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

14,303 篇 会议
98 册 图书
66 篇 期刊文献
1 篇 资讯

馆藏范围

14,468 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

9,574 篇 工学
- 8,758 篇 计算机科学与技术...
- 6,972 篇 软件工程
- 2,028 篇 信息与通信工程
- 1,454 篇 控制科学与工程
- 1,256 篇 电气工程
- 907 篇 生物工程
- 473 篇 网络空间安全
- 436 篇 电子科学与技术（可...
- 421 篇 生物医学工程（可授...
- 313 篇 化学工程与技术
- 307 篇 仪器科学与技术
- 294 篇 机械工程
- 268 篇 光学工程
- 256 篇 安全科学与工程
- 240 篇 交通运输工程
- 182 篇 动力工程及工程热...
3,191 篇 理学
- 1,265 篇 数学
- 932 篇 生物学
- 900 篇 物理学
- 503 篇 统计学（可授理学、...
- 462 篇 系统科学
- 378 篇 化学
2,915 篇 管理学
- 1,865 篇 图书情报与档案管...
- 1,281 篇 管理科学与工程(可...
- 472 篇 工商管理
613 篇 医学
- 418 篇 临床医学
- 369 篇 基础医学(可授医学...
- 353 篇 公共卫生与预防医...
470 篇 法学
- 438 篇 社会学
229 篇 教育学
- 225 篇 教育学
207 篇 文学
159 篇 经济学
98 篇 农学
11 篇 艺术学
9 篇 军事学
1 篇 哲学

主题

2,963 篇 natural language...
874 篇 natural language...
839 篇 natural language...
817 篇 semantics
577 篇 deep learning
554 篇 machine learning
533 篇 sentiment analys...
507 篇 data mining
395 篇 knowledge engine...
368 篇 large language m...
362 篇 training
355 篇 computational mo...
312 篇 feature extracti...
309 篇 speech recogniti...
304 篇 speech processin...
275 篇 signal processin...
272 篇 accuracy
241 篇 neural networks
239 篇 transformers
237 篇 knowledge based ...

机构

57 篇 institute of inf...
52 篇 school of cyber ...
49 篇 school of commun...
40 篇 chitkara univers...
40 篇 maharishi school...
35 篇 lovely professio...
34 篇 university of ch...
34 篇 school of comput...
33 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...
19 篇 beijing universi...
18 篇 pune
17 篇 zhejiang univers...
17 篇 college of compu...

作者

38 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
12 篇 tiejun zhao
12 篇 f. ren
12 篇 li ying
11 篇 li sheng
11 篇 yang yang
11 篇 tao zhang
11 篇 arora chetan
11 篇 wang wei

语言

10,918 篇 英文
3,521 篇 其他
53 篇 中文
1 篇 土耳其文

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

共 14468 条记录，以下是4981-4990 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：

Freeze the Backbones: a Parameter-Efficient Contrastive Approach to Robust Medical Vision-language Pre-Training

Freeze the Backbones: a Parameter-Efficient Contrastive Appr...

引用

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

作者： Jiuming Qin Che Liu Sibo Cheng Yike Guo Rossella Arcucci Department of Computing Imperial College London Data Science Institute Imperial College London Department of Earth Science and Engineering Imperial College London Department of Computer Science and Engineering The Hong Kong University of Science and Technology

Modern healthcare often utilises radiographic images alongside textual reports for diagnostics, encouraging the use of Vision-language Self-Supervised Learning (VL-SSL) with large pre-trained models to learn versatile medical vision representations. However, most existing VL-SSL frameworks are trained end-to-end, which is computation-heavy and can lose vital prior information embedded in pre-trained encoders. To address both issues, we introduce the backbone-agnostic Adaptor framework, which preserves medical knowledge in pre-trained image and text encoders by keeping them frozen, and employs a lightweight Adaptor module for cross-modal learning. Experiments on medical image classification and segmentation tasks across three datasets reveal that our framework delivers competitive performance while cutting trainable parameters by over 90% compared to current pre-training approaches. Notably, when fine-tuned with just 1% of data, Adaptor outperforms several Transformer-based methods trained on full datasets in medical image segmentation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Developments in natural language processing: Applications and Challenges

Developments in Natural Language Processing: Applications an...

引用

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

作者： Sunil G Tamirat Tagesse Takore Praseeda Ravuri Amandeep Nagpal Melanie Lourens K. Ganapathi Babu School of CS & AI SR University Warangal Telangana India Department of Electrical and Computer Engineering Wachemo University Ethiopia Computer Science Engineer Oregon state university Corvallis Oregon USA Lovely Professional University Phagwara Deputy Dean Faculty of Management Sciences Durban University of Technology South Africa Computer Science and Engineering St. Martin's Engineering College Secunderabad Telangana

natural language is any language that a person uses or speaks, such as Hindi, English, French, Marathi, Bengali, Gujrati, and so *** can better comprehend, interpret, and manipulate human language with the help of the area of called NLP. NLP is dependent on a number of academic disciplines, notably software engineering and computational languages, in order to bridge the gap among human communication and machine understanding. natural language processing (NLP), which can represent and interpret human language computer, has attracted a lot of attention *** applications have grown to include, among other things, machine translation, spam email detection, information extraction, summarization, and question answering. The article breaks its topic into four sections: a discussion of different NLP levels and NLG components comes first, then the history and evolution of NLP, the state of the art, a rundown of all the different NLP applications, and a discussion of recent advancements and difficulties.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MAST-NER: A Low-Resource Named Entity Recognition Method Based on Trigger Pool 15th

MAST-NER: A Low-Resource Named Entity Recognition Method Bas...

引用

15th international conference on knowledge Science, engineering, and Management (KSEM)

作者： Xu, Juxiong Li, Minbo Fudan Univ Software Sch Shanghai 200438 Peoples R China Shanghai Key Lab Data Sci Shanghai 200438 Peoples R China

ISBN: (纸本)9783031109898;9783031109881

Named entity recognition (NER) is a basic knowledge extraction task. At present, many domains face a lack of labeled data, but current models for low-resource NER does not utilize the features of domain text. In this paper, we propose the MAST-NER model to improve the NER performance on domain-specific text. This model introducesmultiple type pools based on entity triggers, and enhances sequence tagging through a multi-head attention mechanism, where the query matrix is jointly constructed by each type of triggers. MAST-NER can take full advantages of entity triggers on domain text with similar sentence patterns, and enable each type of entity recognition to be enhanced. The experimental results show that the model in this paper can achieve higher cost-effectiveness, especially for domain datasets (up to 3.33%). For general domain datasets, this model also has a certain performance improvement.

关键词： Named entity recognition Entity trigger Attention mechanism Deep learning natural language processing

来源：评论

学校读者我要写书评

暂无评论

Experimental Evaluation for Text Classification using Improved Deep Learning Models 4

Experimental Evaluation for Text Classification using Improv...

引用

4th international conference on Advances in Computing, Communication Control and Networking, ICAC3N 2022

作者： Mounika, Kata Kumar Chowdary, Bharath Vnr Vignana Jyothi Institute of Engineering and Technology Department of CSE Hyderabad India

ISBN: (纸本)9781665474368

language use on online platforms has dramatically expanded over the last ten years. Turkish text natural language processing (NLP) research, however, has not gotten much attention. This article seeks to give a thorough review of the Turkish text classification tools and models that are currently accessible. On Turkish text classification dataset, we assess proposed improved Convolutional Neural Network (CNN) model. A customization is made with the default optimizer made. An Artificial Neural Network (ANN) based models is given a comparative analysis. We demonstrate that on the available datasets, simple single layer models to outperform conventional models. Ideally, our research and experimentation with paper is concentrated in the Turkish NLP field. © 2022 ieee.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Paraphrase Generator for Indonesian language: Basic Method for Generating Question on Interviewbot Engine 4

Paraphrase Generator for Indonesian Language: Basic Method f...

引用

4th international conference Advancement in Data Science, E-Learning and Information Systems, ICADEIS 2022

作者： Suakanto, Sinung Siswanto, Joko Angela, Dina Kusumasari, Tien Fabrianti Sen, Tjong Wan Cybernetics Research Group Telkom University Bandung Indonesia Industrial Engineering Research Group Bandung of Institute Technology Bandung Indonesia Information Techology Research Group Institut Teknologi Harapan Bangsa Bandung Indonesia President University Faculty of Computing Bekasi Indonesia

ISBN: (纸本)9781665463874

An interview is a stage to dig up information for participants who want to know the profile and matching to the interviewer's needs. The development of interviews using bots has undergone many developments, one of which is by creating more natural conversational interactions. In the process of extracting information, sometimes bots don't get much information if participants only answer in a limited. Therefore, this study proposes a basic technique for generating questions to dig deeper into the information during the interview process. The basic technique used is to use a paraphrase. The proposed paraphrase is to use a structure change based on a predefined structure. The results of this study were carried out in the Indonesian language (Bahasa) and the sentence structure used was referring to the rules in the Indonesian language. The basic method used is using NLP (natural language processing) and Rule Based Structure. The results of this research can be used as a basis for developing questions that will automatically be generated by bots for interview purposes. © 2022 ieee.

关键词： Botnet

来源：评论

学校读者我要写书评

暂无评论

DrLLM: Prompt-Enhanced Distributed Denial-of-Service Resistance Method with Large language Models

DrLLM: Prompt-Enhanced Distributed Denial-of-Service Resista...

引用

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

作者： Zhenyu Yin Shang Liu Guangyuan Xu Shenyang Institute of Computing Technology Chinese Academy of Sciences Liaoning Key Laboratory of Domestic Industrial Control Platform Technology on Basic Hardware and Software University of Chinese Academy of Sciences

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The increasing number of Distributed Denial of Service (DDoS) attacks poses a major threat to the Internet, highlighting the importance of DDoS mitigation. Most existing approaches require complex training methods to learn data features, which increases the complexity and generality of the application. In this paper, we propose DrLLM, which aims to mine anomalous traffic information in zero-shot scenarios through Large language Models (LLMs). To bridge the gap between DrLLM and existing approaches, we embed the global and local information of the traffic data into the reasoning paradigm and design three modules, namely knowledge Embedding, Token Embedding, and Progressive Role Reasoning, for data representation and reasoning. In addition we explore the generalization of prompt engineering in the cybersecurity domain to improve the classification capability of DrLLM. Our ablation experiments demonstrate the applicability of DrLLM in zero-shot scenarios and further demonstrate the potential of LLMs in the network domains. The implementation of DrLLM is available at https://***/liuup/DrLLM.

关键词： Training Resistance Large language models Prevention and mitigation Signal processing Cognition Internet Prompt engineering Computer crime Speech processing

来源：评论

学校读者我要写书评

暂无评论

APTSniffer: Detecting APT Attack Traffic Using Retrieval-Augmented Large language Models

APTSniffer: Detecting APT Attack Traffic Using Retrieval-Aug...

引用

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

作者： Hongbo Xu Chengxiang Si Zhouzhou Chenxu Wang Peishuai Sun Qingyun Liu Institute of Information Engineering Chinese Academy of Sciences Beijing School of Cyber Security University of Chinese Academy of Sciences Beijing China Zhongguancun Laboratory Beijing China National Computer Network Emergency Response Technical Team/Coordination Center of China Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Advanced Persistent Threats (APT) differ from traditional attacks by using more complex and covert strategies for long-term assaults, posing a severe threat to organizational and national security. Due to problems like the shortage of APT traffic data and encrypted traffic obfuscation, existing methods cannot accurately identify APT traffic with just a few traffic samples. To overcome the above limitation, we propose a novel encrypted APT traffic detection model, APTSniffer, which combines large language models (LLM) and retrieval-augmented technology. APTSniffer utilizes the few-shot inference and generalization abilities of large language models by converting raw traffic data into natural language inference examples understandable by the LLM. Experimental results show that, compared to other baseline models, APTSniffer exhibits SOTA performance. It achieves F1 scores above 97% on three APT datasets, making it practically applicable for APT traffic detection tasks.

关键词： Large language models natural languages Training data Signal processing Cognition Acoustics Cryptography Speech processing National security

来源：评论

学校读者我要写书评

暂无评论

Development of Logical Methods for Extracting Emotional Assessments from natural language Texts

Development of Logical Methods for Extracting Emotional Asse...

引用

international conference on Actual Problems of Electronic Instrument engineering (APEIE)

作者： Dmitry E. Palchunov Ergash Yu. Akhmedov DSc. Academian of REA Leading Researcher Sobolev Institute of Mathematics Novosibirsk Russia IT Department Novosibirsk State University Novosibirsk Russia

The article is devoted to the problem of extracting emotional assessments from natural language texts. The article analyzes existing methods of sentiment analysis and explores modern methods of natural language processing to determine the sentiment of Uzbek texts. Existing approaches to the study and description of emotions are explored. Particular attention is paid to emotional assessments of situations presented in natural language texts. Logical-semantic methods and technologies based on deep machine learning methods are considered. Formalization of emotional assessments contained in natural language texts is carried out using the theory of partial models. The task of classification is to assign a class to objects based on their characteristics. In the case of the emotion model, the emotion texts are object-class pairs. Since the number of emotions is not binary, the classification is not binary. To solve the classification problem, a training data set consisting of labeled text with emotions is required.

关键词：

来源：评论

学校读者我要写书评

暂无评论

NL2SQL: natural language to SQL Query Translator 6th

NL2SQL: Natural Language to SQL Query Translator

引用

6th international conference on Emerging Research in Computing, Information, Communication and Applications, ERCICA 2020

作者： Revanth, T.J. Sai, K. Venkat Ramya, R. Chava, Renusree Sushma, V. Ramya, B.S. Department of Information Science and Engineering Nitte Meenakshi Institute of Technology Bangalore560064 India

ISBN: (纸本)9789811613418

Most of the media networks and organizations require a database to store the information and to retrieve the information from the database where structured query language (SQL) is utilized. SQL has its own sentence format to frame the questions. The capacity of end users to recover information from a database is constrained because of an absence of SQL knowledge. To recover right information from the database, this inquiry needs to be written in legitimate or right linguistic structure. Along these lines, the essential target of this proposed work is to locate the reasonable method to change over natural language to SQL and make the information available for end users. In existing NLS-SQL system, the users found difficulty in querying due to firm data dictionaries which users are not allowed to change or modify the data dictionary as per their requirements. In this paper, we propose a system that provides a user-friendly interface between end user and database. The essential feature of our paper is that users have privilege to update data dictionaries by which they can add new terms or phrases which can be mapped to their corresponding clause in SQL. In this, we undertake a lightweight strategy of changing over a characteristic language explanation into comparable SQL articulation, which when executed on a database furnishes us with the precise outcomes using natural language processing (NLP). In the proposed framework, we have used natural language processing (NLP) to enable communication between users and system without need to memorize the complex SQL commands. The project framework will now allow the amateur users who do not have any information about SQL to recover the necessary information. This framework can be used at the training and placement cell officials who deal with database study. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Query processing

来源：评论

学校读者我要写书评

暂无评论

Confidence Elicitation Improves Selective Generation in Black-Box Large language Models

Confidence Elicitation Improves Selective Generation in Blac...

引用

ieee international conference on Systems, Man and Cybernetics

作者： Sha Liu Zhaojuan Yue Jun Li School of Computer Network Information Center Chinese Academy of Sciences and University of Chinese Academy of Sciences Department of Computer Network Information Center Chinese Academy of Sciences

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Large language models (LLMs) exhibit impressive capabilities across various domains in natural language processing. However, LLMs can produce fictional content, which we refer to as hallucinations, and it makes the LLMs unreliable. An important research topic is how to make LLMs accurately express the confidence to their answers, so they can refrain from outputting or regenerate output in cases of low-confidence predictions. It facilitates the application of LLMs in high-stakes areas. Currently, research on eliciting calibrated confidence from LLMs is still insufficient. Additionally, methods for estimating uncertainty in responses based on internal parameters of LLMs become unavailable, as many existing LLMs are black boxes served via APIs. Therefore, we analyze the existing confidence elicitation methods and propose COVO, a new confidence elicitation method that allows the black-box LLMs to output their confidence levels by letting the LLM itself judges whether the answer comes from a reliable source. Our method does not require external knowledge and it has high computational efficiency. Experiments show that COVO achieves better calibration and effectively reduces hallucinations in LLMs through selective generation. Additionally, the confidence scores enhance the reliability of the LLMs' responses.

关键词： Uncertainty Large language models Computational modeling Closed box natural language processing Calibration Reliability Research and development Faces Cybernetics

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 << < 491 492 493 494 495 496 497 498 499 500 > >>

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：