key Laboratory of Knowledge Engineering with Big Data Ministry of Education School of Computer Science and Information Engineering Hefei University of Technology Hefei China

ISBN: (纸本)9781665450515

Service robots play an increasingly important role in people's daily life. The density of pedestrians is large and the movement is irregular in pedestrian-robot mixed traffic flows. Robots are prone to collision with pedestrians, and the tasks to be offloaded are closely related to pedestrians. How to analyze the tasks of robots and select the appropriate roadside unit is an important issue. In this paper, the social force model is used to predict the positions of pedestrians and robots, taking into account the influence of various forces to avoid collisions. A task offloading resource optimization algorithm with position prediction is proposed. According to the predicted information, the size and position distribution of all tasks in the scenario are obtained, and then the neural network trained beforehand based on deep Q-Iearning is used to generate a task offloading strategy. The simulation results show that the running time of the proposed algorithm is very short, and the resource allocation required for task offloading is completed in advance based on the predicted information before robots arriving the corresponding positions. Besides, the algorithm significantly reduces the task offloading delay. © 2022 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Step Feasibility-Aware and Error-Correctable Entailment Tree Generation 30

Step Feasibility-Aware and Error-Correctable Entailment Tree...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Song, Junyue Wu, Xin Cai, Yi School of Software Engineering South China University of Technology China Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China

ISBN: (纸本)9782493814104

An entailment tree is a structured reasoning path that clearly demonstrates the process of deriving hypotheses through multiple steps of inference from known premises. It enhances the interpretability of QA systems. Existing methods for generating entailment trees typically employ iterative frameworks to ensure reasoning faithfulness. However, they often suffer from the issue of false feasible steps, where selected steps appear feasible but actually lead to incorrect intermediate conclusions. Moreover, the existing iterative frameworks do not consider error-prone search branches, resulting in error propagation. In this work, we propose SPEH: an iterative entailment tree generation framework with Step fesibility Perception and state Error Handling mechanisms. Step Feasibility Perception enables the model to learn how to choose steps that are not false feasible. State Error Handling includes error detection and backtracking, allowing the model to correct errors when entering incorrect search branches. Experimental results demonstrate the effectiveness of our approach in improving the generation of entailment trees. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

A Graph with Adaptive AdjacencyMatrix for Relation Extraction

引用

Computers, Materials & Continua 2024年第9期80卷 4129-4147页

作者： Run Yang YanpingChen Jiaxin Yan Yongbin Qin Engineering Research Center of Text Computing&Cognitive Intelligence Ministry of EducationGuizhou UniversityGuiyang550025China State Key Laboratory of Public Big Data Guizhou UniversityGuiyang550025China College of Computer Science and Technology Guizhou UniversityGuiyang550025China

The relation is a semantic expression relevant to two named entities in a *** a sentence usually contains several named entities,it is essential to learn a structured sentence representation that encodes dependency information specific to the two named *** related work,graph convolutional neural networks are widely adopted to learn semantic dependencies,where a dependency tree initializes the adjacency ***,this approach has two main ***,parsing a sentence heavily relies on external toolkits,which can be ***,the dependency tree only encodes the syntactical structure of a sentence,which may not align with the relational semantic *** this paper,we propose an automatic graph learningmethod to autonomously learn a sentence’s structural *** of using a fixed adjacency matrix initialized by a dependency tree,we introduce an Adaptive Adjacency Matrix to encode the semantic dependency between *** elements of thismatrix are dynamically learned during the training process and optimized by task-relevant learning objectives,enabling the construction of task-relevant semantic dependencies within a *** model demonstrates superior performance on the TACRED and SemEval 2010 datasets,surpassing previous works by 1.3%and 0.8%,*** experimental results show that our model excels in the relation extraction task,outperforming prior models.

关键词： Relation extraction graph convolutional neural network adaptive adjacency matrix

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：