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

680 篇 会议
5 册 图书
3 篇 期刊文献

馆藏范围

688 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

505 篇 工学
- 497 篇 计算机科学与技术...
- 303 篇 软件工程
- 96 篇 信息与通信工程
- 75 篇 生物工程
- 44 篇 控制科学与工程
- 30 篇 电气工程
- 27 篇 安全科学与工程
- 26 篇 网络空间安全
- 23 篇 交通运输工程
- 18 篇 生物医学工程（可授...
- 15 篇 化学工程与技术
- 9 篇 仪器科学与技术
- 8 篇 机械工程
159 篇 理学
- 80 篇 生物学
- 59 篇 数学
- 35 篇 物理学
- 31 篇 统计学（可授理学、...
- 18 篇 系统科学
- 17 篇 化学
130 篇 管理学
- 98 篇 图书情报与档案管...
- 48 篇 管理科学与工程(可...
- 21 篇 工商管理
34 篇 文学
- 32 篇 外国语言文学
25 篇 医学
- 16 篇 基础医学(可授医学...
- 14 篇 临床医学
- 7 篇 药学(可授医学、理...
- 6 篇 特种医学
18 篇 法学
- 18 篇 社会学
13 篇 教育学
- 13 篇 教育学
7 篇 经济学
- 7 篇 应用经济学
3 篇 农学

主题

136 篇 natural language...
123 篇 machine learning
79 篇 deep learning
69 篇 sentiment analys...
34 篇 natural language...
20 篇 accuracy
20 篇 machine learning...
18 篇 support vector m...
18 篇 adversarial mach...
17 篇 learning systems
15 篇 nlp
15 篇 feature extracti...
14 篇 analytical model...
14 篇 neural machine t...
13 篇 machine translat...
13 篇 learning algorit...
13 篇 data models
12 篇 computational mo...
12 篇 social networkin...
12 篇 training

机构

4 篇 medical technica...
4 篇 carnegie mellon ...
4 篇 national univers...
4 篇 the islamic univ...
4 篇 school of inform...
4 篇 altoosi universi...
3 篇 xian univ posts ...
3 篇 alibaba grp peop...
3 篇 tianjin universi...
3 篇 the 6th research...
3 篇 faculty of compu...
2 篇 ecloud system an...
2 篇 western sydney u...
2 篇 science and tech...
2 篇 soochow univ sch...
2 篇 college of mlt a...
2 篇 tsinghua univ de...
2 篇 alexandria unive...
2 篇 machine learning...
2 篇 school of electr...

作者

4 篇 li lei
4 篇 wang mingxuan
3 篇 wu liwei
3 篇 gu jiatao
3 篇 nagarhalli tatwa...
2 篇 hong yu
2 篇 zhou guodong
2 篇 yang xinghao
2 篇 valencia-garcia ...
2 篇 diab mona
2 篇 qazi atika
2 篇 manoharan geetha
2 篇 sabetzadeh mehrd...
2 篇 reich christoph
2 篇 li ao
2 篇 sun maosong
2 篇 wei liu
2 篇 liu yang
2 篇 chiraz ben othma...
2 篇 wang cheng

语言

668 篇 英文
18 篇 其他
5 篇 中文

检索条件"任意字段=6th International Conference on Machine Learning and Natural Language Processing, MLNLP 2023"

共 688 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：

Continual learning with Confidence-based Multi-teacher Knowledge Distillation for Neural machine Translation 6

Continual Learning with Confidence-based Multi-teacher Knowl...

引用

6th international conference on natural language processing (ICNLP)

作者： Guo, Jiahua Liang, Yunlong Xu, Jinan Beijing Jiaotong Univ Beijing Peoples R China

ISBN: (纸本)9798350349122;9798350349115

Continual learning is widely used in practical applications of neural machine translation, which aims to not only achieve good performance on new domains but also preserve the knowledge of previously learned domains. However, the existing methods for continual learning usually suffer from catastrophic forgetting in the multi-domain continuous learning scenario. When the model is trained on multiple diverse domains one by one, the performance on the previous domains will decrease drastically. In this work, we propose a multi-teacher knowledge distillation technique to alleviate the problem of catastrophic forgetting systematically. Firstly, we adopted the multi-teacher knowledge method, where models from previous training stages are used as teachers. Secondly, to further effectively enhance the performance of previous domains, we propose a confidence-based integration mechanism in which multiple teachers are integrated with sample-adaptive weights based on their performance. We conduct experiments in the settings of multi-domain continual learning, where the pre-trained model is transferred to five diverse domains (IT, Law, Medical, Subtitles, Koran) sequentially. Experimental results show that the proposed method achieves superior performance compared to several strong baseline methods.

关键词： neural machine translation continual learning knowledge distillation

来源：评论

学校读者我要写书评

暂无评论

Intelligent Fault Diagnosis of Rolling Bearing Based on Deep Transfer learning 6

Intelligent Fault Diagnosis of Rolling Bearing Based on Deep...

引用

6th international conference on natural language processing (ICNLP)

作者： Fang, Lei Liu, Yao Li, Xuan Chang, Jiantao Xian Univ Posts & Telecommun Sch Commun & Informat Engn Xian Peoples R China Xidian Univ Sch Mechanoelect Engn Xian Peoples R China

ISBN: (纸本)9798350349122;9798350349115

Aiming at the problem of poor effect of traditional machine learning and deep learning fault diagnosis methods in actual industrial scenarios, which is caused by the data distribution difference due to the change of equipment working conditions, an intelligent fault diagnosis method for rolling bearing based on deep transfer learning is proposed. Firstly, the original time domain vibration signal is preprocessed using a sliding window to construct a sample dataset;Secondly, a Deep Residual Shrinkage Network (DRSN) is used to filter out the sample noise and automatically extract the data features;then, the marginal distribution and conditional distribution between the domains are aligned by Maximum Mean Discrepancy (MMD) and Local Maximum Mean Discrepancy (LMMD), and the difference of data feature distribution between different working conditions is weakened;Finally, experimental verification is carried out on two multi-condition rolling bearing datasets. the results show that the proposed method has a good fault diagnosis capability under variable working conditions.

关键词： rolling bearing fault diagnosis deep residual shrinkage network deep transfer learning unsupervised domain adaptation

来源：评论

学校读者我要写书评

暂无评论

Multi-view Representation learning for Histologic Subtype Classification of Lung Cancer 6

Multi-view Representation Learning for Histologic Subtype Cl...

引用

6th international conference on machine learning and natural language processing, mlnlp 2023

作者： Gao, Ziyu Luo, Yin Xu, Ying Li, Ao Wang, Minghui School of Information Science and Technology University of Science and Technology of China China

ISBN: (纸本)9798400709241

It is crucial to accurately discerning adenocarcinoma (ADC) from squamous cell carcinoma (SCC) histological subtypes utilizing computed tomography (CT) scans for guiding treatment decisions among individuals with non-small cell lung cancer (NSCLC). While the existing multi-view deep learning methods have shown promise in this domain, they usually struggle to mine common information efficiently due to the presence of intra-view interference, resulting in limited performance. In this research, we introduce an efficient multi-view representation learning technique to eliminate interference, thus obtaining higher-quality multi-view representations. Our approach involves the implementation of attention-based representation decoupling to project axial, coronal and sagittal views into both view-invariant and view-specific subspaces, respectively. Moreover, we employ a novel adversarial loss to ensure that the learned peculiar representations are not tailored to histological subtype classification, thereby effectively eliminating intra-view interference. Extensive experiments confirm our method's effectiveness in addressing the challenges that existing multi-view methods cannot resolve, consistently outperforming state-of-the-Art techniques. © 2023 ACM.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

A Person-job Matching Method Based on BM25 and Pre-Trained language Model 6

A Person-job Matching Method Based on BM25 and Pre-Trained L...

引用

6th international conference on machine learning and natural language processing, mlnlp 2023

作者： Tang, Jiaqi Chen, Heyun Chen, Zifan Pan, Jiahua He, Yijiang Zhao, Jie Li, Zhen PKU-Changsha Institute for Computing and Digital Economy Changsha China Center for Data Science Peking University Beijing China National Engineering Laboratory for Big Data Analysis and Applications Peking University Beijing China

ISBN: (纸本)9798400709241

To address the inefficiency of traditional methods for person-job matching and the lack of interpretability of deep learning approaches, a novel approach for person-job matching based on BM25 and pre-Trained language models is proposed. First, the BM25 algorithm is utilized to perform an initial screening of resumes based on job descriptions. By calculating the matching degree of keywords, it rapidly filters out candidate resumes that do not align with the job requirements. Subsequently, the pre-Trained language model BERT is employed to perform fine-grained sorting of the resumes that passed the initial screening, identifying the candidates that best match with the job. By combining the screening capability of the BM25 algorithm with the semantic understanding ability of pre-Trained language models, this method enhances the accuracy and interpretability of person-job matching results while maintaining matching speed. Furthermore, to improve model generalization, large-scale language models are employed for data augmentation. Experimental results indicate the significant potential for the proposed approach in practical applications, offering improved solutions for the challenges of talent recruitment across diverse job demands. © 2023 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Enhancing Visual Question Answering through Bi-Modal Feature Fusion: Performance Analysis 24

Enhancing Visual Question Answering through Bi-Modal Feature...

引用

6th international conference on Image processing and machine Vision (IPMV)

作者： Mao, Keyu Fudan Univ Sch Data Sci Shanghai Peoples R China

ISBN: (纸本)9798400708473

With the significant development in deep learning within the domains of computer vision and natural language processing, the research involving the multimodal aspects of Visual Question Answering (VQA) has also reached a pivotal turning point in recent years. throughout prior investigations, scholars have consistently emphasized feature extraction from images and text. Numerous models have been applied in this context, ranging from the initial breakthroughs of Recurrent Neural Network (RNN) and Convolutional Neural Network (CNN), to the momentary prominence of Dynamic Memory Networks, and subsequently, the rise of transformers in recent times. Nonetheless, it is imperative to recognize that beyond the ambit of feature extraction models, the fusion of bi-modal features assumes pivotal significance. this paper builds upon SOAT model from the previous work, serving as the baseline, and meticulously scrutinizes its performance across distinct fusion methodologies. Various notable fusion strategies, such as MUTAN and BLOCK, are considered. Notably, the most adept model achieves an impressive 65.74% accuracy on the VQA v2 dataset, outperforming established benchmarks. this outcome robustly substantiates the premise that fusion techniques exert tangible influence over the ultimate research outcomes.

关键词： VQA natural language processing Computer vision Fusion Bilinear models

来源：评论

学校读者我要写书评

暂无评论

Sentiment and Interest Detection in Social Media using GPT-based Large language Models 6

Sentiment and Interest Detection in Social Media using GPT-b...

引用

6th international conference on machine learning and natural language processing, mlnlp 2023

作者： Al Asad, Md Abdullah Imran, Hasan Md Alamin, Md Abdullah, Tareque Abu Chowdhury, Suriya Islam Clark Atlanta University AtlantaGA United States Michigan State University East LansingMI United States

ISBN: (纸本)9798400709241

In the ever-expanding realm of social media, deciphering sentiments and identifying relevant topics from various textual content is challenging. this paper comprehensively investigates sentiment analysis and interest/topic detection using cutting-edge language models, ChatGPT3.5 and gpt4All. the methodology encompasses data collection, meticulous text pre-processing, innovative prompt design, and the exploration of zero-shot, one-shot, and few-shot learning techniques. We unveil the nuances of model performance in sentiment analysis and interest/topic detection through a detailed comparative analysis. Our findings highlight the power of ChatGPT3.5 in achieving a substantial accuracy enhancement in sentiment analysis compared to gpt4All. Moreover, we delve into the intricacies of interest detection, demonstrating the complexities of linguistic structures and model biases. We offer a holistic view of social entities' preferences by categorizing topics into distinct domains. A web portal developed using Google's Flutter SDK facilitates the visualization of user-friendly sentiment and interest outcomes. this research contributes to the understanding of sentiment analysis and interest detection and underscores the evolving capabilities of AI and NLP in navigating the dynamic landscape of social media content. © 2023 ACM.

关键词： learning systems

来源：评论

学校读者我要写书评

暂无评论

Watch Your English language: Text Normalization from Written Expressions to Spoken Forms 6

Watch Your English Language: Text Normalization from Written...

引用

6th international conference on machine learning and natural language processing, mlnlp 2023

作者： Jiang, Yufeng Xidian University Shaanxi Xi'an China

ISBN: (纸本)9798400709241

Based on the existing research results for speech-To-Text and methods based on statistical modelling, machine learning, etc., this paper applied the feature engineering method based on machine learning to speech-Totext, converting English text from written expressions into spoken forms. First, I preprocessed the data, including calculating the file structure and contenthad, missing values as well as reformating features. Next I had a look at normalized sentences and overview visualizations. And then I researched the impact of the normalization. Moreover, I researched token classes and their text normalization, which compose of the "PLAIN"(modifications), the "PUNCT"(punctuation), numerical classes, the "LETTERS"(acronyms anhd initials), the "VERBATIM"(special symbols) as well as the "ELECTRONIC"(websites) class, with the most frequent transformations of each class. Meanwhile, I did a next-neighbour analysis to prove that context matters a lot, inlcuding token class overview-previous vs next, treemap overviews relative percentages, exploration of all neighbour relations. then, I analysed the transformation statistics, such as sentence length and classes, as well as normalized tokens and where to found them. On the basis of these foundings, I did the feature engineering composing of string length, class-specific token distance, numeric tokens and what's in a name. I also did a case study-A tale of four twos, including the class "CARDINAL", "ORDINAL", "LETTERS", and "PLAIN". Ultimately, I evaluated the results with 11.11 MB size test data, getting a extremely high accuracy score of 99.776Additional Key Words and Phrases: Text normalization, Text-To-speechFeature engineering, Tok © 2023 ACM.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Research on Network Personalized Recommendation Algorithm Based on machine learning 6

Research on Network Personalized Recommendation Algorithm Ba...

引用

6th IEEE international conference on Power, Intelligent Computing and Systems, ICPICS 2024

作者： Yu, Jiang Guangzhou Huali College Guangzhou City China

ISBN: (纸本)9798350374315

As a tool of information dissemination, Internet not only provides abundant information, but also brings serious information overload. Recommendation algorithm can extract interests and preferences from users' historical information, so as to make personalized information recommendation to users, which has been widely used in various scenarios in the Internet field. With the development of artificial intelligence, especially the application of machine learning, recommendation algorithm has developed into a multidisciplinary research direction of integrating neural networks, knowledge graphs and natural language processing. In order to alleviate the problem of 'information cocoon' caused by blind pursuit of recommendation accuracy, this paper mainly proposes a fuzzy algorithm recommendation model with dynamic threshold based on machine learning model. By improving association rules, the data imbalance in the data set is adjusted, the speed of data processing is improved, and the dynamic threshold adjustment strategy is adopted to provide personalized information services to users accurately. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

language Detection Using natural language processing 6

Language Detection Using Natural Language Processing

引用

6th international conference on Recent Trends in Advance Computing, ICRTAC 2023

作者： Rao, P. Bhaskar Kotagiri, Chaithanya Madamshetti, Rishanka Minkoori, Abhisree Gande, Sahasra Bvritn Narsapur India Bvritn Cse Narsapur India

ISBN: (纸本)9798350394702

the natural language Detection Model is a project that uses machine learning techniques to estimate the language of a given document. the project makes use of a data set containing text information for 17 distinct languages and employs methods that include labelled encoding, preprocessing of text, or a Bag of Word model. the predictive model undergoes training using the Multinomial Naive Bayes approach and achieves an excellent accuracy of 0.97. this study demonstrates the ability of NLP to identify languages or its possible uses in translation by machines and multilingual content tracking. the model's precise predictions and strong performance verify the model's efficacy in real-world circumstances. the project starts by installing modules and uploading the language recognition data set, then separates both dependent and independent variables. the text data is subsequently processed with preprocessing for text techniques, and then a Bag with Words model is generated with CountVectorizer. the dataset is divided into sets for training and testing, and the model is trained using the Multinomial Naive Bayes method on the training data. the model that has been trained is then applied to the test set to forecast the language of the text. the project showcases the successful application of natural language processing (NLP) approaches for language recognition and emphasizes the value of hands-on project experience for budding machine learning enthusiasts. © 2023 IEEE.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

A Survey of Sarcasm Detection Techniques in natural language processing 6

A Survey of Sarcasm Detection Techniques in Natural Language...

引用

6th international conference on Information Systems and Computer Networks, ISCON 2023

作者： Singh, Bhuvanesh Sharma, Dilip Kumar University of St. Thomas United States Gla University Mathura India

ISBN: (纸本)9798350346961

Sarcasm is a linguistic style that is often employed in regular conversation and that natural language processing (NLP) systems may find difficult to recognize. the use of sarcasm in social media, online reviews, and other digital communication has increased in recent years, making it essential for NLP systems to detect sarcasm accurately. In this survey, we provide an overview of the current state of the art in sarcasm detection using NLP techniques. We discuss the various approaches to detect sarcasm, including machine learning, deep learning, and lexicon-based methods. We also review recent research on sarcasm detection in various languages and contexts, such as social media, customer reviews, and online forums. We also identify opportunities for future study and address the difficulties and limits of the present sarcasm detection techniques. the overall goal of this survey is to further this field of study by providing a thorough grasp of sarcasm detection in NLP.. © 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

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69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：