检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

4,243 篇 会议
103 册 图书
50 篇 期刊文献

馆藏范围

4,396 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,558 篇 工学
- 2,413 篇 计算机科学与技术...
- 1,799 篇 软件工程
- 347 篇 信息与通信工程
- 274 篇 控制科学与工程
- 257 篇 电气工程
- 173 篇 生物工程
- 93 篇 化学工程与技术
- 78 篇 生物医学工程（可授...
- 72 篇 机械工程
- 66 篇 网络空间安全
- 59 篇 电子科学与技术（可...
- 49 篇 仪器科学与技术
- 36 篇 光学工程
- 31 篇 材料科学与工程（可...
- 30 篇 动力工程及工程热...
- 29 篇 安全科学与工程
792 篇 管理学
- 543 篇 图书情报与档案管...
- 300 篇 管理科学与工程(可...
- 104 篇 工商管理
675 篇 理学
- 302 篇 数学
- 178 篇 生物学
- 156 篇 物理学
- 118 篇 统计学（可授理学、...
- 100 篇 化学
- 68 篇 系统科学
91 篇 医学
- 72 篇 临床医学
- 64 篇 基础医学(可授医学...
- 48 篇 公共卫生与预防医...
75 篇 法学
- 68 篇 社会学
74 篇 教育学
- 73 篇 教育学
35 篇 文学
28 篇 农学
25 篇 经济学
4 篇 艺术学
2 篇 军事学

主题

1,052 篇 natural language...
318 篇 semantics
314 篇 natural language...
299 篇 natural language...
231 篇 knowledge engine...
226 篇 data mining
210 篇 machine learning
168 篇 information retr...
150 篇 training
148 篇 artificial intel...
144 篇 deep learning
140 篇 accuracy
133 篇 computational mo...
120 篇 knowledge based ...
119 篇 sentiment analys...
118 篇 ontologies
111 篇 computer science
110 篇 databases
109 篇 feature extracti...
108 篇 knowledge graph

机构

27 篇 faculty of engin...
26 篇 maharishi school...
22 篇 school of inform...
15 篇 centre of interd...
14 篇 lovely professio...
14 篇 institute of inf...
13 篇 school of comput...
13 篇 department of co...
13 篇 school of cyber ...
12 篇 beijing universi...
12 篇 school of comput...
11 篇 school of comput...
10 篇 national laborat...
10 篇 knowledge engine...
10 篇 institute of com...
9 篇 school of comput...
9 篇 beijing univ pos...
9 篇 university of ch...
9 篇 school of electr...
9 篇 moe-ms key labor...

作者

67 篇 fuji ren
37 篇 ren fuji
16 篇 bo xu
14 篇 shingo kuroiwa
14 篇 yixin zhong
14 篇 xiaojie wang
11 篇 tiejun zhao
10 篇 dongfeng cai
10 篇 lei li
10 篇 f. ren
10 篇 jingbo zhu
9 篇 s. kuroiwa
8 篇 wenju liu
8 篇 tianrui li
8 篇 zhu jingbo
8 篇 degen huang
7 篇 tanioka tetsuya
7 篇 tingting he
7 篇 guiping zhang
7 篇 vogelsang andrea...

语言

4,216 篇 英文
162 篇 其他
25 篇 中文

检索条件"任意字段=2003 International Conference on Natural Language Processing and Knowledge Engineering"

共 4396 条记录，以下是761-770 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Personalized Academic Communication Recommendation System Based on knowledge Graph

Personalized Academic Communication Recommendation System Ba...

引用

Electronic Communication and Artificial Intelligence (IWECAI), international Workshop on

作者： Jiajia Liu Meilin Luan Ning Jiang School of Information Engineering Wuhan University of Technology Wuhan China International Office Wuhan University of Technology Wuhan China

ISBN: (数字)9798350386943

ISBN: (纸本)9798350386950

Scholar retrieval resources are faced with the problems of information overload, low efficiency, and low matching degree. To address this issue, we developed a personalized academic resource recommendation system based on the knowledge graph. The system consists of a data layer, a policy layer, and an application layer, which include four main functional modules: resource storage module, knowledge description module, wisdom recommendation module, and user management module. The back-end of the system utilizes the Spring Boot, Spring MVC, and MyBatis frameworks, while the front-end communicates with the back end via HTTP requests. The system database primarily utilizes MySQL and Neo4j. The system integrates knowledge graph and natural language processing technology to recommend high-quality academic resources for scholars.

关键词： Databases Collaborative filtering knowledge graphs natural language processing HTTP Springs Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Focus, Distinguish, and Prompt: Unleashing CLIP for Efficient and Flexible Scene Text Retrieval 24

Focus, Distinguish, and Prompt: Unleashing CLIP for Efficien...

引用

32nd ACM international conference on Multimedia, MM 2024

作者： Zeng, Gangyan Zhang, Yuan Wei, Jin Yang, Dongbao Zhang, Peng Gao, Yiwen Qin, Xugong Zhou, Yu School of Cyber Science and Engineering Nanjing University of Science and Technology Nanjing China State Key Laboratory of Media Convergence and Communication Communication University of China Beijing China Lenovo Research Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China Laboratory for Advanced Computing and Intelligence Engineering Wuxi China TMCC College of Computer Science Nankai University Tianjin China

ISBN: (纸本)9798400706868

Scene text retrieval aims to find all images containing the query text from an image gallery. Current efforts tend to adopt an Optical Character Recognition (OCR) pipeline, which requires complicated text detection and/or recognition processes, resulting in inefficient and inflexible retrieval. Different from them, in this work we propose to explore the intrinsic potential of Contrastive language-Image Pre-training (CLIP) for OCR-free scene text retrieval. Through empirical analysis, we observe that the main challenges of CLIP as a text retriever are: 1) limited text perceptual scale, and 2) entangled visual-semantic concepts. To this end, a novel model termed FDP (Focus, Distinguish, and Prompt) is developed. FDP first focuses on scene text via shifting the attention to the text area and probing the hidden text knowledge, and then divides the query text into content word and function word for processing, in which a semantic-aware prompting scheme and a distracted queries assistance module are utilized. Extensive experiments show that FDP significantly enhances the inference speed while achieving better or competitive retrieval accuracy compared to existing methods. Notably, on the IIIT-STR benchmark, FDP surpasses the state-of-the-art model by 4.37% with a 4 times faster speed. Furthermore, additional experiments under phrase-level and attribute-aware scene text retrieval settings validate FDP's particular advantages in handling diverse forms of query text. The source code will be available at https://***/Gyann-z/FDP. © 2024 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

DRHTG: A knowledge-Centric Approach for Document Retrieval Based on Heterogeneous Entity Tree Generation and RDF Mapping 13th

DRHTG: A Knowledge-Centric Approach for Document Retrieval B...

引用

13th international conference on Innovations in Bio-Inspired Computing and Applications, IBICA 2022, and 12th World Congress on Information and Communication Technologies, WICT 2022

作者： Arulmozhi Varman, M. Deepak, Gerard Department of Electronics and Electrical Engineering SASTRA Deemed University Tamil Nadu Thanjavur India Department of Computer Science and Engineering National Institute of Technology Tiruchirappalli India

ISBN: (纸本)9783031274985

There is an enormous amount of data stored on the World Wide Web throughout the years of internet practice. There is a necessity for sophisticated techniques of acquiring and categorizing information resources available on the internet. In the domains of information retrieval and natural language processing, document retrieval has been an important task. Despite the fact that document retrieval algorithms have evolved significantly over the years, there is always space for improvement. Tokenization, lemmatization, SWE, and NER are among the preparation methods applied to the dataset. The preprocessed dataset is then transferred to XML format, where the RDF mapping is performed using the Jellyfish method. The knowledge graph is built using blogs, social network APIs, crowdsource community ontology, wiki data and Freebase, and LODC. The formulated knowledge graph is converted to RDF format from OWL format. The Jellyfish method is used on the updated knowledge graph in OWL format and the RCVI dataset in OWL format to conduct RDF mapping in terms of (subject predicate object predicate). To rank the document in increasing order of semantic similarity, KL divergence is applied to the RDF mapping obtained in the previous phase. Based on the increasing order of semantic similarity the most relevant document is recommended. The proposed framework accomplished an accuracy of 92.78%. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Resource Description Framework (RDF)

来源：评论

学校读者我要写书评

暂无评论

Improving Contextual knowledge in natural language processing: An Analysis of Complex language Models and Their Uses

Improving Contextual Knowledge in Natural Language Processin...

引用

IEEE UP Section conference on Electrical Computer and Electronics (UPCON)

作者： Ketankumar V Rawal Vinay A M Hari Krishna Navdeep Singh Muntather Almusawi Soleman Awad Alzobidy Information Technology Citibank Jersey city NJ USA Division of Languages School of Life Sciences JSS Academy of Higher Education & Research Mysuru Karnataka India Institute of Aeronautical Engineering Dundigal Hyderabad Lovely Professional University Phagwara The Islamic university Najaf Department of English Language and Translation Studies College of Sciences and Theoretical Studies Saudi Electronic University Kingdom of Saudi Arabia

Recent years have seen tremendous progress in natural language processing (NLP), mostly because of the creation of sophisticated language models. This study examines how NLP methods have developed with an emphasis on improving contextual knowledge. This work investigates the function of complex language models in enhancing contextual comprehension in NLP tasks by thoroughly analyzing their designs, training methods, and applications. Through an assessment of different cutting-edge models and their practical uses, this study offers insights into the difficulties encountered, the progress achieved, and the potential for future development in the field of contextual knowledge enhancement in natural language processing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GIST: Guided Interpretable Large language Model Strategy Transfer for Multi-Task Reinforcement Learning

GIST: Guided Interpretable Large Language Model Strategy Tra...

引用

international conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Bo Zhao Zhuo Tang College of Computer Science and Electronic Engineering Hunan University Changsha China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Multi-task reinforcement learning (MTRL) presents critical challenges, such as the complexities of task-switching and maintaining knowledge retention across various tasks, especially within control tasks. These challenges frequently result in sub-optimal decision-making and catastrophic forgetting during task transitions. To mitigate these challenges, we introduce a framework that leverages large language models for strategic guidance, optimizing decision-making and action selection. The framework integrates a Kolmogorov-Arnold Network to ensure interpretability via symbolic regression, enabling effective strategy transfer across diverse environments. Adaptive Elastic Weight Consolidation is employed to prevent catastrophic forgetting, preserving task-specific knowledge across training. A caching mechanism reduces computational overhead linked to large language model queries, enhancing overall efficiency. Experimental evaluations indicate competitive performance, robust interpretability, and effective strategy transfer.

关键词： Training Large language models Scalability Decision making Reinforcement learning Signal processing Multitasking Robustness Computational efficiency Speech processing

来源：评论

学校读者我要写书评

暂无评论

Research on the Construction of Chinese Literature knowledge Graph and Intelligent Recommendation Algorithm

Research on the Construction of Chinese Literature Knowledge...

引用

language Technology and Digital Humanities (LTDH), international conference on

作者： Donglei Zhang Ye Luo Bingxian Li Weifang Engineering Vocational College Shandong China

ISBN: (数字)9798350380187

ISBN: (纸本)9798350380194

The digitization trend of Chinese literature is becoming more and more significant, which provides literature lovers with more convenient ways of reading and rich literary resources. However, how to quickly and accurately find the works that meet personal interests and needs among the vast amount of literary works has become an urgent problem to be solved. Therefore, this paper focuses on the construction of Chinese literature knowledge-graph and intelligent recommend-algorithms, aiming to provide personalized reading recommendation services for literature lovers. Through natural language processing and text mining technology, a large number of Chinese literary works are deeply analyzed and structured to extract the key information in the literary works. This paper designs a variety of intelligent recommendation strategies based on the constructed knowledge-graph of Chinese literature. Combined with the classical recommend-algorithm, a hybrid recommend-algorithm based on knowledge-graph is designed. By training the neural network model, the mining and prediction of the user's potential interest is realized, which further ameliorates the intelligent level of recommendation. This study not only provides personalized reading recommendation service for Chinese literature lovers, but also provides new ideas and methods for the construction of Chinese literature knowledge-graph and the research of intelligent recommend-algorithms.

关键词： Training Text mining Accuracy Semantics Neural networks knowledge graphs Predictive models natural language processing Optimization Recommender systems

来源：评论

学校读者我要写书评

暂无评论

A survey on few-shot learning in natural language processing 2

A survey on few-shot learning in natural language processing

引用

2nd international conference on Artificial Intelligence and Electromechanical Automation, AIEA 2021

作者： Yang, Mengde China University of Geosciences Beijing School of Information Engineering Beijing China

ISBN: (纸本)9781665432658

The annotated dataset is the foundation for Supervised natural language processing. However, the cost of obtaining dataset is high. In recent years, the Few-Shot Learning has gradually attracted the attention of researchers. From the definition, in this paper, we conclude the difference in Few-Shot Learning between natural language processing and Computer Vision. On that basis, the current Few-Shot Learning on natural language processing is summarized, including Transfer Learning, Meta Learning and knowledge Distillation. Furthermore, we conclude the solutions to Few-Shot Learning in natural language processing, such as the method based on Distant Supervision, Meta Learning and knowledge Distillation. Finally, we present the challenges facing Few-Shot Learning in natural language processing. © 2021 IEEE.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Simple and Efficient knowledge Graph Attention Network for Recommendation

Simple and Efficient Knowledge Graph Attention Network for R...

引用

2023 international conference on Cyber-Physical Social Intelligence, ICCSI 2023

作者： Li, Yangding Fu, Shaobin Feng, Hao Zeng, Yangyang Wang, Jinghao Jiang, Zhihao Zhang, Lvyun Hunan Provincial Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University School of Information Science and Engineering Changsha China Shenzhen Lazada Software Technology Company Limited Shenzhen China Hechi University School of Big Data and Computer Science Guangxi China

ISBN: (纸本)9798350312492

Existing methods for modeling recommendation systems based on knowledge graphs include embedding-based, pathbased, and propagation-based methods. The embedding-based approach is flexible but more suitable for intra-graph applications, the path-based approach can model complex relationships but has a high computational cost, and the propagation-based approach considers global information but may introduce noise. This study proposed a simple and efficient model, called SEKGAT, which comprehensive the ideology of path-based and propagation approach to personalized recommendation by aggregating the user preferences through graph attention mechanism and fusing multiple feature representations on the knowledge graph into item features through pooling aggregators. Experimental results for the CTR prediction and Top-K recommendation tasks on three datasets of real-world scenarios show that our model approach is competitive. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Graph-to-Text Generation Combining Directed and Undirected Structural Information in knowledge Graphs*

Graph-to-Text Generation Combining Directed and Undirected S...

引用

natural language processing (ICNLP), international conference on

作者： Hongda Gong Shimin Shan Hongkui Wei Software School Dalian University of Technology Dalian University of Technology DaLian China State Key Laboratory of Intelligent Manufacturing System Technology Beijing Institute of Electronic System Engineering Beijing China

Graph-to-text generation task is transforms knowledge graphs into natural language. In current research, pretrained language models(PLMs) have shown better performance than structured graph encoders in the generation task. Currently, PLMs serialise knowledge graphs mostly by transforming them into undirected graph structures. The advantage of an undirected graph structure is that it provides a more comprehensive representation of the information in knowledge graph, but it is difficult to capture the dependencies between entities, so the information represented may not be accurate. Therefore, We use four types of positional embedding to obtain both the directed and undirected structure of the knowledge graph, so that we can more fully represent the information in knowledge graph, and the dependencies between entities. We then add a semantic aggregation module to the Transformer layer of PLMs, which is used to obtain a more comprehensive representation of the information in knowledge graph, as well as to capture the dependencies between entities. Thus, our approach combines the advantages of both directed and undirected structural information. In addition, our new approach is more capable of capturing generic knowledge and can show better results with small samples of data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

knowledge Enhancement and Feature Purification for Single-stage Joint Entity and Relation Extraction 29

Knowledge Enhancement and Feature Purification for Single-st...

引用

29th IEEE international conference on Parallel and Distributed Systems, ICPADS 2023

作者： Zhai, Guohao Pei, Songwen University of Shanghai for Science and Technology School of Optical-Electrical and Computer Engineering Shanghai China

ISBN: (纸本)9798350330717

Joint entity and relation extraction aim to achieve named entity recognition and relation extraction in unstructured text. We use the form of triples (subject, relation, object) to describe entity and relation. Joint entity and relation extraction play an important role in knowledge graph construction, question and answering, data analysis, and other natural language processing domains. Most of the existing works suffered from insufficient interaction between entity features and relation features due to the extraction order. Moreover, there is a prevalence of heterogeneous representations of entities and relations. They not only increase the amount of model design and the complexity of training, but also lead to the problem of exposure bias due to the extraction order. Therefore, in this paper, we propose KFRel, where we enhance the entity and relation representations by encoding text and relation. Then, the features are fused to enhance the entity and relation representations, and adopt a feature purification module, where the features are enhanced by a feature purification module that removes feature information irrelevant to the joint entity and relation extraction while retaining feature information of relevance. In addition, we adopt a single-stage joint entity and relation extraction module to address the issue of overlapping triples. This module aims to help improve the effectiveness of joint entity and relation extraction. Comprehensive experiments are conducted on two widely-used datasets, and the experimental results demonstrate that the proposed method is effective and outperforms the state-of-the-art baselines. © 2023 IEEE.

关键词： Feature Purification Joint Entity and Relation Extraction knowledge Enhancement

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共440页 << < 73 74 75 76 77 78 79 80 81 82 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：