检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Zhuochun Miao Xingrui Zhuo Gongqing Wu Chenyang Bu Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) School of Computer Science and Information Engineering Hefei University of Technology Anhui China

Event detection (ED) is a key subtask of information extraction to extract key events, such as stock rise and fall and social public opinion, from news or social media. Although current GCN-based event detection methods achieve remarkable success via building graphs with dependency trees, they typically suffer from two challenges: 1) They use sequence models to learn contextual information of sentences, ignoring the longterm dependencies problem of sequence models might learn ineffective information and make it propagate in GCN layers. 2) Most methods do not exploit global dependency label information and grammatical structure information that convey rich linguistic knowledge directly, and only consider local dependency label information. To cope with these challenges, we propose a novel event detection model via semantic-reconstructed graph transformer networks (SRGTNED), which incorporates semantic reconstruction and path information collection methods. Using the semantic reconstruction method, we assign a pruned sequence to each word based on the path information to capture contextual information consistent with sentence semantics. Moreover, to better utilize global dependency label information and grammatical structure information, a Graph Transformer Network (GTN)-based heterogeneous graph embedding framework is introduced to automatically learn path information between important words by converting sentences as heterogeneous graphs. We conduct experiments on the ACE2005 dataset and the Commodity News dataset, and the experimental results demonstrate that our method significantly outperforms 11 state-of-the-art baselines in terms of the F1-score.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Performance to Detecting Topic Shift of Large Language Models: A Study 9

Evaluating the Performance to Detecting Topic Shift of Large...

引用

9th International Conference on Intelligent Computing and Signal Processing, ICSP 2024

作者： Tian, Pingfang Liu, Deting Department of Computer Science and Technology Wuhan University of Science and Technology Wuhan430065 China Institute of Scientific and Technical Information of China The Key Laboratory of the Rich Media Knowledge Organisation and Service of Digital Publishing Content Beijing100038 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China Big Data Science and Engineering Research Institute Wuhan University of Science and Technology Wuhan430065 China

ISBN: (纸本)9798350376548

Topic shift detection aims to identify whether there is a change in the current topic of conversation or if a change is needed. The study found previous work did not evaluate the performance of large language models like ChatGPT on the task of topic shift. Therefore, this paper's main task and innovation lie in analyzing ChatGPT's performance on topic shift detection. To provide a more comprehensive evaluation, we conducted topic shift detection tasks on ChatGPT from three aspects: single utterances, adjacent utterances, and contextual levels. Additionally, to gauge the performance of large language models, we conducted experiments on multiple small-scale models and compared the results of the two models. Experimental results on the publicly available English TIAGE dataset showed that small-scale models exhibited lower recall in all three aspects, while ChatGPT performed better in the recall. This suggests that compared to small-scale models, large models are more capable of accurately detecting topic shifts. However, large models also exhibited lower precision, indicating that while ChatGPT can recognize content differences in utterances, its judgment on whether these different contents belong to the same topic is poor. © 2024 IEEE.

关键词： adjacent utterances level ChatGPT contextual level single utterances level topic shift detection

来源：评论

学校读者我要写书评

暂无评论

Multivariate Time Series Classification via Hierarchical Graph Embedding

Multivariate Time Series Classification via Hierarchical Gra...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Wenhao Niu Xingrui Zhuo Gongqing Wu JunWei Lv Zan Zhang Chenyang Bu Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) School of Computer Science and Information Engineering Hefei University of Technology Anhui China

Multivariate time series classification aims to determine the labels for multivariate time series samples. Although variable interaction relationships and sample similarity relationships exist in multivariate time series, the available related methods usually ignore the rich relationships and are ineffective in exploiting these. To solve this problem, we propose a Hierarchical Graph Embedding for Multivariate Time Series Classification (MTSC-HGE), which consists of a variable-wise attentive graph pooling module and a sample-wise graph convolutional module to obtain the relationships of variables and samples. Specifically, we design an attentive graph pooling module based on self-attention, which can obtain sample features fusing temporal patterns and variable interaction relationships in samples. Furthermore, we propose a graph mapping criterion that converts the MTS dataset into a graph based on dynamic time warping to explicitly reflect the similarity relationships between samples. To capture latent sample relationships, a GCN module is utilized on the sample graph to integrate sample features obtained from the attentive graph pool module. In addition, a classifier takes the rich representation output by the model to get the final predicted class. Extensive experiments on 14 public datasets show that MTSC-HGE significantly outperforms state-of-the-art baselines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Production quality early warning method for firearms components based on cloud edge collaboration 4

Production quality early warning method for firearms compone...

引用

4th International Conference on Machine Learning and Computer Application, ICMLCA 2023

作者： Sun, Jiawei Hao, Jia Zhang, Xiaoning School of Mechanical Engineering Beijing Institute of Technology Beijing10081 China Yangtze Delta Region Academy of Beijing Institute of Technology Jiaxing314019 China Key Laboratory of Industry Knowledge and Data Fusion Technology and Application Ministry of Industry and Information Technology Beijing Institute of Technology Beijing10008 China Tianjin Key Laboratory of Space Environment Simulation Technology Tianjing300450 China

ISBN: (纸本)9798400709449

Digital transformation in manufacturing has become a trend with the continuous development of cloud computing and edge computing. The production process of firearms components is highly challenging and quality problems in the production process may directly affect the safety of people's lives and property. Thus, this paper proposes a production-quality early warning method for firearms components based on cloud-edge collaboration. Real-time early warning and rapid processing for abnormal conditions in the production process are realized based on cloud data analysis and edge intelligent prediction, thereby improving production efficiency and quality. The cloud edge collaboration framework is developed for cloud training of the long short-term memory models and real-time sample edge acquisition, enhancing the adaptability of quality early warning algorithms under specific conditions and the real-time quality of early warning for firearms components. © 2023 ACM.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

An MRC Framework for Semantic Role Labeling 29

An MRC Framework for Semantic Role Labeling

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Wang, Nan Li, Jiwei Meng, Yuxian Sun, Xiaofei Qiu, Han Wang, Ziyao Wang, Guoyin He, Jun Key Laboratory of Data Engineering and Knowledge Engineering of MOE School of Information Renmin University of China China Shannon.AI Zhejiang University China Tsinghua University China University of Leeds United Kingdom Amazon Alexa AI

Semantic Role Labeling (SRL) aims at recognizing the predicate-argument structure of a sentence and can be decomposed into two sub-tasks: predicate disambiguation and argument labeling. Prior work deals with these two tasks independently, which ignores the semantic connection between the two tasks. In this paper, we propose to use the machine reading comprehension (MRC) framework to bridge this gap. We formalize predicate disambiguation as multiple-choice machine reading comprehension, where the descriptions of candidate senses of a given predicate are used as options to select the correct sense. The chosen predicate sense is then used to determine the semantic roles for that predicate, and these semantic roles are used to construct the query for another MRC model for argument labeling. In this way, we are able to leverage both the predicate semantics and the semantic role semantics for argument labeling. We also propose to select a subset of all the possible semantic roles for computational efficiency. Experiments show that the proposed framework achieves state-of-the-art or comparable results to previous work. Code is available at https://***/ShannonAI/MRC-SRL. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Research on access control decision model of Internet of Things based on attribute exploration

Research on access control decision model of Internet of Thi...

引用

2021 International Conference on Signal Processing and Communication Technology, SPCT 2021

作者： Shen, XiaJiong Zhang, Peng Zhang, YanFeng Henan Key Laboratory of Big Data Analysis and Processing Henan Univ. HA Kaifeng475004 China School of Computer and Information Engineering Henan Univ. HA Kaifeng475004 China Institute of Data and Knowledge Engineering Henan Univ. HA Kaifeng475004 China

ISBN: (数字)9781510653344

ISBN: (纸本)9781510653337

With the rapid development of the Internet of things, the problem of access control has become increasingly prominent. In order to solve the problems of high redundancy and low integrity caused by the traditional Role-Based Access Control model, this paper proposes an access control model of Internet of things based on attribute exploration. Firstly, the decision model is established based on attribute exploration algorithm, and finally merged into a complete decision model. The model has the function of dynamically modifying access rights in the process of building decision model. It is a new exploration in the field of access control model. © 2022 SPIE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

LoRS: Efficient Low-Rank Adaptation for Sparse Large Language Model

arXiv

引用

arXiv 2025年

作者： Hu, Yuxuan Zhang, Jing Chen, Xiaodong Zhao, Zhe Li, Cuiping Chen, Hong School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering Beijing China Engineering Research Center of Database and Business Intelligence Beijing China Tencent AI Lab Beijing China

Existing low-rank adaptation (LoRA) methods face challenges on sparse large language models (LLMs) due to the inability to maintain sparsity. Recent works introduced methods that maintain sparsity by augmenting LoRA techniques with additional masking mechanisms. Despite these successes, such approaches suffer from an increased memory and computation overhead, which affects efficiency of LoRA methods. In response to this limitation, we introduce LoRS, an innovative method designed to achieve both memory and computation efficiency when fine-tuning sparse LLMs. To mitigate the substantial memory and computation demands associated with preserving sparsity, our approach incorporates strategies of weight recompute and computational graph rearrangement. In addition, we also improve the effectiveness of LoRS through better adapter initialization. These innovations lead to a notable reduction in memory and computation consumption during the fine-tuning phase, all while achieving performance levels that outperform existing LoRA approaches. © 2025, CC BY.

关键词： Problem oriented languages

来源：评论

学校读者我要写书评

暂无评论

Meta-path Enhanced knowledge Graph Convolutional Network for Recommender Systems 12

Meta-path Enhanced Knowledge Graph Convolutional Network for...

引用

12th IEEE International Conference on Big knowledge, ICBK 2021

作者： Wang, Ru Wu, Meng Ji, Shengwei Hefei University of Technology Key Laboratory of Knowledge Engineering With Big Data Ministry of Education School of Computer Science and Information Engineering Hefei China

ISBN: (纸本)9781665438582

knowledge Graph (KG) is a directed heterogeneous information network that contains a large number of entities and relations, which is widely used as effective side information in rec-ommender systems. Moreover, in recommender systems, the Graph Convolutional Network (GCN) model is introduced to mine the relatedness between entities in a KG because of its efficiency in extracting spatial features on topological graphs. The knowledge Graph Convolutional Network (KGCN) model up-dates the embedding of a currently positioned entity by aggregating the information of adjacent entities selected randomly. Never-theless, it has two limititations: 1) the information of neighbors se-lected randomly cannot accurately represent the current entity in the KG;2) the model is hard to converge as graph features (i.e. The spatial relation features and semantic information features of en-tities in the KG) grow. To solve these limitations, in this paper, a meta-path (i.e., a sequence of artificially constructed relationships) is introduced into the selection of neighbors in the KGCN model to enhance the representation of each entity. Furthermore, two construction methods of the meta-path - constructing a meta-path based on the same relation (KGCN-SP) and the characteris-tics of KG (KGCN-MP) -are proposed. The experiments based on three real-world datasets demonstrate that the neighbor selection based on the meta-path is able to collect more accurate infor-mation from a KG and improve the recommendation performance effectively. © 2021 IEEE.

关键词： knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Assisted Diagnostic Learning Based on Concept Lattice

Assisted Diagnostic Learning Based on Concept Lattice

引用

2021 International Conference on Signal Processing and Communication Technology, SPCT 2021

作者： Shen, Xiajiong Li, Xingchen Han, Daojun Zhang, Yanfeng Henan Key Laboratory of Big Data Analysis and Processing Henan Univ. HA Kaifeng475004 China School of Computer and Information Engineering Henan Univ. HA Kaifeng475004 China Institute of Data and Knowledge Engineering Henan Univ. HA Kaifeng475004 China

ISBN: (数字)9781510653344

ISBN: (纸本)9781510653337

With the continuous development of education, online education is becoming more and more popular with learners because of its convenience. However, online education has the problem of insufficient interaction with students. Students still need to rely on the students themselves to judge the lack of knowledge in practice tasks, which will greatly affect the learning efficiency. In this paper, we propose a method based on formal concept analysis to analyze the knowledge that may not be mastered, and a method of intensive practice for students. First of all, establishing the formal context of student error test questions, construct the concept lattice to calculate the degree of importance of the knowledge concept that may not be mastered, judge the student's mastery of the knowledge concept, and give feedback. Secondly, construct the concept lattice of the unpractised test set, and calculate the similarity of the concept extension set that meets the threshold, find similar topics and push them, and realize targeted training for students who have not mastered the knowledge concepts. © 2022 SPIE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Identifying Scientific and Technical“Unicorns”

引用

Journal of data and Information Science 2021年第2期6卷 96-115页

作者： Lucy L.Xu Miao Qi Fred Y.Ye Jiangsu Key Laboratory of Data Engineering and Knowledge Service School of Information ManagementNanjing UniversityNanjing 210023China University Library Nantong UniversityNantong 226019China

Purpose:Using the metaphor of"unicorn,"we identify the scientific papers and technical patents characterized by the informetric feature of very high citations in the first ten years after publishing,which may provide a new pattern to understand very high impact works in science and ***/methodology/approach:When we set CT as the total citations of papers or patents in the first ten years after publication,with CT≥5,000 for scientific"unicorn"and CT≥500 for technical"unicorn,"we have an absolute standard for identifying scientific and technical"unicorn"***:We identify 165 scientific"unicorns"in 14,301,875 WoS papers and 224 technical"unicorns"in 13,728,950 DII patents during 2001–*** 50%of"unicorns"belong to biomedicine,in which selected cases are individually *** rare"unicorns"increase following linear model,the fitting data show 95%confidence with the RMSE of scientific"unicorn"is 0.2127 while the RMSE of technical"unicorn"is *** limitations:A"unicorn"is a pure quantitative consideration without concerning its quality,and"potential unicorns"as CT≤5,000 for papers and CT≤500 for patents are left in future *** implications:Scientific and technical"unicorns"provide a new pattern to understand high-impact works in science and ***"unicorn"pattern supplies a concise approach to identify very high-impact scientific papers and technical ***/value:The"unicorn"pattern supplies a concise approach to identify very high impact scientific papers and technical patents.

关键词： Unicorn Scientific paper Technical patent Citation analysis Patent analysis

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：