检索结果-内蒙古大学图书馆

31st International Conference on Computational Linguistics, COLING 2025

作者： Zhao, Yike Wang, Xiaoman Lan, Yunshi Qian, Weining School of Data Science and Engineering East China Normal University Shanghai Engineering Research Center of Big Data Management China

ISBN: (纸本)9798891761988

Grammatical Error Correction is an important research direction in NLP field. Although many models of different architectures and datasets across different languages have been developed to support the research, there is a lack of a comprehensive evaluation on these models, and different architectures make it hard for developers to implement these models on their own. To address this limitation, we present UnifiedGEC, the first open-source GEC-oriented toolkit, which consists of several core components and reusable modules. In UnifiedGEC, we integrate 5 widely-used GEC models and compare their performance on 7 datasets in different languages. Additionally, GEC-related modules such as data augmentation, prompt engineering are also deployed in it. Developers are allowed to implement new models, run and evaluate on existing benchmarks through our framework in a simple way. Code, documents and detailed results of UnifiedGEC are available at https://***/AnKate/UnifiedGEC. ©2025 Association for Computational Linguistics.

关键词： Error correction

来源：评论

学校读者我要写书评

暂无评论

Large Language Models are Good Annotators for Type-aware data Augmentation in Grammatical Error Correction 31

Large Language Models are Good Annotators for Type-aware Dat...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Li, Xinyuan Lan, Yunshi East China Normal University China Shanghai Engineering Research Center of Big Data Management China

ISBN: (纸本)9798891761964

Large Language Models (LLMs) have achieved outstanding performance across various NLP tasks. Grammatical Error Correction (GEC) is a task aiming at automatically correcting grammatical errors in text, but it encounters a severe shortage of annotated data. researchers have tried to make full use of the generalization capabilities of LLMs and prompt them to correct erroneous sentences, which however results in unexpected over-correction issues. In this paper, we rethink the role of LLMs in GEC tasks and propose a method, namely TypeDA, considering LLMs as the annotators for type-aware data augmentation in GEC tasks. Different from the existing data augmentation methods, our method prevents in-distribution corruption and is able to generate sentences with multi-granularity error types. Our experiments verify that our method can generally improve the GEC performance of different backbone models with only a small amount of augmented data. Further analyses verify the high consistency and diversity of the pseudo data generated via our method. Our code can be accessed via the provided URL. © 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

Psychological Counseling with Integration of Knowledge Graph and Multi-Agent Collaboration

引用

Journal of shanghai Jiaotong University (Science) 2025年 1-13页

作者： Liu, Xi Zheng, Xiaohu Cui, Weiwei College of Information Science and Technology Donghua University Shanghai201620 China Institute of artificial Intelligence Donghua University Shanghai201620 China Shanghai Engineering Center of Industrial Big Data and Intelligent System Shanghai201620 China Management College Wuzhou University Guangxi Wuzhou543003 China

Applying large language models (LLMs) to psychological counseling can reduce costs and lower barriers to access. However, issues inherent to LLMs, such as output hallucinations, knowledge lags, and response biases, limit the quality of counseling services. To address these challenges, we propose a psychological counseling method that integrates a knowledge graph (KG) and multi-agent collaboration (MAC). First, we design an ontology model and use an improved convolution residual network (CRN) to extract relational triples for constructing a psychological medicine KG. Second, we perform low-rank adaptation (LoRA) on Qwen1.5-7B-chat using the Text2Cypher training set. Finally, we design MAC prompts based on the characteristics of the retrieval-based question-answering (QA) process to facilitate the collaborative implementation of psychological medicine knowledge QA and updates. The experiments showed that the improved CRN achieved an extraction accuracy of 80%. The mean squared error of the general-domain capability of the LLM before and after LoRA was only 0.738, with a Text2Cypher score of 99.8 after LoRA. The results generated after prompting received a 70.44% approval rate compared to other methods. Thus, the proposed method can effectively enhance the intelligence, accuracy, and controllability of psychological counseling. © shanghai Jiao Tong University 2024.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Puzzle mode graph learning with pattern composition relationships reasoning for defect detection of printed products

引用

Journal of Manufacturing systems 2025年 81卷 34-48页

作者： Zhu, Zixun Zhang, Jie Wang, Junliang Zhang, Peng Li, Jiacheng College of Mechanical Engineering Donghua University Shanghai China Engineering Research Center of Artificial Intelligence for Textile Industry Ministry of Education Institute of Artificial Intelligence Donghua University Shanghai China Shanghai Engineering Research Center of Industrial Big Data Intelligent System Institute of Artificial Intelligence Donghua University Shanghai China College of Materials Science and Engineering Donghua University Shanghai China

Patterns are designs composed of specific elements and are widely present in various printed products, representing particular design intentions. However, due to printing errors, pattern defects are extremely common in these products, significantly impacting their visual quality and market price, especially in high-value customized products like luxury apparel, premium wallpapers and decorative tiles. Traditional detection methods struggle to provide effective judgments with conventional visual cues purely and frequently fall short due to the intricate nature of the pattern composition. To overcome this challenge, we propose a puzzle mode graph learning method capable of reasoning about pattern composition relationships. This novel detection framework simulates the logical reasoning ability of humans in assembling unordered puzzle pieces into a complete pattern, thus surpassing spatial structure limitations and enabling structural defect detection in patterns. Specifically, a parametric representation function is integrated into convolutional layers to enhance the segmentation accuracy of shape masks. Then, cross-graph semantic matching rules are developed to dynamically re-encode the adjacency matrix, enabling the construction of an attribute relationship graph that explicitly describes pattern attributes, including pattern elements, color sequences and shape positions. Moreover, the defective reasoning mechanism calculates puzzle-mode scores to decouple semantic relationships of defect features, inferring anomalous node and edge weights affecting the graph structure, thereby facilitating more precise judgments of pattern defects. Comparative experiments conducted on a real printed defect dataset validate this method. Results demonstrate its effectiveness and robustness in identifying complex pattern defects, providing essential support for appearance quality control in high-end industrial products. © 2025 The Society of Manufacturing Engineers

关键词： Computer control

来源：评论

学校读者我要写书评

暂无评论

RELIEF: Reinforcement Learning Empowered Graph Feature Prompt Tuning 25

RELIEF: Reinforcement Learning Empowered Graph Feature Promp...

引用

Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and data Mining V.1

作者： Jiapeng Zhu Zichen Ding Jianxiang Yu Jiaqi Tan Xiang Li Weining Qian East China Normal University Shanghai China East China Normal University Shanghai China Engineering Research Center of Blockchain Data Management (East China Normal University) Ministry of Education Shanghai China & Shanghai Engineering Research Center of Big Data Management Shanghai China

ISBN: (纸本)9798400712456

The advent of the "pre-train, prompt'' paradigm has recently extended its generalization ability and data efficiency to graph representation learning, following its achievements in Natural Language Processing (NLP). Initial graph prompt tuning approaches tailored specialized prompting functions for Graph Neural Network (GNN) models pre-trained with specific strategies, such as edge prediction, thus limiting their applicability. In contrast, another pioneering line of research has explored universal prompting via adding prompts to the input graph's feature space, thereby removing the reliance on specific pre-training strategies. However, the necessity to add feature prompts to all nodes remains an open question. Motivated by findings from prompt tuning research in the NLP domain, which suggest that highly capable pre-trained models need less conditioning signal to achieve desired behaviors, we advocate for strategically incorporating necessary and lightweight feature prompts to certain graph nodes to enhance downstream task performance. This introduces a combinatorial optimization problem, requiring a policy to decide 1) which nodes to prompt and 2) what specific feature prompts to attach. We then address the problem by framing the prompt incorporation process as a sequential decision-making problem and propose our method, RELIEF, which employs Reinforcement Learning (RL) to optimize it. At each step, the RL agent selects a node (discrete action) and determines the prompt content (continuous action), aiming to maximize cumulative performance gain. Extensive experiments on graph and node-level tasks with various pre-training strategies in few-shot scenarios demonstrate that our RELIEF outperforms fine-tuning and other prompt-based approaches in classification performance and data efficiency. The code is available at https://***/JasonZhujp/RELIEF.

关键词： few-shot learning

来源：评论

学校读者我要写书评

暂无评论

Out-of-Distribution Fault Diagnosis of Industrial Cyber-Physical systems Based on Orthogonal Anchor Clustering With Adaptive Balance

IEEE Transactions on Industrial Cyber-Physical Systems

引用

IEEE Transactions on Industrial Cyber-Physical systems 2025年 3卷 48-60页

作者： Liu, Ruonan Hu, Puyuan Zhao, Siheng Sun, Zhijian Han, Te Pang, Zhibo Zhang, Weidong Shanghai Jiao Tong University Department of Automation Shanghai200240 China National Key Laboratory of Marine Engine Science and Technology Shanghai201108 China Crossocean of Suzhou Technology Suzhou215121 China Beijing Institute of Technology Center for Energy and Environmental Policy Research School of Management Beijing100081 China ABB Corporate Research Sweden Department of Automation Technology Vasteras722 26 Sweden KTH Royal Institute of Technology Department of Intelligent Systems Stockholm114 28 Sweden Henan University Henan Key Laboratory of Big Data Analysis and Processing School of Computer and Information Engineering Kaifeng475001 China Shanghai Jiaotong University Department of Automation Shanghai200240 China

Given the critical role of rotating machinery in industrial cyber-physical systems (ICPS), ensuring their reliable operation is essential for the stability and safety of ICPS. Deep neural networks have demonstrated competitive results for intelligent fault diagnosis, which are usually trained via the historical data of all fault modes. However, in real engineering, it is usually difficult to collect samples and exhaust all failures during the training stage. As a result, out-of-distribution fault diagnosis (OOD-FD) becomes a more realistic problem that requires the methods to not only accurately diagnose the known faults, but also effectively recognize unknown ones. Therefore, a novel orthogonal anchor clustering with focal attention (FA-OAC) is proposed in this paper for OOD-FD. Firstly, an orthogonal anchor clustering (OAC) algorithm is proposed to fix the class center of each fault mode orthogonally and distinguish the known and unknown faults at the class level. Then, because the identifiability of different fault modes changes a lot in OOD-FD, the focal attention mechanism is applied to dynamically adjust the attention to different fault modes according to the distance loss of OAC, thus addressing the identifiability imbalance problem. To verify the effectiveness of the proposed method, different OOD-FD tasks are designed based on two rotating machinery datasets. The experimental results and comparison with state-of-the-art fault diagnosis methods have demonstrated that the proposed method has improved the OOD-FD performance greatly and therefore provides an effective tool in real engineering. © 2023 IEEE.

关键词： Rotating machinery

来源：评论

学校读者我要写书评

暂无评论

Interval quantile correlations with applications to testing high-dimensional quantile effects

引用

Journal of Econometrics 2025年 249卷

作者： Zhang, Yaowu Zhou, Yeqing Zhu, Liping Research Institute for Interdisciplinary Sciences School of Information Management and Engineering Shanghai University of Finance and Economics China School of Mathematical Sciences School of Economics and Management and Key Laboratory of Intelligent Computing and Applications Tongji University China Center for Applied Statistics and Institute of Statistics and Big Data Renmin University of China China

In this article, we propose interval quantile correlation and interval quantile partial correlation to measure the association between two random variables over an interval of quantile levels. We construct efficient estimators for the proposed correlations, and establish their asymptotic properties under the null and alternative hypotheses. We further use the interval quantile partial correlation to test for the significance of covariate effects in high-dimensional quantile regression when a subset of covariates are controlled. We calculate marginal interval quantile partial correlations for each covariate, then aggregate them to construct a sum-type test statistic. The null distribution of our proposed test statistic is asymptotically standard normal. We use extensive simulations and an application to illustrate that our proposed test, which pools information across an interval of quantile levels to enhance power performances, is very effective in detecting quantile effects. © 2024 Elsevier B.V.

关键词： Interval quantile Partial correlation Quantile regression

来源：评论

学校读者我要写书评

暂无评论

Multifactor SM9 blind signature large models data privacy preservation approach

引用

Peer-to-Peer Networking and Applications 2025年第4期18卷 1-19页

作者： Zhang, Jiazheng Li, Shouwei Chen, Minghui School of Cyber Science and Engineering Southeast University Nanjing211189 China School of Economics and Management Southeast University Nanjing211189 China Research and Development Center for System and Information Engineering Southeast University Nanjing211189 China Laboratory of Philosophy and Social Sciences at Universities in Jiangsu Province-Fintech and Big Data Laboratory of Southeast University Nanjing211189 China

In response to the need for a privacy protection method for Large models(LM) data that can accommodate partial information hiding and authentication of both data and interactor identity, paper proposes an enhanced SM9 algorithm based on blockchain technology. The proposed algorithm employs blind signature techniques to ensure the privacy of data while uniquely authenticating both the data and the identity of the interactor. The article proposes the least recently used (LRU) strategy to enhance the cuckoo filter, thereby optimizing the time efficiency of data interaction in the blockchain environment while ensuring secure and effective data privacy protection, signature verification and authentication, and public depository. The theory validates the accuracy and security of the proposed multifactor SM9 blind signature scheme and authentication method. The experimental results demonstrate that paper's method outperforms existing cryptographic schemes in terms of signing, signature checking, and authentication efficiency while optimizing the time consumption of the SM2/Schnorr scheme in the blind signature checking phase of the larger experimental data test volume was found to be 4.7/5.9 times faster, respectively, memory consumption reduced by an average of 26.91%, and demonstrates a 47.3% data interaction reduction and 16.56% throughput enhancement in blockchain's improved Cuckoo consensus, with 14.3% communication reduction and 10.38% latency optimization, indicating excellent performance and a lower growth rate of time consumption. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

FedPHE: A Secure and Efficient Federated Learning via Packed Homomorphic Encryption

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Li, Yuqing Yan, Nan Chen, Jing Wang, Xiong Hong, Jianan He, Kun Wang, Wei Li, Bo Wuhan University Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan430072 China Wuhan University RiZhao Information Technology Institute Rizhao276800 China Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Wuhan430074 China Shanghai Jiao Tong University School of Cyber Science and Engineering Shanghai200240 China Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong

Cross-silo federated learning (FL) enables multiple institutions (clients) to collaboratively build a global model without sharing private data. To prevent privacy leakage during aggregation, homomorphic encryption (HE) is widely used to encrypt model updates, yet incurs high computation and communication overheads. To reduce these overheads, packed HE (PHE) has been proposed to encrypt multiple plaintexts into a single ciphertext. However, the original design of PHE assumes all clients share a single private key, making the system vulnerable to security threats of ciphertexts being intercepted and decrypted by honest-but-curious clients. Also, it does not consider the heterogeneity among different clients, resulting in undermined training efficiency with slow convergence and stragglers. To address these challenges, we propose FedPHE, a secure and efficient FL framework with PHE by jointly exploiting contribution-aware secure aggregation and straggler-resistant client selection. Using CKKS with sparsification and blinding, FedPHE achieves efficient secure aggregation that allows clients to only provide obscured encrypted updates while the server can perform aggregation by accounting for contributions of local updates. To mitigate the straggler effect, we devise a perturbed sketch-based selection to cherry-pick representative clients with heterogeneous models and computing capabilities in a communication-efficient and privacy-preserving manner. We show, through rigorous security analysis and extensive experiments, that FedPHE can efficiently safeguard clients' privacy, achieve 2.45-6.56× training speedup, cut the communication overhead by 1.32-24.85×, and reduce straggler effects by 1.89-2.78×. © 2004-2012 IEEE.

关键词： Privacy by design

来源：评论

学校读者我要写书评

暂无评论

A hybrid surrogate-assisted dual-population co-evolutionary algorithm for multi-area integrated scheduling in wafer fabs

引用

Swarm and Evolutionary Computation 2025年 96卷

作者： Mengyu Jin Peng Zhang Youlong Lv Ming Wang Wenbing Xiang Hongsen Li Jie Zhang Engineering Research Center of Artificial Intelligence for Textile Industry Ministry of Education Institute of Artificial Intelligence Donghua University Shanghai China Shanghai Engineering Research Center of Industrial Big Data and Intelligent System Institute of Artificial Intelligence Donghua University Shanghai China College of Mechanical Engineering Donghua University Shanghai China

In wafer fabrication, multiple areas handle different processes and production flows. To maintain the desired chemical and physical properties of wafers, strict time window constraints (TWCs) must be observed as wafers progress through these areas. However, independent scheduling within each area without collaboration complicates resource allocation and hinders overall production optimization. Implementing multi-area integrated scheduling is thus essential for effective production management, aiming to reduce total lead time and production costs. This paper proposes a hybrid surrogate-assisted dual-population co-evolutionary algorithm (HSA-DPEA) to efficiently tackle the multi-area integrated scheduling problem under multiple TWCs. The algorithm employs a dual-population co-evolutionary mechanism, consisting of normal and auxiliary populations, to balance convergence and diversity while ensuring feasibility. The normal population focuses on feasible solutions to maintain overall quality, while the auxiliary population explores infeasible regions to identify promising individuals that can guide the normal population's evolution. To enhance evolutionary efficiency and reduce the number of time-consuming real fitness evaluations, a hybrid surrogate-assisted model is introduced. This model adapts by training regression or classification models at different stages of population evolution. Additionally, an online learning strategy based on convergence and diversity is employed for continuous model updating to improve accuracy. The proposed algorithm is tested on 18 instances and validated through six months of continuous testing on a wafer fab simulation system. The results demonstrate that HSA-DPEA obtains better Pareto optimal sets, effectively reducing total lead time and production costs in multi-area integrated scheduling under multiple TWCs.

关键词：

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：