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

14,558 篇 会议
663 篇 期刊文献
101 册 图书
40 篇 学位论文
1 篇 科技报告

馆藏范围

15,362 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

11,025 篇 工学
- 10,359 篇 计算机科学与技术...
- 5,436 篇 软件工程
- 1,474 篇 信息与通信工程
- 963 篇 电气工程
- 925 篇 控制科学与工程
- 446 篇 生物工程
- 223 篇 网络空间安全
- 220 篇 化学工程与技术
- 187 篇 机械工程
- 175 篇 生物医学工程（可授...
- 144 篇 电子科学与技术（可...
- 102 篇 仪器科学与技术
- 99 篇 安全科学与工程
2,494 篇 理学
- 1,163 篇 数学
- 655 篇 物理学
- 520 篇 生物学
- 395 篇 统计学（可授理学、...
- 241 篇 系统科学
- 235 篇 化学
2,427 篇 管理学
- 1,755 篇 图书情报与档案管...
- 760 篇 管理科学与工程(可...
- 241 篇 工商管理
- 106 篇 公共管理
1,761 篇 文学
- 1,709 篇 外国语言文学
- 184 篇 中国语言文学
514 篇 医学
- 303 篇 临床医学
- 284 篇 基础医学(可授医学...
- 113 篇 公共卫生与预防医...
278 篇 法学
- 249 篇 社会学
238 篇 教育学
- 225 篇 教育学
100 篇 农学
98 篇 经济学
9 篇 艺术学
7 篇 哲学
4 篇 军事学

主题

3,557 篇 natural language...
1,786 篇 natural language...
953 篇 computational li...
740 篇 semantics
682 篇 machine learning
613 篇 deep learning
520 篇 natural language...
352 篇 computational mo...
343 篇 accuracy
339 篇 training
335 篇 large language m...
335 篇 sentiment analys...
325 篇 feature extracti...
312 篇 data mining
290 篇 speech processin...
260 篇 speech recogniti...
256 篇 transformers
236 篇 neural networks
218 篇 iterative method...
212 篇 support vector m...

机构

85 篇 carnegie mellon ...
52 篇 university of ch...
46 篇 tsinghua univers...
45 篇 carnegie mellon ...
43 篇 zhejiang univers...
43 篇 national univers...
38 篇 nanyang technolo...
36 篇 university of sc...
36 篇 university of wa...
35 篇 univ chinese aca...
34 篇 carnegie mellon ...
33 篇 gaoling school o...
33 篇 stanford univers...
32 篇 school of artifi...
32 篇 alibaba grp peop...
29 篇 tsinghua univ de...
28 篇 harbin institute...
26 篇 microsoft resear...
26 篇 language technol...
26 篇 peking universit...

作者

55 篇 zhou guodong
50 篇 neubig graham
46 篇 liu yang
39 篇 sun maosong
36 篇 zhang min
34 篇 liu qun
33 篇 smith noah a.
28 篇 schütze hinrich
27 篇 liu zhiyuan
26 篇 wen ji-rong
26 篇 lapata mirella
24 篇 chang kai-wei
23 篇 zhou jie
23 篇 yang diyi
23 篇 zhao hai
23 篇 zhao wayne xin
21 篇 chua tat-seng
20 篇 dredze mark
18 篇 biemann chris
18 篇 fung pascale

语言

14,282 篇 英文
966 篇 其他
113 篇 中文
18 篇 法文
14 篇 土耳其文
2 篇 德文
2 篇 西班牙文
2 篇 俄文

检索条件"任意字段=Conference on empirical methods in natural language processing"

共 15363 条记录，以下是4581-4590 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：

SA²VP: Spatially Aligned-and-Adapted Visual Prompt 38

SA<SUP>2</SUP>VP: Spatially Aligned-and-Adapted Visual Promp...

引用

38th AAAI conference on Artificial Intelligence (AAAI) / 36th conference on Innovative Applications of Artificial Intelligence / 14th Symposium on Educational Advances in Artificial Intelligence

作者： Pei, Wenjie Xia, Tongqi Chen, Fanglin Li, Jinsong Tian, Jiandong Lu, Guangming Harbin Inst Technol Shenzhen Peoples R China Shenzhen Jiang Associates Creat Design Co Ltd Shenzhen Peoples R China Chinese Acad Sci Shenyang Inst Automat Shenyang Peoples R China

ISBN: (纸本)1577358872

As a prominent parameter-efficient fine-tuning technique in NLP, prompt tuning is being explored its potential in computer vision. Typical methods for visual prompt tuning follow the sequential modeling paradigm stemming from NLP, which represents an input image as a flattened sequence of token embeddings and then learns a set of unordered parameterized tokens prefixed to the sequence representation as the visual prompts for task adaptation of large vision models. While such sequential modeling paradigm of visual prompt has shown great promise, there are two potential limitations. First, the learned visual prompts cannot model the underlying spatial relations in the input image, which is crucial for image encoding. Second, since all prompt tokens play the same role of prompting for all image tokens without distinction, it lacks the fine-grained prompting capability, i. e., individual prompting for different image tokens. In this work, we propose the Spatially Aligned-and-Adapted Visual Prompt model (SA2VP), which learns a two-dimensional prompt token map with equal (or scaled) size to the image token map, thereby being able to spatially align with the image map. Each prompt token is designated to prompt knowledge only for the spatially corresponding image tokens. As a result, our model can conduct individual prompting for different image tokens in a fine-grained manner. Moreover, benefiting from the capability of preserving the spatial structure by the learned prompt token map, our SA2VP is able to model the spatial relations in the input image, leading to more effective prompting. Extensive experiments on three challenging benchmarks for image classification demonstrate the superiority of our model over other state-of-the-art methods for visual prompt tuning. Code is available at https://***/tommy-xq/SA2VP.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

NLP based Text Summarization of Fintech RFPs 2

NLP based Text Summarization of Fintech RFPs

引用

2nd International conference on Sustainable Computing and Data Communication Systems, ICSCDS 2023

作者： Patil, Krutika Badamikar, Medha Sonawane, Sheetal Pune Institute of Computer Technology Department of Computer Engineering Pune India

ISBN: (纸本)9781665491990

In today's day and age, where huge quantities of textual data are generated every second, it has become difficult to keep ourselves abreast with new information. Documents in the financial sector tell a quantitative story. The qualitative or language content that accompanies financial statements is an essential component of the information set used by financial market participants for monitoring and stewardship. This necessitates the development of efficient technological methods for leveraging the existence of these massive amounts of textual data. Reading financial documents such as annual reports is extremely time-consuming and thus corporations have to allocate precious human capital to understand, analyze and derive insight from these reports. As a result, automatic summarization techniques can make this task simpler by enabling access to a smaller but informative portion of a given document. In this work, a system utilizing NLP techniques for summarizing financial documents based on queries provided by the user, is presented. This system overcomes the challenges posed by existing section-based summarization models. As machine learning methods have proven to be effective on downstream tasks such as text summarization, the intent of this work is to take advantage of these methods for effective extractive summarization and generate human-like summaries. The proposed model categorizes phrases according to their relevance by leveraging the strength of unsupervised clustering approaches, and it gets a ROUGE-1 score of 46%. © 2023 IEEE.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

CEEMDAN–WTD Denoising Method for Enhanced Magnetic Memory Detection Signal of Defects 16

CEEMDAN–WTD Denoising Method for Enhanced Magnetic Memory D...

引用

16th International conference on Signal processing Systems, ICSPS 2024

作者： Ji, Shouhong Yan, Jie Liu, Yang He, Guojun National Pipeline Network Group Zhejiang Natural Gas Pipeline Network Co. Ltd Hangzhou310000 China

ISBN: (纸本)9781510689251

During the enhanced magnetic memory detection of defects, many interference signals appear in the detection signal, which makes it difficult to accurately extract the characteristics of the defect signals and significantly affects the detection effectiveness. When the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) is employed independently for signal denoising, the noise and feature signals of the transition components will be retained or removed. When wavelet threshold denoising (WTD) is employed independently for signal denoising, the denoising effect is restricted because of the difficulty in determining the number of decomposition layers m and wavelet basis function. To solve these problems, a denoising method for enhanced magnetic memory detection signals based on CEEMDAN and WTD, called CEEMDAN–WTD, is proposed in the paper. Firstly, the correlation coefficient R of the signal components obtained by performing decomposition with the CEEMDAN method is calculated, and the signal components are divided into noise-dominant components, transition components, and useful signal components based on the R. Subsequently, WTD is employed to perform denoising on the two order signal components before and after transition components IMF(k − 2) ~ IMF(k + 2) obtained from the CEEMDAN method. Ultimately, the denoising components IMF(k − 2) ~ IMF(k + 2) and high-order useful signal components obtained by the CEEMDAN method are selected for signal reconstruction to obtain a denoised signal. To validate the effectiveness of the proposed method, the denoising effects of the CEEMDAN–WTD, CEEMDAN, and WTD methods were compared based on the signal-to-noise ratio (SNR). The comparison indicated that the CEEMDAN–WTD denoising method significantly enhanced the denoising effect, and the SNRs of the components of the magnetic field signal could be increased by up to 8.24% and 45.88%, respectively, indicating that the CEEMDAN-WTD denoising method is relativel

关键词： Wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

Edit-based adversarial text attack 24

Edit-based adversarial text attack

引用

5th International conference on Computer Information and Big Data Applications, CIBDA 2024

作者： Li, Ang Yang, Xinghao Liu, Weifeng QingDao266580 China

ISBN: (纸本)9798400718106

Adversarial text attack is an effective way to investigate the vulnerability. Recently, several text attack strategies have been proposed. However, the samples produced through word-level and character-level attacks exhibit a certain uniformity, offering limited variation in their structure. Sentence-level attack methods usually generate human unreadable sentences, or are hard to yield a high attack success rate (ASR). In this paper, we propose the Edit-based adversarial text attack (EA). Specifically, we employ three techniques: changing the order, adding definitions, or inserting phrases to manipulate the sentence. To evaluate the effectiveness of the proposed EA method, we conduct extensive experiments on three datasets by attacking several popular models, such as BERT, DistilBERT, CNN, and LSTM etc. Experimental results show that EA enhances the ASR performance compared to word-level and sentence-level baselines while preserving high semantic similarity and incurring minimal perturbation costs. Additionally, EA is helpful in improving the robustness of modern NLP models by retraining. © 2024 ACM.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Recognition of classical visual works appellations 29

Recognition of classical visual works appellations

引用

29e conference sur le Traitement Automatique des Langues Naturelles, TALN 2022 - 29th conference on natural language processing, TALN 2022

作者： Lessieux, Aurore Eshkol-Taravella, Iris Szabados, Anne-Violaine Nazarian, Marlene UMR7114 Université Paris Nanterre France UMR7041 LIMC France

The multidisciplinary project MonumenTAL aims to identify and list the names of works of classical visual works of art in French texts published from the 18th to the 21st century using NLP methods. It is based on a close collaboration between art historians (LIMC), NLP researchers (MoDyCo) and librarians (BnF). The process includes several stages: selection of the study corpus, elaboration of a typology of appellations, constitution of a corpus annotated by experts in the field and development of a tool for automatic recognition of appellations based on symbolic methods. © 2022 Traitement Automatique des Langues Naturelles, TALN 2022 - Actes de la 29e conference sur le Traitement Automatique des Langues Naturelles, Atelier TAL et Humanites Numeriques, TAL-HN 2022. All rights reserved.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

2nd International conference on Robotics and Artificial Intelligence, RoAI 2021

2nd International Conference on Robotics and Artificial Inte...

引用

2nd International conference on Robotics and Artificial Intelligence, RoAI 2021

The proceedings contain 14 papers. The topics discussed include: AIR TOUCH: human machine interface using electromyography signals;robotic arm for brake performance testing;the fuzzy-based systems in the communication between a human and a humanoid robot;rocker-bogie stair climbing robot;the design of an intelligent chatbot with natural language processing capabilities to support learners;the empirical analysis for effective prediction of crop price using neuro evolutionary algorithm based on machine learning approach;Azerbaijani sign language recognition using machine learning approach;DograNet – a comprehensive offline Dogra handwriting character dataset;congestion-free routing based on a hybrid meta-heuristic algorithm to provide an effective routing protocol by analyzing the significant impacts of QoS parameters in a dynamic VANET environment;and face recognition using nearest neighbor and nearest mean classification framework: empirical analysis, conclusions and future directions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

natural language processing in Strategic Planning Analysis

Natural Language Processing in Strategic Planning Analysis

引用

International conference on Computational and Characterization Techniques in Engineering & Sciences (CCTES)

作者： Keerthi Shetty Swati Tyagi Anupama Jha D N Murali Krishna Rao J.R. Arunkumar Lakshmikanth R Department of MCA NMAM Institute of Technology Nitte (Deemed to be University) Udupi India University of Delaware DE USA VSIT Vivekananda Institute of Professional Studies Guru Gobind Singh IP University Delhi Electrical and Electronics Engineering JNTUH Department of Computer Science and Engineering Modern Institute of Technology and Research Centre Alwar Rajasthan Department of Management Studies Adithya Institute of Technology Coimbatore India

ISBN: (数字)9798350364699

ISBN: (纸本)9798350364705

natural language processing (NLP) has emerged as a game-changing technique in the field of strategic planning analysis. This development represents a significant step forward. Improved methods for obtaining meaningful insights from massive amounts of textual data are made available by natural language processing (NLP). According to the findings of this research project, the application of natural language processing (NLP) technology to enhance the strategic planning processes that are carried out within enterprises is being investigated. natural language processing (NLP) approaches, such as semantic analysis, sentiment identification, and topic modeling, can be utilized to acquire a more in-depth grasp of market tendencies, consumer feedback, and internal communications. This can be accomplished by utilizing these techniques. The study demonstrates how natural language processing (NLP) can facilitate the discovery of emergent patterns, simplify the understanding of data, and encourage decision-making that is driven by data. There are a great number of case studies that demonstrate the incorporation of natural language processing (NLP) into strategic frameworks. These case studies show improvements in the accuracy of forecasting, risk management, and competitive analysis processes. The findings of this study demonstrate the potential for natural language processing (NLP) to revolutionize strategic planning by providing a more nuanced and comprehensive evaluation of qualitative data. This, in turn, will ultimately result in strategic decisions that are more informed and agile.

关键词： Analytical models Semantics Decision making Transforms Organizations Strategic planning Market research natural language processing Risk management Forecasting

来源：评论

学校读者我要写书评

暂无评论

Enhancing Axial Compressor Stall Warning with Time-Frequency Generative Adversarial Networks: A Novel Approach in Advanced Signal processing 36

Enhancing Axial Compressor Stall Warning with Time-Frequency...

引用

36th Chinese Control and Decision conference (CCDC)

作者： Qiu, Xiaohong Wu, Jiawei Guo, Chaochao Wu, Xin Jiangxi Univ Sci & Technol Sch Software Engn Nanchang 330013 Jiangxi Peoples R China

ISBN: (纸本)9798350387780;9798350387797

In the domain of axial compressor stall warnings, existing methods largely focus on time or frequency domain analyses, leading to excessive dependence on signal quality, increased rates of false alarms, and merely partial extraction of characteristics signaling an imminent stall. To overcome these challenges, it is imperative to develop a model that can swiftly and effectively identify early anomalies that signal an impending stall within a complex time series. Such a model ideally enables a thorough extraction of early stall indicators. This paper introduces the Time-Frequency Generative Adversarial Networks (TFGAN), representing the inaugural innovative fusion of adversarial training with time-frequency analysis. Utilizing the Wigner-Ville distribution function, the TFGAN achieves enhanced fidelity in information exchange between the time and frequency domains. Through adversarial training, the TFGAN discerns the characteristic states of various sequences following time-frequency analysis, precisely identifying conditions that suggest pre-stall precursors, thus fulfilling the goal of accurate stall warnings. empirical results show that the TFGAN model effectively captures the complex time-frequency relationships present in signal data, facilitating the identification of subtle temporal changes across different features. This enables the swift extraction of stall characteristics, anomaly detection, and stall prediction within complex time series data. When compared with a range of generative models, the proposed method markedly outperforms experimental benchmarks in generative accuracy and predictive capability, as demonstrated by both qualitative and quantitative analyses.

关键词： Adversarial training Axial compressor Fault monitoring Time-frequency analysis

来源：评论

学校读者我要写书评

暂无评论

NovoBench: Benchmarking Deep Learning-based De Novo Peptide Sequencing methods in Proteomics 38

NovoBench: Benchmarking Deep Learning-based De Novo Peptide ...

引用

38th conference on Neural Information processing Systems, NeurIPS 2024

作者： Zhou, Jingbo Chen, Shaorong Xia, Jun Liu, Sizhe Ling, Tianze Du, Wenjie Liu, Yue Yin, Jianwei Li, Stan Z. Zhejiang University China Westlake University China University of Southern California United States Tsinghua Univerisity China

Tandem mass spectrometry has played a pivotal role in advancing proteomics, enabling the high-throughput analysis of protein composition in biological tissues. Many deep learning methods have been developed for de novo peptide sequencing task, i.e., predicting the peptide sequence for the observed mass spectrum. However, two key challenges seriously hinder the further advancement of this important task. Firstly, since there is no consensus for the evaluation datasets, the empirical results in different research papers are often not comparable, leading to unfair comparison. Secondly, the current methods are usually limited to amino acid-level or peptide-level precision and recall metrics. In this work, we present the first unified benchmark NovoBench for de novo peptide sequencing, which comprises diverse mass spectrum data, integrated models, and comprehensive evaluation metrics. Recent impressive methods, including DeepNovo, PointNovo, Casanovo, InstaNovo, AdaNovo and π-HelixNovo are integrated into our framework. In addition to amino acid-level and peptide-level precision and recall, we evaluate the models' performance in terms of identifying post-tranlational modifications (PTMs), efficiency and robustness to peptide length, noise peaks and missing fragment ratio, which are important influencing factors while seldom be considered. Leveraging this benchmark, we conduct a large-scale study of current methods, report many insightful findings that open up new possibilities for future development. The code is available at https://***/Westlake-OmicsAI/NovoBench. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recognition Model of Transfer Learning for the Marathi Named Entity 4

Recognition Model of Transfer Learning for the Marathi Named...

引用

4th International conference on Emerging Research in Electronics, Computer Science and Technology, ICERECT 2022

作者： Gokul Rajan, V. Arvind, K.S. Galgotias University Department of Computer Science and Engineering Greater Noida India Jain University Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9781665456357

Artificial intelligence (AI) has a subfield called information extraction (IE). In unstructured information sources, IE recognises data that complies to specified semantics, such as persons, places, etc. A important task of IE and natural language processing is the recognition of named entities (NEs) from computer-readable natural language material (NLP). Extraction of named entities (NEs) is a crucial stage in the processing of unstructured input. Computationally, unstructured data is opaque. Data that can be processed by computers must be computationally transparent. To make raw data easier for computers to process, IE gives it meaning. For the purpose of extracting entities from text, numerous alternative methods are used. In this piece, Marathi, a language of India that is widely spoken in Maharashtra state, is the subject of our attention. Since Marathi has little resources, there aren't many relevant NER materials available. We introduce L3Cube-MahaNER, the first significant Marathi named entity recognition dataset that adheres to the gold standard. We also go over the manual annotation procedures that were used. We compare the dataset using a variety of CNN, LSTM, and Transformer-based models, including mBERT, XLM-RoBERTa, IndicBERT, MahaBERT, etc. © 2022 IEEE.

关键词： natural language processing systems

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 << < 455 456 457 458 459 460 461 462 463 464 > >>

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：