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

14,082 篇 会议
98 册 图书
65 篇 期刊文献
1 篇 资讯

馆藏范围

14,246 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

9,384 篇 工学
- 8,573 篇 计算机科学与技术...
- 6,863 篇 软件工程
- 1,927 篇 信息与通信工程
- 1,310 篇 控制科学与工程
- 1,209 篇 电气工程
- 906 篇 生物工程
- 418 篇 生物医学工程（可授...
- 417 篇 电子科学与技术（可...
- 413 篇 网络空间安全
- 307 篇 化学工程与技术
- 288 篇 仪器科学与技术
- 281 篇 机械工程
- 266 篇 光学工程
- 211 篇 安全科学与工程
- 196 篇 交通运输工程
3,131 篇 理学
- 1,227 篇 数学
- 932 篇 生物学
- 887 篇 物理学
- 486 篇 统计学（可授理学、...
- 460 篇 系统科学
- 355 篇 化学
2,813 篇 管理学
- 1,831 篇 图书情报与档案管...
- 1,192 篇 管理科学与工程(可...
- 463 篇 工商管理
567 篇 医学
- 408 篇 临床医学
- 365 篇 基础医学(可授医学...
- 312 篇 公共卫生与预防医...
- 163 篇 药学(可授医学、理...
450 篇 法学
- 418 篇 社会学
217 篇 教育学
- 213 篇 教育学
194 篇 文学
155 篇 经济学
98 篇 农学
11 篇 艺术学
9 篇 军事学
1 篇 哲学

主题

2,893 篇 natural language...
873 篇 natural language...
841 篇 natural language...
815 篇 semantics
552 篇 deep learning
546 篇 machine learning
512 篇 sentiment analys...
505 篇 data mining
390 篇 knowledge engine...
369 篇 training
355 篇 computational mo...
351 篇 large language m...
322 篇 speech recogniti...
307 篇 feature extracti...
301 篇 speech processin...
272 篇 signal processin...
264 篇 accuracy
239 篇 neural networks
235 篇 knowledge based ...
234 篇 transformers

机构

55 篇 institute of inf...
50 篇 school of cyber ...
48 篇 school of commun...
40 篇 maharishi school...
38 篇 chitkara univers...
36 篇 school of comput...
35 篇 lovely professio...
34 篇 university of ch...
32 篇 school of comput...
31 篇 xi'an university...
30 篇 faculty of engin...
27 篇 department of el...
23 篇 school of inform...
22 篇 school of comput...
22 篇 department of co...
20 篇 centre of interd...
18 篇 pune
17 篇 zhejiang univers...
16 篇 college of compu...
15 篇 college of compu...

作者

36 篇 ren fuji
27 篇 wan wanggen
17 篇 liu yang
16 篇 yixin zhong
14 篇 wu jin
14 篇 lei li
14 篇 shingo kuroiwa
13 篇 zhang tao
13 篇 wang lei
13 篇 sabetzadeh mehrd...
13 篇 zheng dequan
13 篇 liu jie
13 篇 fuji ren
12 篇 tiejun zhao
12 篇 f. ren
12 篇 ge haibo
11 篇 li sheng
11 篇 yang yang
11 篇 tao zhang
11 篇 li ying

语言

11,805 篇 英文
2,410 篇 其他
49 篇 中文
3 篇 土耳其文

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

共 14246 条记录，以下是51-60 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：

A Review on Deep Learning Based Question Answering with natural language processing in Healthcare

A Review on Deep Learning Based Question Answering with Natu...

引用

2024 international conference on knowledge engineering and Communication Systems, ICKECS 2024

作者： Javeed, Abdul Saleem Gopala Krishnan, C. Gitam School of Technology Dept. of Computer Science & Engineering Bengaluru India

ISBN: (纸本)9798350359688

Over the Internet, an efficient approach and promising solution to retrieve significant information envisages the beginning of Question Answering Systems (QAS). Because of data sources availability, the deep learning model based on open domain QAS focuses a substantial quantity of research work. Because of the lack of medical datasets, less attention is received in the medical domain. The deep learning (DL) utility increases the development of huge data in the healthcare domain. In the past years, popularity has grown in hardware parallelism and quick data storage availability. The challenge, pipelines, and tasks involved in medical NLP and medical imaging deploy the existing review of research in this work. The medical NLP and imaging fields deploy DL structures with its extensive survey is presented here. Over all 39 research papers are collected for this survey analysis from the years 2017 to 2023. The diagnosis is enhanced with medical imaging, natural language processing, and DL combination to detect the appropriate combination. Each of the outcomes is shown graphically. The information provided in this survey is quite useful for newcomers carrying out research in medical informatics. © 2024 ieee.

关键词： and Medical Data Deep Learning Healthcare natural language processing Question Answering

来源：评论

学校读者我要写书评

暂无评论

An Efficient Training Framework for Chinese Text Classification: Integrating Large language Models and Reinforcement Learning 5

An Efficient Training Framework for Chinese Text Classificat...

引用

5th international conference on Artificial Intelligence and Computer engineering

作者： Wang, Teng Xue, Zhenyu China Jiliang Univ Coll Informat Engn Hangzhou Peoples R China

ISBN: (纸本)9798331528911;9798331528928

This study proposes an efficient model training framework aimed at improving the performance of hierarchical classification of Chinese text in low-computation environments. By leveraging the generative capabilities of large language models for data annotation and augmentation, a high-quality dataset is constructed. knowledge distillation techniques are applied to transfer knowledge from a complex teacher model to a lightweight student model, effectively reducing computational resources. Additionally, a reinforcement learning strategy is introduced to further optimize the student model, enabling it to surpass the teacher model in both accuracy and inference efficiency, providing a novel solution for natural language processing and other resource-constrained tasks.

关键词： data labeling knowledge distillation data augmentation reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Large language Model-Enabled Multi-Agent Manufacturing Systems 20

Large Language Model-Enabled Multi-Agent Manufacturing Syste...

引用

ieee 20th international conference on Automation Science and engineering (CASE)

作者： Lim, Jonghan Vogel-Heuser, Birgit Kovalenko, Ilya Penn State Univ Dept Ind & Mfg State Coll PA 16802 USA Penn State Univ Dept Mech Engn State Coll PA 16802 USA Tech Univ Munich Inst Automat & Informat Syst Munich Germany

ISBN: (纸本)9798350358513;9798350358520

Traditional manufacturing faces challenges adapting to dynamic environments and quickly responding to manufacturing changes. The use of multi-agent systems has improved adaptability and coordination but requires further advancements in rapid human instruction comprehension, operational adaptability, and coordination through natural language integration. Large language models like GPT-3.5 and GPT-4 enhance multi-agent manufacturing systems by enabling agents to communicate in natural language and interpret human instructions for decision-making. This research introduces a novel framework where large language models enhance the capabilities of agents in manufacturing, making them more adaptable, and capable of processing context-specific instructions. A case study demonstrates the practical application of this framework, showing how agents can effectively communicate, understand tasks, and execute manufacturing processes, including precise G-code allocation among agents. The findings highlight the importance of continuous large language model integration into multi-agent manufacturing systems and the development of sophisticated agent communication protocols for a more flexible manufacturing system.

关键词： Flexible manufacturing systems

来源：评论

学校读者我要写书评

暂无评论

GraphLingo: Domain knowledge Exploration by Synchronizing knowledge Graphs and Large language Models 40

GraphLingo: Domain Knowledge Exploration by Synchronizing Kn...

引用

40th ieee international conference on Data engineering, ICDE 2024

作者： Le, Duy Zhao, Kris Wang, Mengying Wu, Yinghui Case Western Reserve Univ. United States

ISBN: (纸本)9798350317152

knowledge graphs (KGs) are routinely curated to provide factual data for various domain-specific analyses. Nevertheless, it remains nontrivial to explore domain knowledge with standard query languages. We demonstrate GraphLingo, a natural language (NL)-based knowledge exploration system designed for exploring domain-specific knowledge graphs. It differs from conventional knowledge graph search tools in that it enables an interactive exploratory NL query over domain-specific knowledge graphs. GraphLingo seamlessly integrates graph query processing and large language models with a graph pattern-based prompt generation approach to guide users in exploring relevant factual knowledge. It streamlines NL-based question & answer, graph query optimization & refining, and automatic prompt generation. A unique feature of GraphLingo is its capability to enable users to explore by seamlessly switching between a more 'open' approach and a more relevant yet 'conservative' one, facilitated by diversified query suggestions. We show cases of GraphLingo in curriculum suggestion, and materials scientific data search. © 2024 ieee.

关键词： knowledge graph

来源：评论

学校读者我要写书评

暂无评论

language-ORIENTED COMMUNICATION WITH SEMANTIC CODING AND knowledge DISTILLATION FOR TEXT-TO-IMAGE GENERATION 49

LANGUAGE-ORIENTED COMMUNICATION WITH SEMANTIC CODING AND KNO...

引用

49th ieee international conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Nam, Hyelin Park, Jihong Choi, Jinho Bennis, Mehdi Kim, Seong-Lyun Yonsei Univ Seoul South Korea Deakin Univ Geelong Vic Australia Univ Oulu Oulu Finland

ISBN: (纸本)9798350344868;9798350344851

By integrating recent advances in large language models (LLMs) and generative models into the emerging semantic communication (SC) paradigm, in this article we put forward to a novel framework of language-oriented semantic communication (LSC). In LSC, machines communicate using human language messages that can be interpreted and manipulated via natural language processing (NLP) techniques for SC efficiency. To demonstrate LSC's potential, we introduce three innovative algorithms: 1) semantic source coding (SSC) which compresses a text prompt into its key head words capturing the prompt's syntactic essence while maintaining their appearance order to keep the prompt's context;2) semantic channel coding (SCC) that improves robustness against errors by substituting head words with their lenghthier synonyms;and 3) semantic knowledge distillation (SKD) that produces listener-customized prompts via in-context learning the listener's language style. In a communication task for progressive text-to-image generation, the proposed methods achieve higher perceptual similarities with fewer transmissions while enhancing robustness in noisy communication channels.

关键词： Semantic communication (SC) large language model (LLM) generative model

来源：评论

学校读者我要写书评

暂无评论

UNSUPERVISED MULTIPLE CHOICES QUESTION ANSWERING VIA UNIVERSAL CORPUS 49

UNSUPERVISED MULTIPLE CHOICES QUESTION ANSWERING VIA UNIVERS...

引用

49th ieee international conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Zhang, Qin Ge, Hao Chen, Xiaojun Fang, Meng Shenzhen Univ Shenzhen Peoples R China Univ Liverpool Liverpool Merseyside England

ISBN: (纸本)9798350344868;9798350344851

Unsupervised question answering is a promising yet challenging task, which alleviates the burden of building large-scale annotated data in a new domain. It motivates us to study the unsupervised multiple-choice question answering (MCQA) problem. In this paper, we propose a novel framework designed to generate synthetic MCQA data barely based on contexts from the universal domain without relying on any form of manual annotation. Possible answers are extracted and used to produce related questions, then we leverage both named entities (NE) and knowledge graphs to discover plausible distractors to form complete synthetic samples. Experiments on multiple MCQA datasets demonstrate the effectiveness of our method.

关键词： natural language processing Unsupervised Multiple Choices Question Answering knowledge Graphs

来源：评论

学校读者我要写书评

暂无评论

The Application of LLMs in the Analysis and Modeling of Software Requirements 24

The Application of LLMs in the Analysis and Modeling of Soft...

引用

24th ieee international conference on Software Quality, Reliability and Security Companion, QRS-C 2024

作者： Wang, Zhipeng Feng, Changxi Liu, Longfei Jiao, Guotao Ye, Peng School of Computer Science and Artificial Intelligence WuGuotao Jiaohan Textile University China Engineering Research Center of Hubei Province for Clothing Information Wuhan Textile University China

ISBN: (纸本)9798350365658

In modern software engineering, requirements analysis and modeling are key steps in requirements engineering, influencing the subsequent system design and implementation. Traditional requirements analysis and modeling methods usually involve multiple stakeholders such as requirements providers and analysts working together collaboratively and iteratively, requiring a significant amount of manpower. It is of great significance to reduce the burden on requirements providers and analysts and improve the efficiency of analysis and modeling. In existing work, some merely utilize knowledge repositories to provide more knowledge in support of analysis or modeling, while others employ natural language processing (NLP) techniques to automate the analysis or modeling process. However, neither has relieved the burden on requirements providers and analysts. The emergence of large language models(LLMs) has brought new possibilities to requirements analysis and modeling. LLMs can combine knowledge base processing and understanding of large amounts of natural language data, providing a new automated requirement analysis method. This paper proposes an automated requirements analysis and modeling method for Support Vector Machine(SVM) classifier and LLMs - SVM-LLMs. The method is deployed based on the intelligent requirement service platform - 'Wisdom Requirement Communication', which combines SVM and LLMs to effectively improve the accuracy of requirements analysis and significantly reduce the time in the software development process. © 2024 ieee.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

AI-CRAS: AI-driven Cloud Service Requirement Analysis and Specification 12

AI-CRAS: AI-driven Cloud Service Requirement Analysis and Sp...

引用

12th international conference on Cloud engineering

作者： Casalicchio, Emiliano Cotumaccio, Alberto Sapienza Univ Rome Dept Comp Sci Rome Italy

ISBN: (纸本)9798331528690;9798331528706

Automated analysis and specification of software requirements expressed in natural language is a challenge addressed by the research community and is becoming a reality thanks to the advances in Artificial Intelligence (AI) and natural language processing (NLP) techniques. While the research community focuses mainly on generic software requirements or specialized solutions for security requirements, we find a gap in the automation of analysis and specification for requirements in the cloud computing domain and the automatic mapping of requirements on actual products offered in the cloud service market. In this research work, we propose AI-CRAS an AI-driven cloud service requirement analysis and specification methodology. The proposed method, which leverages state-of-the-art transformer-based large language model, has been implemented and validated in a real case. Experimental results demonstrate that the model performed well in binary and multilabel classification of requirements (achieving recall/F1-score of 0.96/0.92 and 0.86/0.76, respectively) and mapping requirements into actual cloud services.

关键词： cloud computing cloud migration cloud services requirement engineering artificial intelligence natural language processing cloud service broker

来源：评论

学校读者我要写书评

暂无评论

Correcting Factual Errors in LLMs via Inference Paths Based on knowledge Graph

Correcting Factual Errors in LLMs via Inference Paths Based ...

引用

2024 international conference on Computational Linguistics and natural language processing, CLNLP 2024

作者： Ye, Weiqi Zhang, Qiang Zhou, Xian Hu, Wenpeng Tian, Changhai Cheng, Jiajun Hebei University of Engineering School of Information and Electrical Engineering Handan China Pla Academy of Military Sciences Information Research Center of Military Science Beijing China

ISBN: (纸本)9798350392098

Large language models (LLMs) have been observed to occasionally exhibit hallucination, a phenomenon where they generate statements unsupported by factual evidence, thereby compromising the trustworthiness of their output. Current approaches to mitigating this problem largely rely on extracting a single triplet from a knowledge graph, which fails to adequately capture the complex and interlinked nature of factual reasoning. In an effort to address this critical challenge, this paper delves into the utilization of inference paths based on knowledge graph for factual error correction of LLMs. At the heart of our approach lies the deployment of deep reinforcement learning algorithms, which traverse the knowledge graph to retrieve inference paths. These paths, replete with contextual depth and logical coherence, thereby amending the content and diminishing the incidence of factual discrepancies in the reasoning process of LLMs. Experimental results demonstrate that our approach markedly enhances the factual QA performance of LLMs. Furthermore, it shows great potential in improving the reliability of LLMs in complex reasoning scenarios, highlighting the effectiveness of inference path derived from knowledge graph. © 2024 ieee.

关键词： knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Robust knowledge Distillation and Self-Contrast Reasoning for Debiased Visual Question Answering

Robust Knowledge Distillation and Self-Contrast Reasoning fo...

引用

ieee international conference on Multimedia and Expo (ICME)

作者： Ning, Ke Shen, Rongrong Li, Zhixin Guangxi Normal Univ Key Lab Educ Blockchain & Intelligent Technol Minist Educ Guilin 541004 Peoples R China Guangxi Normal Univ Guangxi Key Lab Multisource Informat Min & Secur Guilin 541004 Peoples R China

ISBN: (纸本)9798350390155;9798350390162

The language prior problem in VQA makes the model directly predictis based on questions, causing the model's performance to drop sharply outside the distribution. Current debiased methods often achieve good out-of-distribution generalization capabilities at the expense of in-distribution performance degradation. We propose a novel method combining Robust knowledge distillation and self-contrast Reasoning (RR-VQA) to solve the language prior problem in VQA. We propose the QAS module to select reasonable questions for images, perform knowledge distillation through the ID and OOD teacher models, and obtain pseudo answers after passing through the QAS module. The CRSG module we propose synthesizes four visual language positive and negative samples for contrastive reasoning, which effectively increases the semantic dependency of the images while avoiding performance degradation due to spurious correlations between questions and answers. Our method is model-agnostic and achieves state-of-the-art performance on VQA-CP v2 dataset while maintaining performance on VQA v2 dataset.

关键词： Visual Question Answering language Priors knowledge Distillation Contrastive Learning

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500页 << < 2 3 4 5 6 7 8 9 10 11 > >>

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：