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

26,472 篇 会议
406 册 图书
372 篇 期刊文献
3 篇 学位论文
1 篇 资讯

馆藏范围

27,254 篇 电子文献
2 种 纸本馆藏

日期分布

学科分类号

16,535 篇 工学
- 15,143 篇 计算机科学与技术...
- 11,278 篇 软件工程
- 2,836 篇 信息与通信工程
- 1,806 篇 控制科学与工程
- 1,581 篇 电气工程
- 1,410 篇 生物工程
- 625 篇 生物医学工程（可授...
- 614 篇 化学工程与技术
- 576 篇 机械工程
- 523 篇 电子科学与技术（可...
- 508 篇 网络空间安全
- 397 篇 仪器科学与技术
- 371 篇 光学工程
- 280 篇 安全科学与工程
- 250 篇 交通运输工程
5,110 篇 理学
- 2,102 篇 数学
- 1,481 篇 物理学
- 1,469 篇 生物学
- 784 篇 统计学（可授理学、...
- 620 篇 系统科学
- 617 篇 化学
4,728 篇 管理学
- 3,171 篇 图书情报与档案管...
- 1,833 篇 管理科学与工程(可...
- 769 篇 工商管理
848 篇 医学
- 610 篇 临床医学
- 569 篇 基础医学(可授医学...
- 403 篇 公共卫生与预防医...
681 篇 法学
- 599 篇 社会学
573 篇 文学
- 401 篇 外国语言文学
451 篇 教育学
- 440 篇 教育学
252 篇 经济学
177 篇 农学
19 篇 艺术学
17 篇 军事学
1 篇 哲学

主题

5,711 篇 natural language...
1,715 篇 natural language...
1,552 篇 semantics
1,445 篇 natural language...
1,206 篇 machine learning
1,200 篇 sentiment analys...
1,152 篇 deep learning
978 篇 accuracy
917 篇 training
809 篇 data mining
796 篇 feature extracti...
795 篇 computational mo...
776 篇 artificial intel...
543 篇 knowledge engine...
526 篇 speech recogniti...
514 篇 large language m...
513 篇 transformers
492 篇 data models
466 篇 information retr...
463 篇 support vector m...

机构

58 篇 chitkara univers...
51 篇 lovely professio...
49 篇 school of comput...
33 篇 university of ch...
31 篇 school of comput...
31 篇 centre of interd...
31 篇 xi'an university...
30 篇 school of comput...
28 篇 tsinghua univers...
28 篇 school of comput...
27 篇 school of inform...
26 篇 zhejiang univers...
26 篇 microsoft resear...
24 篇 institute of inf...
24 篇 school of comput...
23 篇 school of inform...
22 篇 department of co...
22 篇 beijing univ pos...
21 篇 college of compu...
21 篇 school of inform...

作者

29 篇 liu yang
27 篇 wan wanggen
20 篇 tiejun zhao
18 篇 zhou guodong
18 篇 wang lei
16 篇 zhang tao
16 篇 zhao hai
16 篇 yang yang
15 篇 sabetzadeh mehrd...
15 篇 lei li
15 篇 liu ying
14 篇 li sheng
14 篇 wu jin
14 篇 zhang lei
14 篇 liu jun
13 篇 li yang
13 篇 li li
13 篇 shanmugasundaram...
13 篇 f. ren
12 篇 li peng

语言

26,244 篇 英文
910 篇 其他
150 篇 中文
5 篇 土耳其文
2 篇 西班牙文
1 篇 法文
1 篇 葡萄牙文

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

共 27256 条记录，以下是311-320 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：

Benchmarking the Performance of Pre-trained LLMs across Urdu NLP Tasks 1

Benchmarking the Performance of Pre-trained LLMs across Urdu...

引用

1st Workshop on Challenges in processing South Asian languages, CHiPSAL 2025, co-located with the 31st international conference on Computational Linguistics, COLING 2025

作者： Tahir, Munief Hassan Shams, Sana Fiaz, Layba Adeeba, Farah Hussain, Sarmad Center for Language Engineering Al-Khawarizmi Institute of Computer Science University of Engineering and Technology Lahore Pakistan

ISBN: (纸本)9798891762015

Large language Models (LLMs) pre-trained on multilingual data have revolutionized natural language processing research, by transitioning from languages and task specific model pipelines to a single model adapted on a variety of tasks. However majority of existing multilingual NLP benchmarks for LLMs provide evaluation data in only few languages with little linguistic diversity. In addition these benchmarks lack quality assessment against the respective state-of the art models. This study presents an in-depth examination of 7 prominent LLMs: GPT-3.5-turbo, Llama 2-7B-Chat, Llama 3.1-8B, Bloomz 3B, Bloomz 7B1, Ministral-8B and Whisper (Large, medium and small variant) across 17 tasks using 22 datasets, 13.8 hours of speech, in a zero-shot setting, and their performance against state-of-the-art (SOTA) models, has been compared and analyzed. Our experiments show that SOTA models currently outperform encoder-decoder models in majority of Urdu NLP tasks under zero-shot settings. However, comparing Llama 3.1-8B over prior version Llama 2-7B-Chat, we can deduce that with improved language coverage, LLMs can surpass these SOTA models. Our results emphasize that models with fewer parameters but richer language-specific data, like Llama 3.1-8B, often outperform larger models with lower language diversity, such as GPT-3.5, in several tasks. © 2025 international Committee on Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

ActivMedica—MRI Brain Image Detection & Captioning with ActivGPT Integration

ActivMedica—MRI Brain Image Detection & Captioning with Act...

引用

international conference on Advances and Applications of Artificial Intelligence and Machine Learning, ICAAAIML 2023

作者： Malayil, Shanid Krishna, P. Sudeep Pattupara, Rabeen Mohamed, P. M. Rishil Faris, Salman Suhair, K. Muhammed Ahmed, P. Jemsheer MEA Engineering College Kerala Perinthelmanna India

ISBN: (纸本)9789819795062

ActivMedica is an innovator in brain tumor diagnosis in the rapidly changing healthcare industry, employing cutting edge AI tools including deep learning and natural language processing (NLP). The shortcomings of existing manual approaches for medical imaging data analysis include difficulty in identifying diverse brain tumors and increasing medical expenditures. Our approach, which at first is based on transfer learning and GIT architecture, uses the GIT convolutional neural network, or CNN, model. A carefully chosen and preprocessed diverse dataset, enhanced for variety and improved by transfer learning from the ImageNet dataset for feature extraction, is essential for successful model training. Using the GIT-based methodology, ActivGPT, an AI chatbot built on OpenAI, enables real-time image analysis through natural language conversations. In addition to brain tumor detection, our research generates brief medical reports based on detected brain tumors, providing medical experts with comprehensive information. Brain tumor diagnosis is ethically improved by ActivMedica, a comprehensive healthcare innovation that combines AI, deep learning, and natural language processing. By doing this, diagnosis accuracy is greatly increased while moral and ethical requirements for AI use in healthcare are maintained. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Applying natural language processing for Detecting Cybersecurity Threats Using Sentimental Analysis Techniques 5th

Applying Natural Language Processing for Detecting Cybersecu...

引用

5th international conference on Data Science, Machine Learning and Applications, ICDSMLA 2023

作者： Mishra, Awakash Ganesh, D. Sharma, Apurva Vignesh, R. Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Karnataka Bangalore India Department of Computer Science and Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Navgaon Manduwala Dehradun India School of Computer Science and Engineering Presidency University Karnataka Bengaluru India

ISBN: (纸本)9789819780426

This paper examines the ability to use herbal language processing (NLP) and Sentiment evaluation strategies to detect cybersecurity threats. We describe the traditional tactics and present-day tendencies in cybersecurity chance detection and discuss the demanding situations the technique confronts. We then present how NLP and Sentiment analysis can resource inside the detection technique, provide examples of ways NLP tools can assist in chance detection, and discuss how NLP can offer beneficial data in phrases of danger detection. We quickly review the strategies for classifying and verifying sentiment from textual statistics. Our findings propose that NLP and mawkish analysis can successfully discover cybersecurity threats and provide treasured insights for additional studies. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Microservices Enterprise Architecture Design with AI-Powered OCR for Improving Fixed Broadband Complaint Handling: A Telco Company Case Study

Microservices Enterprise Architecture Design with AI-Powered...

引用

2025 international conference on Advancement in Data Science, E-learning and Information System, ICADEIS 2025

作者： Puspadarma, Inka Sharatu Mukti, Iqbal Yulizar Ramadani, Luthfi School of Industrial Engineering Telkom University Department of Information System Bandung Indonesia

ISBN: (纸本)9798331513320

The rapid growth of internet users in Indonesia has increased the demand for efficient broadband services. This study proposes a microservices-based enterprise architecture integrating AI-powered Optical Character Recognition (OCR) and natural language processing (NLP) with the Integrated Customer Management System (ICMS) and knowledge Management System (KMS). The architecture addresses challenges arising from Fixed Mobile Convergence (FMC), which introduced complexities in customer service. Automating complaint categorization and solution retrieval through AIbased recommender systems improves accuracy, response times, and operational efficiency, supporting digital transformation goals. The current customer service processes rely heavily on manual intervention, causing inefficiencies like long wait times, especially on digital platforms. Leveraging TOGAF, this research designs a scalable architecture where OCR extracts data from unstructured sources, and NLP enables intelligent categorization and recommendations. Using Design Science Research Methodology, the study demonstrates the architecture's potential to enhance customer experience, streamline workflows, and optimize telco operations in a rapidly evolving technological landscape. © 2025 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Identifying cognitive evaluation statements in reflection documents based on the PDCA cycle 24

Identifying cognitive evaluation statements in reflection do...

引用

8th international conference on natural language processing and Information Retrieval, NLPIR 2024

作者： Abe, Kenta Matsumoto, Takuya Mine, Tsunenori Department of Information Science and Technology Graduate School of Information Science and Electrical Engineering Kyushu University Fukuoka Japan Department of Advanced Information Technology Faculty of Information Science and Electrical Engineering Kyushu University Fukuoka Japan

ISBN: (纸本)9798400717383

The analysis of reflective reports, which are typically produced by trainees during corporate training, allows for the identification of deficiencies in the training program and the evaluation of its educational efficacy. Furthermore, the evaluation of individual trainees' cognitive state, including their self-assessment of their performance during the training period, provides insight into their mental state and enables the discernment of their distinctive abilities and characteristics. The present study is concerned with the analysis of reflective reports produced by trainees during corporate training. To date, no research has been conducted on the cognitive state of individuals based on the PDCA cycle, which is widely used in business situations. In this study, we propose a method for determining whether a reflective report includes a description of one's evaluation in the "Check"state of the PDCA cycle when recognizing trainees' cognitive states. To this end, we investigate the impact of supervised contrastive learning on accuracy and the effect of sentence segmentation on prediction performance. To validate the proposed method, we conducted an experiment using the trainees' reflection reports collected in real training. The results demonstrated that the proposed method exhibited the highest accuracy compared to the baseline models, achieving 0.846 on the Macro-F1 score when the sentence was segmented. © 2024 Copyright held by the owner/author(s).

关键词： Personnel training

来源：评论

学校读者我要写书评

暂无评论

Adaptive Large language Models via Attention Shortcuts

Adaptive Large Language Models via Attention Shortcuts

引用

2025 IEEE international conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Verma, Prateek Pilanci, Mert Department of Electrical Engineering Stanford University StanfordCA94305 United States

ISBN: (纸本)9798350368741

Transformer architectures are the backbone of the modern AI revolution. However, these models simply stack the same blocks in dozens of layers and process information sequentially from one block to another. In this paper, we propose to challenge this and introduce adaptive computations for LLM-like setups, which allow the final layer to attend to all of the intermediate layers as it deems fit through the attention mechanism, thereby introducing computational attention shortcuts. These shortcuts can thus make the architecture depth and context adaptive. We showcase four different datasets, namely acoustic tokens, natural language, and symbolic music, and we achieve superior performance for GPT-like architecture. We give evidence via attention maps that the models learn complex dependencies across layers that are adaptive in context and depth depending on the input tokens. © 2025 IEEE.

关键词： Adaptive Models Attention LLMs

来源：评论

学校读者我要写书评

暂无评论

A comparative study of One-Hot,TF-IDF, and Word2Vec for Classifying Illegal Advertising Texts 24

A comparative study of One-Hot,TF-IDF, and Word2Vec for Clas...

引用

8th international conference on natural language processing and Information Retrieval, NLPIR 2024

作者： Zhang, Yuedan He, Lingmin Zhang, Yunpeng Zhao, Panzhi Zhang, Bole Cheng, Fang Liangxin Honors College College of Information Engineering China Jiliang University Zhejiang Hangzhou China Department of Computer Science College of Information Engineering Big Data Laboratory China Jiliang University Zhejiang Hangzhou China College of Information Engineering China Jiliang University Zhejiang Hangzhou China

ISBN: (纸本)9798400717383

With the vigorous development of the Internet advertising industry, the increasing number of illegal advertisements has brought misleading information and risks to consumers, while also posing challenges to market order. Therefore, how to efficiently and accurately identify and classify illegal advertisements has become an urgent issue that needs to be addressed. This paper delves into this topic, starting from the traditional one-hot encoding approach and progressing to the study of the TF-IDF method. However, when the text data vectorized by these methods is fed into the Support Vector Machine (SVM) model, it becomes evident that both approaches lack semantic information, which is crucial for identifying illegal advertisement texts. To address this limitation, this paper subsequently introduces the study of Word2Vec and employs grid search to find the optimal parameters for the SVM model. This enhanced approach significantly improves the accuracy and efficiency of illegal advertisement recognition, raising the model's accuracy from the initial 69.8 percent to 88.3 percent, thereby contributing to the creation of a healthier and more transparent advertising environment. © 2024 Copyright held by the owner/author(s).

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Robust Semantic Communications for Speech Transmission

Robust Semantic Communications for Speech Transmission

引用

2025 IEEE international conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Weng, Zhenzi Qin, Zhijin Li, Geoffrey Ye Department of Electrical and Electronic Engineering Imperial College London London United Kingdom Department of Electronic Engineering Tsinghua University Beijing China

ISBN: (纸本)9798350368741

In this paper, we propose a robust semantic communication system for speech transmission, named Ross-S2T, by delivering the essential semantic information. Specifically, we consider the speech-to-text translation (S2TT) as the transmission goal. First, a new deep semantic encoder is developed to convert speech in the source language to textual features associated with the target language, facilitating the end-to-end semantic exchange to perform the S2TT task and reducing the transmission data without performance degradation. To mitigate semantic impairments inherent in the corrupted speech, a novel generative adversarial network (GAN)-enabled deep semantic compensator is established to estimate the lost semantic information within the speech and extract deep semantic features simultaneously, which enables robust semantic transmission for corrupted speech. Furthermore, a semantic probe-aided compensator is devised to enhance the semantic fidelity of recovered semantic features and improve the understandability of the target text. According to simulation results, the proposed Ross-S2T exhibits superior S2TT performance compared to conventional approaches and high robustness against semantic impairments. © 2025 IEEE.

关键词： Deep learning generative adversarial network semantic communications speech-to-text translation

来源：评论

学校读者我要写书评

暂无评论

language-Based Colorization with Sparse Attention and Multi-scale Cross-Modal Semantic Alignment 24th

Language-Based Colorization with Sparse Attention and Mult...

引用

24th international conference on Algorithms and Architectures for Parallel processing, ICA3PP 2024

作者： Zhang, Ying Gao, Yutong Liu, Xuan Zhang, Lefeng Liu, Xianggan Jiang, Shan Ethnic Language Intelligent Analysis and Security Governance Minzu University of China Beijing China Faculty of Data Science City university of Macau China Natural Language Processing and Knowledge Graph Lab Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9789819615476

language-based colorization generates realistic and aesthetically appealing colors by leveraging the guidance of intuitive and user-friendly natural language descriptions. Previous methods in language-based image colorization face several significant challenges, including limited color richness, color bleeding, color distortions, and inconsistent color styles. These issues often arise due to the reliance on dense attention mechanisms, which can lead to an overemphasis on global features at the expense of local details. Furthermore, many feature fusion modules for text and grayscale images are not designed to achieve adequate alignment of the diverse feature representations, resulting in suboptimal colorization outcomes. In this paper, we explore a novel module that employs sparse attention to mitigate the issue of color bleeding and limited colorfulness in image colorization tasks. By introducing a sparse attention mechanism, our method enables more flexible allocation of computational resources with a focus on color awareness. Additionally, we propose a module that effectively aligns grayscale images with color descriptions, thereby improving the consistency and quality of the colorization results. This module leverages the synergy between image features and language descriptions to solve long-standing issues like color bleeding. Empirical evaluations demonstrate that our approach surpasses recent state-of-the-art techniques in both automatic and language-based colorization tasks, validating the effectiveness and robustness of our proposed method in generating high-quality, visually appealing colorized images. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis on Telugu Text Translated from English using NLP and ML 3

Sentiment Analysis on Telugu Text Translated from English us...

引用

3rd international conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Karthik, A.H.N. Aneesh, Ch. Saumik, Gembali Varun, K.V.V. Kavitha, C.R. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798331527549

This research study mainly uses natural language processing (NLP) and Machine Learning. The general approach of this tool is to apply sentiment analysis in Telugu Text translated from English. The Technique contains many preprocessing steps, for example, tokenization of texts, normalization and noise removal for translating English text into Telugu which then will use machine translation services. It is followed by sentiment analysis of the statement using NLP models and machine learning approaches and classified them as;positive, negative, or neutral. The main objective of this study is to enhance the accuracy of sentiment identification with non-English language. Environments and also to develop rigorous sentiment analysis tools optimized for Telugu, which are designed as to the language and context-related difficulties to be taken into account. Additionally, the research examines analyses the impact of bilingual datasets on increasing translation accuracy and sentiment classification, while also tackling the obstacles given by idiomatic idioms and context-specific interpretations in Telugu language. © 2025 IEEE.

关键词： Machine translation

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 << < 28 29 30 31 32 33 34 35 36 37 > >>

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：