检索结果-内蒙古大学图书馆

31st International Conference on computational Linguistics, COLING 2025

作者： Wang, Tianshu Chen, Xiaoyang Lin, Hongyu Chen, Xuanang Han, Xianpei Wang, Hao Zeng, Zhenyu Sun, Le Chinese Information Processing Laboratory Institute of Software Chinese Academy of Sciences China Hangzhou Institute for Advanced Study University of Chinese Academy of Sciences China University of Chinese Academy of Sciences China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China Alibaba Cloud Intelligence Group China

ISBN: (纸本)9798891761964

Entity matching (EM) is a critical step in entity resolution (ER). Recently, entity matching based on large language models (LLMs) has shown great promise. However, current LLM-based entity matching approaches typically follow a binary matching paradigm that ignores the global consistency among record relationships. In this paper, we investigate various methodologies for LLM-based entity matching that incorporate record interactions from different perspectives. Specifically, we comprehensively compare three representative strategies: matching, comparing, and selecting, and analyze their respective advantages and challenges in diverse scenarios. Based on our findings, we further design a compound entity matching framework (COMEM) that leverages the composition of multiple strategies and LLMs. COMEM benefits from the advantages of different sides and achieves improvements in both effectiveness and efficiency. Experimental results on 8 ER datasets and 10 LLMs verify the superiority of incorporating record interactions through the selecting strategy, as well as the further cost-effectiveness brought by COMEM. © 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

Study on the Rainfall-flood Association Pattern Database Based on Image Features 7

Study on the Rainfall-flood Association Pattern Database Bas...

引用

7th IEEE International Conference on Big Data and Artificial Intelligence, BDAI 2024

作者： Yu, Yufeng Cai, Difei Wu, Panqi Liu, Weifu Wang, Xuhang Hohai University College of Computer Science and Software Engineering Nanjing China

ISBN: (纸本)9798350352009

Precipitation images can clearly reflect the rainfall spatio-temporal features and play an important role in hydrological analysis and flood forecasting. However, it is challenging to mine the association response relationship between rainfall and flood events. This paper proposed a rainfall-flood association pattern database construction method based on rainfall image features. First, the rainfall pattern database and flood pattern database are constructed respectively through the steps of hydrological process segmentation, feature extraction, similarity measurement and cluster analysis. Additionally, association rule mining algorithm is used to conduct rainfall-flood association pattern mining and consrtuct the rainfall-flood association pattern database. The experimental results in the Jialing River basin show that the method proposed in this paper can effectively mine the rainfall-flood association pattern database and provide technical support for intelligent flood prediction based on historical scene patterns. © 2024 IEEE.

关键词： Rain

来源：评论

学校读者我要写书评

暂无评论

SFTCS: Multiform Semantic Fusion Based on Transformer for Code Summarization 14

SFTCS: Multiform Semantic Fusion Based on Transformer for Co...

引用

14th International Conference on software Technology and Engineering, ICSTE 2024

作者： Yang, Jun Ao, Longhao Qi, Rongzhi College of Computer Science and Software Engineering Hohai University Nanjing China

ISBN: (纸本)9798350378955

Automatic code summarization aims to create co-herent natural language descriptions for code snippets. Recent studies indicate that integrating additional code representation structures improve the quality of generated summaries beyond token sequence-based approaches. Current technical research mainly concentrates on the graph structure information of code snippets. However, using a graph method makes it challenging to extract meaningful semantic information from the code snippets. To address the issue, we investigate how to learn more about code semantics and information from the perspective of code text feature representation. Consequently, we propose a novel model named SFTCS. SFTCS employs a conjoint feature fusion strategy, focusing on two types of information in code snippets: code token sequence features and FGT features based on Abstract Syntax Trees (AST) sequence and graph sequence. An N-adjacency ma-trix based on AST features is constructed, and the corresponding feature for AST block are optimized through a graph-based structure. Subsequently, a FGC decoder processes the two types of features. With the aid of an attention mechanism for feature enhancement, the SFTCS model ultimately predicts the results concretely. Evaluations on two publicly available Java datasets validate the effectiveness of SFTCS, showing its superiority over six advanced code summarization models. Ablation studies further elucidate the contributions of each component within the SFTCS model. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Ultrasensitive electrospinning fibrous strain sensor with synergistic conductive network for human motion monitoring and human-computer interaction

引用

材料科学技术（英文版） 2025年第10期213卷 213-222页

作者： Jingwen Wang Shun Liu Zhaoyang Chen Taoyu Shen Yalong Wang Rui Yin Hu Liu Chuntai Liu Changyu Shen State Key Laboratory of Structural Analysis Optimization and CAE Software for Industrial EquipmentNational Engineering Research Center for Advanced Polymer Processing TechnologyZhengzhou UniversityZhengzhou 450002China State Key Laboratory of Structural Analysis Optimization and CAE Software for Industrial EquipmentNational Engineering Research Center for Advanced Polymer Processing TechnologyZhengzhou UniversityZhengzhou 450002China China Astronaut Research and Training Center Beijing 100094China

With the rapid development of wearable electronic skin technology,flexible strain sensors have shown great application prospects in the fields of human motion and physiological signal detection,medical diagnostics,and human-computer interaction owing to their outstanding sensing *** pa-per reports a strain sensor with synergistic conductive network,consisting of stable carbon nanotube dispersion(CNT)layer and brittle MXene layer by dip-coating and electrostatic self-assembly method,and breathable three-dimensional(3D)flexible substrate of thermoplastic polyurethane(TPU)fibrous membrane prepared through electrospinning *** MXene/CNT@PDA-TPU(MC@p-TPU)flexible strain sensor had excellent air permeability,wide operating range(0-450％),high sensitivity(Gauge Fac-tor,GF max=8089.7),ultra-low detection limit(0.05％),rapid response and recovery times(40 ms/60 ms),and excellent cycle stability and durability(10,000 cycles).Given its superior strain sensing capabilities,this sensor can be applied in physiological signals detection,human motion pattern recognition,and driv-ing exoskeleton *** addition,MC@p-TPU fibrous membrane also exhibited excellent photothermal conversion performance and can be used as a wearable photo-heater,which has far-reaching application potential in the photothermal therapy of human joint diseases.

关键词： Flexible strain sensors Synergistic conductive network Electrospinning fibrous membrane Motion monitoring Human-machine interface

来源：评论

学校读者我要写书评

暂无评论

A topical VAEGAN-IHMM approach for automatic story segmentation

引用

Mathematical Biosciences and Engineering 2024年第7期21卷 6608-6630页

作者： Yu, Jia Peng, Huiling Wang, Guoqiang Shi, Nianfeng School of Computer and Information Engineering Luoyang Institute of Science and Technology China Software Research Institute Technological University of Shannon Ireland

Feature representations with rich topic information can greatly improve the performance of story segmentation tasks. VAEGAN offers distinct advantages in feature learning by combining variational autoencoder (VAE) and generative adversarial network (GAN), which not only captures intricate data representations through VAE's probabilistic encoding and decoding mechanism but also enhances feature diversity and quality via GAN's adversarial training. To better learn topical domain representation, we used a topical classifier to supervise the training process of VAEGAN. Based on the learned feature, a segmentor splits the document into shorter ones with different topics. Hidden Markov model (HMM) is a popular approach for story segmentation, in which stories are viewed as instances of topics (hidden states). The number of states has to be set manually but it is often unknown in real scenarios. To solve this problem, we proposed an infinite HMM (IHMM) approach which utilized an HDP prior on transition matrices over countably infinite state spaces to automatically infer the state's number from the data. Given a running text, a Blocked Gibbis sampler labeled the states with topic classes. The position where the topic changes was a story boundary. Experimental results on the TDT2 corpus demonstrated that the proposed topical VAEGAN-IHMM approach was significantly better than the traditional HMM method in story segmentation tasks and achieved state-of-the-art performance. © 2024 the Author(s).

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Self-stabilizing (Δ+ 1 ) -Coloring in Sublinear (in Δ ) Rounds via Locally-Iterative Algorithms 29th

Self-stabilizing (Δ+ 1 ) -Coloring in Sublinear (in Δ ) R...

引用

29th International Computing and Combinatorics Conference, COCOON 2023

作者： Fu, Xinyu Yin, Yitong Zheng, Chaodong State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

ISBN: (纸本)9783031491894

Fault-tolerance is a central theme in distributed computing. Self-stabilization is a key property that guarantees a distributed system starting from an arbitrary state eventually converges to a desired behavior. Such strong level of fault-tolerance is often desirable due to the error-prone nature of distributed systems. Developing fast and robust coloring algorithms has been a central topic in the study of distributed graph algorithms. In this paper, we give a (Δ+ 1 ) -coloring algorithm with O(Δ3 / 4log Δ) + log ∗n stabilization time, only using messages of size O(log n), on input graphs of n vertices and maximum degree Δ. This is the first self-stabilizing (Δ+ 1 ) -coloring algorithm with sublinear-in- Δ stabilization time. The key building block of our algorithm is a new locally-iterative (Δ+ 1 ) -coloring algorithm with O(Δ3 / 4log Δ) + log ∗n runtime. To the best of our knowledge, this is the first locally-iterative (Δ+ 1 ) -coloring algorithm with sublinear-in- Δ runtime. This answers an open question raised in [Barenboim, Elkin, and Goldberg, JACM ’21]. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Medicine and Disease Association Prediction via Attention-Based Medical Heterogeneous Information Network Representation Learning

IAENG International Journal of Computer Science

引用

IAENG International Journal of Computer science 2022年第1期49卷 69-78页

作者： Zhang, Bin Yang, Dan Lin, Zhihuang Master of Computer Science and Software Engineering Department University of Science and Technology Liao Ning Anshan China School of Computer Science and Software Engineering University of Science and Technology Liao Ning Anshan China

Knowledge of medication and disease has been rapidly accumulated. Also, an increasing number of researchers have paid more attention to predicting medicine-disease associations by machine learning methods. The associations of entities in the medical heterogeneous information network involve different association types. In this paper, we propose MHIN-MD, a representation learning of medical heterogeneous network model to solve the association between medicines and diseases in medical heterogeneous information network. Specifically, we first construct a medical heterogeneous information network contains diseases, medicines, diagnosis, etc. Next, we design a neural network model to learn the feature vector representation of medical nodes information. We try to find the association between medicines and diseases through the characteristics of medicines structure and the interaction between medicines. Using the Euclidean distance to calculate medicine similarity and disease similarity, generates a set of similar nodes between medicines and diseases to prediction association between medicines and diseases. Finally, our extensive experiments on MIMIC- III datasets and DrugBank datasets, the result demonstrates that MHIN-MD can outperform baselines in the association prediction. © 2022. All Rights Reserved.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Self-healing automation testing with Selenium and ChatGPT API integration to improve the efficiency of the maintenance 2

Self-healing automation testing with Selenium and ChatGPT AP...

引用

2nd International Conference on Foundation and Large Language Models, FLLM 2024

作者： Kim, Yunjin Kouatly, Rand University of Europe for Applied Science Department of Tech & Software Potsdam Germany

ISBN: (纸本)9798350354799

The rapid delivery in software development life cycle demands more adaptable automation testing frameworks. The current automation test frameworks struggle with maintaining the scripts due to frequent changes in web elements. To resolve this issue, this paper introduces a self-healing automation testing framework that updates broken locators without human intervention. ChatGPT API is integrated within the newly developed automation framework to reduce time and effort for maintenance. The results show the potential of the self-healing automation testing framework with ChatGPT API integration compared to traditional automation tests. © 2024 IEEE.

关键词： Life cycle

来源：评论

学校读者我要写书评

暂无评论

Improve Graph Convolutional Network Performance via Incorporating Message Filter 15

Improve Graph Convolutional Network Performance via Incorpor...

引用

15th IEEE International Conference on Knowledge Graph, ICKG 2024

作者： Qiu, Dehong Cai, Kangle Lei, Shiyu Wu, Xiang Huazhong University of Science and Technology School of Software Engineering Wuhan China

ISBN: (纸本)9798331508821

Graph Convolutional Network (GCN) has shown great potential in graph learning. However, since the message-passing mechanism treats all messages equally and updates representation of each node by transforming messages received from its neighbors and itself linearly, GCN lacks the capability to distinguish between good and bad messages for the task at hand and suffers from drawbacks such as over-smoothing. To overcome the limitation, we propose to incorporate message filter into GCN to improve message propagation and finally to enhance GCN performance. This is a flexible method, because for different tasks, different message filters can be designed from various viewpoints to achieve corresponding goals. Moreover, a message filter can be realized as a plug-and-play module and incorporated into GCN conveniently, without introducing new model parameters. We design a message filter for the task of node classification, which improves message aggregation of each node via strengthening the messages from the nodes with the same label and filtering out the messages from the nodes with different label. We theoretically prove the effectiveness of the message filter and evaluate the learned node representations quantitatively. Extensive experimental results demonstrate that incorporating the message filter into GCN makes a significant accuracy improvement in node classification. © 2024 IEEE.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

Leveraging Computer Vision for Automatic Modulation Classification: Insights from Spectrum and Constellation Diagram Analysis 27th

Leveraging Computer Vision for Automatic Modulation Classifi...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Zhao, Wenjie Luo, Qiuming College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China

ISBN: (纸本)9783031783821

Automated modulation recognition is a challenging task in communication systems. Leveraging recent advancements in transfer learning, this paper proposes a novel method for automatic modulation recognition using transferred computer vision models. The method allows fine-tuning of the vision models to recognize modulation signals through spectrum and constellation diagrams. Experiments on the Radioml dataset demonstrate that the proposed method outperforms recent traditional methods by 8.97%, with an average accuracy of 0.5732. An ablation study confirms the effectiveness of using spectrum and constellation diagrams. This study verifies the feasibility of transferring vision models to AMC tasks. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Signal modulation

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：