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

1,581 篇 会议
28 册 图书
23 篇 期刊文献

馆藏范围

1,632 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,110 篇 工学
- 1,018 篇 计算机科学与技术...
- 747 篇 软件工程
- 245 篇 信息与通信工程
- 90 篇 电气工程
- 69 篇 控制科学与工程
- 67 篇 生物工程
- 42 篇 化学工程与技术
- 24 篇 仪器科学与技术
- 24 篇 安全科学与工程
- 23 篇 生物医学工程（可授...
- 21 篇 交通运输工程
- 19 篇 机械工程
- 17 篇 网络空间安全
- 16 篇 电子科学与技术（可...
- 15 篇 建筑学
360 篇 管理学
- 288 篇 图书情报与档案管...
- 107 篇 管理科学与工程(可...
- 49 篇 工商管理
343 篇 理学
- 131 篇 数学
- 124 篇 物理学
- 75 篇 生物学
- 55 篇 统计学（可授理学、...
- 48 篇 系统科学
- 41 篇 化学
41 篇 教育学
- 41 篇 教育学
38 篇 法学
- 32 篇 社会学
37 篇 文学
- 31 篇 外国语言文学
29 篇 医学
- 27 篇 临床医学
- 22 篇 基础医学(可授医学...
19 篇 农学
- 17 篇 作物学
14 篇 经济学
4 篇 军事学

主题

183 篇 natural language...
65 篇 natural language...
55 篇 semantics
50 篇 web services
46 篇 sentiment analys...
42 篇 computational mo...
42 篇 accuracy
41 篇 deep learning
40 篇 information retr...
37 篇 data mining
36 篇 classification (...
35 篇 machine learning
35 篇 artificial intel...
33 篇 ontology
31 篇 speech recogniti...
31 篇 training
29 篇 data models
28 篇 semantic web
26 篇 search engines
26 篇 feature extracti...

机构

7 篇 spoken language ...
7 篇 sri lanka instit...
7 篇 faculty of compu...
6 篇 faculty of infor...
4 篇 key laboratory o...
4 篇 fujian yirong in...
4 篇 korea univ nat l...
4 篇 school of inform...
4 篇 international in...
4 篇 information engi...
3 篇 big data and art...
3 篇 graduate school ...
3 篇 national univers...
3 篇 institute of art...
3 篇 carnegie mellon ...
3 篇 school of inform...
3 篇 chitkara univers...
3 篇 beijing univ pos...
3 篇 ipswich
3 篇 department of in...

作者

7 篇 nakagawa seiichi
5 篇 ren fuji
5 篇 zhao tiejun
5 篇 rim hae-chang
4 篇 heyan huang
4 篇 shikano kiyohiro
4 篇 fuji ren
4 篇 liu ting
3 篇 li li
3 篇 rykowski jarogni...
3 篇 nakamura satoshi
3 篇 zheng dequan
3 篇 ngoc thanh nguye...
3 篇 medhat walaa
3 篇 kinshuk
3 篇 bogdan trawiński
3 篇 sun xu
3 篇 mizera-pietraszk...
3 篇 bollegala danush...
3 篇 kitsuregawa masa...

语言

1,592 篇 英文
37 篇 其他
11 篇 中文

检索条件"任意字段=6th International Conference on Advanced Language Processing and Web Information Technology"

共 1632 条记录，以下是21-30 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：

AI-Enabled Program Management System for BTFEC 6th

AI-Enabled Program Management System for BTFEC

引用

6th international conference on Intelligent Communication, Control and Devices, ICICCD 2024

作者： Wangdi, thinley Rani, Seema Amity Institute of Information Technology Amity University Noida Sector-125 U.P. Noida201313 India

ISBN: (纸本)9789819783281

In today’s digital age, the integration of artificial intelligence (AI) systems is essential for businesses to streamline workflows and boost efficiency. the Bhutan Trust Fund for Environmental Conservation depends on manual processes to screen project proposals, leading to significant delays and transparency issues. An automated AI-based system, particularly one that employs natural language processing with Hugging Face transformers, is proposed to mitigate these challenges. this system has been demonstrated to reduce screening time by 70.21% while achieving a content accuracy of 91.8%, marking a substantial improvement in efficiency. However, its limitation lies in not providing automatic scoring for proposals based on predefined criteria, a feature that could minimize human involvement further. By extracting relevant information and presenting condensed concept notes, the system streamlines the decision-making process, significantly reducing the resources required for project proposals screening. this advancement is particularly impactful for Bhutan, a country with a rich ecosystem and a focus on donor agencies such as the Adaptation Fund (AF) and the Green Climate Fund (GCF). Implementing a reliable AI system addresses the concerns of donor agencies and supports their priority of enhancing efficiency and transparency. © the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Vietnamese Text Summarization Using Transformer Approach 6th

Vietnamese Text Summarization Using Transformer Approach

引用

6th international conference on Computational Intelligence in Pattern Recognition, CIPR 2024

作者： Hung, Bui thanh Tan, Phan Nguyen Trong Long, Tran Ho Phi Data Science Laboratory Faculty of Information Technology Industrial University of Ho Chi Minh city Ho Chi Minh Viet Nam

ISBN: (纸本)9789819780891

Text summarization is a crucial aspect of natural language processing, finding widespread applications in various aspects of our lives. Numerous studies have delved into this task, employing diverse approaches ranging from linguistic analysis to machine learning and deep learning methodologies. However, there has been limited exploration of transformer-based models for Vietnamese text summarization. In our research, we leverage transformer models, namely, PhoBERT, BARTpho, and ViT5, to develop and refine effective summarization models. through experimentation on the Vietnews dataset and evaluation using ROUGE metrics, our proposed method demonstrates noteworthy achievements in the realm of Vietnamese text summarization, showcasing its potential for advancing the quality of summarization tasks. © the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： BARTpho BERT Deep learning PhoBERT Text summarization Transformer ViT5

来源：评论

学校读者我要写书评

暂无评论

Development of a Comprehensive technology for Analyzing Data on the Used Car Market 6th

Development of a Comprehensive Technology for Analyzing Data...

引用

6th international conference on communication and computational technologies, ICCCT 2024

作者： Lapina, Maria Kulikova, Svetlana Kireenkov, Vadim Kumar, Sandeep Department of Information Security of Automated Systems North-Caucasus Federal University Stavropol Russia Department of Applied Informatics Moscow Polytechnic University Moscow Russia Kengeri Campus Bengaluru560074 India

ISBN: (纸本)9789819774258

In today's information society, organizations face a huge amount of data that requires analysis and intelligent technologies to make informed decisions. In this paper, the authors consider the problem of analyzing the used car market using big and open data technologies. the used car market has characteristics characterized by heterogeneity and dynamic demand depending on the region. this problem is relevant and important not only for companies involved in producing and selling cars but also for potential buyers. the authors developed a comprehensive data analysis technique based on the Python programming language and the K-means clustering algorithm in the research process. In the article, the authors described a comprehensive technology for analyzing the used car market, including various analysis methods, such as prices, offers, and competition. the proposed comprehensive technology includes various tools and programs for collecting, processing, and analyzing data. these methods can be combined into a single system, providing a more complete picture of the market and making more informed decisions. the structure of the study reflects an independent approach to the topic under study based on open data and research by Russian and foreign scientists. It should be noted that the study is based on a large amount of analytical data obtained from reliable sources and tools that confirm the conclusions formulated in this study. © the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Typeface Identification for English Using Convolutional Neural Networks 6th

Typeface Identification for English Using Convolutional Neur...

引用

6th international conference on Computational Intelligence in Pattern Recognition, CIPR 2024

作者： Suthar, Sanket Katriya, Rajnik Dalwadi, Bijal Changa India Department of Information Technology Birla Vishwakarma Mahavidyalaya Engineering College Gujarat Vallabh Vidyanagar India

ISBN: (纸本)9789819780891

this research is carried out to identify the font of an English language using convolution neural network (CNN);the motivation behind this research is to unravel a realistic designer’s issue. It helps a lot to solve the designer’s problem. Typography is an integral feature of a brand or a creative design. While working as a graphic designer, we would often come across the pain of guessing the font/typeface of the requirement from the given reference by just eye-balling it. the main focus is to develop a model to identify the font which we want to use. But again, you just have to guess it. Sometimes, you don’t even know the typeface to guess in the first place. For this, one just has to take an image of the required typeface sample and feed it to the CNN model and it can effectively recognize the font. It scopes across the platforms of web and Android application and also in future looking forward to iOS application. this study endeavors to employ convolution neural network techniques for the purpose of font identification within the context of the English language. the impetus driving this research lies in the aspiration to address a pertinent concern faced by designers in a realistic manner. the elucidation of font selection significantly contributes to the resolution of design-related challenges. Typography constitutes an indispensable facet of brand identity and creative design. In the capacity of a graphic designer, one frequently encounters the vexing task of discerning the appropriate font or typeface from a given reference solely through visual assessment. the primary emphasis centers on the development of a model capable of accurately identifying the desired font. Nevertheless, this task often entails a degree of conjecture. At times, one may lack even the initial knowledge of the typeface to contemplate. To mitigate this, a simple capture of the requisite typeface sample in image format suffices, subsequently provided as input to the CNN model, thus enablin

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Using LLMs and websearch in Order to Perform Fact Checking on Texts Generated by LLMs 19thth

Using LLMs and Websearch in Order to Perform Fact Checkin...

引用

19th international conference on Computer Aided Systems theory, EUROCAST 2024

作者： Sandler, Simone Krauss, Oliver Stöckl, Andreas University of Applied Sciences Upper Austria Campus Hagenberg Softwarepark 11 Hagenberg4232 Austria Advanced Information Systems and Technology Hagenberg Austria Digital Media Department Hagenberg Austria

ISBN: (纸本)9783031829598

Finding out if a given text contains any false information is not an easy task. On large corpora of data, such as the tremendous amount of texts generated by LLMs, fact checking is a prohibitively expensive task. To address this challenge, we propose a novel approach that combines fact checking by LLMs with web search. this method can be applied not only to single sentences by applying a true, false or unknown label. For whole text paragraphs, a 0..1 score representing the truthfulness from the sentence labels is calculated. the process begins by extracting claims from the text, which is done using GPT3. then, these claims are validated, with Google search results being used to supplement the GPT3 results. When validating our method against a corpus of 122 LLM-generated text samples, we achieve an accuracy of 0.79. To compare our work to other approaches, we also applied our fact checking to the FEVER dataset, achieving an accuracy of 0.78. Which is similar than the current best accuracy of 0.79 on the FEVER dataset. this demonstrates the potential of our proposed approach for automated fact checking. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Classification of Emoji in Text Documents of Users in Social Networks Using Machine Learning

Classification of Emoji in Text Documents of Users in Social...

引用

Mobile Computing and Sustainable Informatics (ICMCSI), international conference on

作者： Dildora Muhamediyeva Nilufar Niyozmatova Nafisakhon Turgunova Sanjar Ungalov Nigora Almuradova Department of Information Technology Software Tashkent University of Information Technologies named after Mukhammad al-Khwarizmi Tashkent city Uzbekistan dept. Digital Technologies and Artificial Intelligence “Tashkent Institute of Irrigation and Agricultural Mechanization Engineers” National Research University Tashkent city Uzbekistan

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

this paper presents a study conducted to classify emotions in social media texts using machine learning. With the rapid increase in the amount of data in digital media, efficient and highly accurate methods for analyzing the emotional content of texts are needed. It is shown that modern deep learning algorithms, natural language processing methods, and feature extraction methods work well for emotion analysis tasks. Data preprocessing methods such as lemmatization, normalization, and text cleaning are given special attention since they are crucial to improving the quality of analysis. the paper also discusses the performance metrics such as precision, recall, and F1-score to demonstrate the advantages of the proposed methods. Furthermore, the current challenges in processing unstructured social media data such as user review analysis and social trend detection are discussed. By leveraging multimodal data and modern context-aware models, the work places special emphasis on improving emotion classification. It is important to leverage advanced machine learning methods to improve text analysis in the dynamic context of social media.

关键词： Sentiment analysis Accuracy Text analysis Social networking (online) Reviews Data preprocessing Market research Transformers Data models Emojis

来源：评论

学校读者我要写书评

暂无评论

Improving Text Classification by Fusing Linguistic and Semantic Features

Improving Text Classification by Fusing Linguistic and Seman...

引用

international conference on Advancements in Computational Sciences (ICACS)

作者： Sarang Shaikh Ehtesham Hashmi Sule Yildirim Yayilgan Mohamed Abomhara Rajendra Akerkar Department of Information Security and Communication Technology (IIK) Norwegian University of Science and Technology (NTNU) Gjøvik Norway Big Data & Emerging Technologies Group Western Norway Research Institute Sogndal Norway

ISBN: (数字)9798331533038

ISBN: (纸本)9798331533045

Text classification remains a fundamental challenge in natural language processing (NLP), with performance often limited by the reliance on either traditional linguistic features or semantic embedding techniques in isolation. this study addresses this limitation by proposing a feature fusion method that integrates traditional linguistic features—such as part-of-speech tags, bag-of-words, TF-IDF, and n-grams—with advanced semantic embedding techniques like word 2 vec and doc 2 vec. the proposed approach aims to capture both syntactic and semantic nuances, enhancing the robustness and accuracy of text classification tasks. To evaluate its effectiveness, the method was applied to five datasets across three critical domains: fake news detection, bloom’s taxonomy classification, and hate speech detection. Key performance metrics, including accuracy, precision, recall, and f1-score, were used to assess the performance of the proposed approach. the experimental results demonstrate that the fusion of linguistic and semantic features consistently outperforms compared to using the each feature type alone, achieving accuracies of $\mathbf{7 9 \%}$ and $\mathbf{6 7 \%}$ for fake news datasets, $38 \%$ and $\mathbf{6 4 \%}$ for bloom’s taxonomy datasets, and $\mathbf{7 0 \%}$ for hate speech datasets. the findings highlight the proposed method’s ability to bridge syntactic and semantic gaps, offering a robust solution for improving text classification performance across diverse NLP applications.

关键词： Accuracy Semantics Text categorization Taxonomy Hate speech Linguistics Syntactics Natural language processing Robustness Fake news

来源：评论

学校读者我要写书评

暂无评论

Towards Completeness: A Generalizable Action Proposal Generator for Zero-Shot Temporal Action Localization 27th

Towards Completeness: A Generalizable Action Proposal Genera...

引用

27th international conference on Pattern Recognition, ICPR 2024

作者： Du, Jia-Run Lin, Kun-Yu Meng, Jingke Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou China Guangdong Province Key Laboratory of Information Security Technology Sun Yat-sen University Guangzhou China

ISBN: (纸本)9783031784439

To address the zero-shot temporal action localization (ZSTAL) task, existing works develop models that are generalizable to detect and classify actions from unseen categories. they typically develop a category-agnostic action detector and combine it with the Contrastive language-Image Pre-training (CLIP) model to solve ZSTAL. However, these methods suffer from incomplete action proposals generated for unseen categories, since they follow a frame-level prediction paradigm and require hand-crafted post-processing to generate action proposals. To address this problem, in this work, we propose a novel model named Generalizable Action Proposal generator (GAP), which can interface seamlessly with CLIP and generate action proposals in a holistic way. Our GAP is built in a query-based architecture and trained with a proposal-level objective, enabling it to estimate proposal completeness and eliminate the hand-crafted post-processing. Based on this architecture, we propose an Action-aware Discrimination loss to enhance the category-agnostic dynamic information of actions. Besides, we introduce a Static-Dynamic Rectifying module that incorporates the generalizable static information from CLIP to refine the predicted proposals, which improves proposal completeness in a generalizable manner. Our experiments show that our GAP achieves state-of-the-art performance on two challenging ZSTAL benchmarks, i.e., thumos14 and ActivityNet1.3. Specifically, our model obtains significant performance improvement over previous works on the two benchmarks, i.e., +3.2% and +3.4% average mAP, respectively. the code is available at https://***/Run542968/GAP. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Text Extraction Using OCR with AWS Textract Service 6th

Enhancing Text Extraction Using OCR with AWS Textract Servic...

引用

6th international conference on advanced Informatics for Computing Research, ICAICR 2023

作者： Bawasker, Aakash Dedania, Yash Karia, Vrushti Bhatt, Nirav Prajapati, Purvi Bhatt, Nikita Chandubhai S. Patel Institue of Technology Charotar University of Science and Technology Gujarat Anand India

ISBN: (纸本)9783031840616

the advent of Optical Character Recognition (OCR) technology has revolutionized document handling for businesses, enabling the conversion of handwritten text into machine-readable content. this project explores Amazon web Services Textract, a cutting-edge OCR service integrating advanced machine learning and deep learning models. Emphasis is placed on dissecting Textract's architecture, features, and practical applications, showcasing its proficiency in extracting text, forms, and tables from diverse document types such as scanned papers, PDFs, and images. Real-world examples demonstrate Textract's seamless integration with document management systems, facilitating data analysis and ***, the article conducts a comprehensive evaluation of the efficiency and accuracy of three OCR solutions: Tesseract (English text), Amazon Textract (Arabic text), and Google DocumentAI (English text). through a comparative analysis of their performance and identification of distinctions in handling common text imperfections, the study aids researchers in informed decision-making for OCR solutions aligned with specific research ***, the project underscores the utility and benefits of incorporating AWS Textract into OCR applications. It highlights how Textract enhances document processing efficiency, improves data accessibility, and ensures compliance adherence. Valuable insights are provided for organizations seeking to optimize document management workflows and leverage OCR capabilities through AWS Textract. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Optical data processing

来源：评论

学校读者我要写书评

暂无评论

Transformer-Based Approaches for Research Paper Categorization

Transformer-Based Approaches for Research Paper Categorizati...

引用

Mobile Computing and Sustainable Informatics (ICMCSI), international conference on

作者： Anguluri Venkata Siva Pavani Sujitha M. Suneetha Mohammad Shameera Department of Information Technology Velagapudi Ramakrishna Siddhartha Engineering College Vijayawada Andhra Pradesh India

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

Efficient classification of research papers is crucial for managing the growing volume of academic literature. Traditional single-label methods fall short in capturing interdisciplinary content, emphasizing the need for multilabel classification. this project's findings address existing limitations and provide a pathway for better knowledge discovery and research efficiency. To overcome these limitations, this study utilized multilabel classification through advanced transformer models such as BERT, RoBERTa, ALBERT, XLNet, DistilBERT, and XLM. Among these, RoBERTa achieved the highest accuracy of 92.76%, followed by ALBERT (92.19%), XLNet (92.17%), BERT (92.06%), and DistilBERT (92.18%). In contrast, XLM lagged significantly with 79.09%. Hybrid transformer models performed worse than standalone ones. this automated classification system enhances the efficiency of literature reviews, making it easier to access relevant research material quickly. Furthermore, by offering a more precise categorization of research articles, it supports academic institutions and researchers in identifying the most pertinent studies across disciplines. this advancement not only improves research productivity but also encourages collaborative efforts by reducing the time spent on manual classification. the ability to accurately classify research papers facilitates more efficient access to relevant information, supporting researchers in their efforts to stay abreast of advancements in their fields. Additionally, the approach has wide applicability, particularly in domains where timely and accurate information is critical, such as healthcare and policy-making.

关键词： Technological innovation Accuracy Collaboration Bidirectional control Multi label classification Transformers Natural language processing Encoding Reliability Systematic literature review

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164页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：