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181-190 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：

Simulation of Structured natural language Algorithm on Cloud Computing 3

Simulation of Structured Natural Language Algorithm on Cloud...

引用

3rd ieee international conference on Electrical engineering, Big Data and Algorithms, EEBDA 2024

作者： Fang, Quanrong Tang, Keyin Investment Co. Ltd. Beijing China

ISBN: (纸本)9798350380989

From the sentiment analysis of social media to the monitoring of public opinion in the financial field, the application of natural language analysis continues to expand, and people's demand for natural language processing technology is also increasing. However, traditional natural language analysis algorithms face performance bottlenecks and energy consumption. Therefore, this paper proposes a structured natural language analysis algorithm based on cloud computing. Through simulation experiments, the performance and energy consumption of the algorithm are tested and evaluated. After a comprehensive experimental scheme design, the experimental group is compared with the control group by selecting the appropriate data set and establishing appropriate evaluation indicators, while configuring the experimental environment. The experimental results show that the lowest energy consumption of the algorithm in this paper is 2.41%, and the structured natural language analysis algorithm based on cloud computing has obvious advantages over traditional methods. The proportion of energy consumption in the experimental group is lower than that of the control group, indicating that the algorithm of the experimental group is better in terms of energy utilization efficiency. The performance degradation of the experimental group is lower when processing large-scale data, indicating that the experimental group algorithm has better extensibility and efficiency. These results provide strong support for the application of structured natural language analysis algorithms based on cloud computing, which helps to improve system efficiency and sustainability. © 2024 ieee.

关键词： algorithm simulation cloud computing natural language structured analysis

来源：评论

学校读者我要写书评

暂无评论

Research and Application of Artificial Intelligence Large language Models Based on Feature Enhancement 4

Research and Application of Artificial Intelligence Large La...

引用

4th international conference on Consumer Electronics and Computer engineering, ICCECE 2024

作者： Zhuang, Li Wang, Qiulin Song, Lihua Wu, Peiying Fujian Yirong Information Technology Co. Ltd. Fuzhou Fujian350001 China

ISBN: (纸本)9798350384062

In recent years, natural language processing has become a crucial research direction in artificial intelligence. The Transformer model, in particular, has emerged as a foundational model in the field of natural language processing. Transformer and its various variants have significantly improved the performance of many natural language processing tasks. Therefore, this study focuses on the research and application of artificial intelligence large language models based on feature enhancement. Firstly, the paper proposes a pre-trained language model based on the Transformer architecture. Secondly, it analyzes BERT model's pre-training on representing news content to enhance the model's accuracy. Finally, through experimentation, this study demonstrates that the proposed model and algorithm effectively optimize language vocabulary in news, thereby improving its performance in tasks. © 2024 ieee.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Continual Joint Event Extraction via Adaptive Bias Mixing 14

Continual Joint Event Extraction via Adaptive Bias Mixing

引用

14th ieee international conference on Big Data and Cloud Computing, BDCloud 2024

作者： Lu, Chengeng Shen, Yatian Henan University School of Computer and Information Engineering Kaifeng China

ISBN: (纸本)9798331510268

Continual event extraction is a practical task in natural language processing that requires models to learn quickly from new event types and data sources without forgetting pre-existing knowledge. It is important since language models often encounter new information to which they must efficiently adapt. Current work on continual event extraction either reuses existing parameters to learn from new tasks or statically assigns parameters specific to each new incoming task, incurring significant computational cost while preventing the potential knowledge sharing between tasks. To achieve a balance between the two, in this work, we present a means to adapt the model to incoming tasks in a parameter-efficient manner. We also incorporate metric learning to construct a prototypical network for maximum parameter efficiency. Experimental results on the ACE2005 dataset show that our framework maintains baseline performance with significantly smaller parameter sizes. © 2024 ieee.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Open-Source Large language Models: A Comprehensive Survey 2

Open-Source Large Language Models: A Comprehensive Survey

引用

2nd international conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Sahana Lokesh, R. Siddaganga Institute of Technology Department of Computer Science and Engineering Karnataka Tumakuru India

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505745

Large language Models (LLMs) have emerged as strategic in the promotion of natural language processing (NLP) to the extent of having machines translate languages as well as making logical deductions. The role of the open-source team in advancing this progress is that LLMs are now available for development and research. This paper offers an elaborate literature review on some of the most widely used open-source LLMs and their architecture, training approach, and evaluation results. Certainly, the mathematical aspects behind these models are explored, the comparison of the models is given and the problems and perspectives of development of the models are described. © 2025 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

Exploring Social Media Sentiment Polarity: A Case Study Utilizing language Models 4

Exploring Social Media Sentiment Polarity: A Case Study Util...

引用

4th ieee international conference on Software engineering and Artificial Intelligence (SEAI)

作者： Yang, Bo Johnson-Shapoval, Sophie Bowie State Univ Dept Comp Sci Bowie MD 20715 USA

ISBN: (纸本)9798350374353;9798350374346

Large language models are crucial for processing social media data, aiding in recommendation systems, sentiment analysis, and more. This study proposes a method to enhance sentiment analysis accuracy by combining word embeddings with insights from a language-based model. Focused on consumer reviews, sentiments are categorized based on extreme polarities, excluding intermediate ratings. Empirical assessments show superior outcomes when combining opinions, summaries, and pre-processed summaries. Machine learning algorithms are applied to hybrid vectors to classify sentiments accurately, distinguishing between positive and negative viewpoints. This approach offers nuanced sentiment analysis within consumer feedback, facilitating understanding of product reviews. Overall, the method integrates feature extraction and machine learning to analyze binary polar data, providing sentiment estimates in a concise vector form, with promising implications for sentiment analysis and consumer sentiment understanding.

关键词： sentiment analysis polarity categorization language models artificial intelligence natural language processing

来源：评论

学校读者我要写书评

暂无评论

What Makes a High-Quality Training Dataset for Large language Models: A Practitioners' Perspective 24

What Makes a High-Quality Training Dataset for Large Languag...

引用

39th ACM/ieee international conference on Automated Software engineering (ASE)

作者： Yu, Xiao Zhang, Zexian Niu, Feifei Hu, Xing Xia, Xin Grundy, John Huawei Hangzhou Peoples R China Wuhan Univ Technol Sch Comp Sci & Artificial Intelligence Wuhan Peoples R China Univ Ottawa Sch Elect Engn & Comp Sci Ottawa ON Canada Zhejiang Univ State Key Lab Blockchain & Data Secur Hangzhou Peoples R China Monash Univ Fac Informat Technol Melbourne Vic Australia Wuhan Univ Technol Chongqing Res Inst Chongqing Peoples R China

ISBN: (数字)9798400712487

ISBN: (纸本)9798400712487

Large language Models (LLMs) have demonstrated remarkable performance in various application domains, largely due to their self-supervised pre-training on extensive high-quality text datasets. However, despite the importance of constructing such datasets, many leading LLMs lack documentation of their dataset construction and training procedures, leaving LLM practitioners with a limited understanding of what makes a high-quality training dataset for LLMs. To fill this gap, we initially identified 18 characteristics of high-quality LLM training datasets, as well as 10 potential data pre-processing methods and 6 data quality assessment methods, through detailed interviews with 13 experienced LLM professionals. We then surveyed 219 LLM practitioners from 23 countries across 5 continents. We asked our survey respondents to rate the importance of these characteristics, provide a rationale for their ratings, specify the key data pre-processing and data quality assessment methods they used, and highlight the challenges encountered during these processes. From our analysis, we identified 13 crucial characteristics of high-quality LLM datasets that receive a high rating, accompanied by key rationale provided by respondents. We also identified some widely-used data pre-processing and data quality assessment methods, along with 7 challenges encountered during these processes. Based on our findings, we discuss the implications for researchers and practitioners aiming to construct high-quality training datasets for optimizing LLMs.

关键词： Large language Models High-Quality Data Practitioners' Perspective Empirical Study

来源：评论

学校读者我要写书评

暂无评论

ENHANCING SPEAKER DIARIZATION WITH LARGE language MODELS: A CONTEXTUAL BEAM SEARCH APPROACH 49

ENHANCING SPEAKER DIARIZATION WITH LARGE LANGUAGE MODELS: A ...

引用

49th ieee international conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Park, The Jin Dhawan, Kimal Koluguri, Nithin Balam, Jagadeesh NVIDIA Santa Clara CA 95051 USA

ISBN: (纸本)9798350344868;9798350344851

Large language models (LLMs) have shown great promise for capturing contextual information in natural language processing tasks. We propose a novel approach to speaker diarization that incorporates the prowess of LLMs to exploit contextual cues in human dialogues. Our method builds upon an acoustic-based speaker diarization system by adding lexical information from an LLM in the inference stage. We model the multi-modal decoding process probabilistically and perform joint acoustic and lexical beam searches to incorporate cues from both modalities: audio and text. Our experiments demonstrate that infusing lexical knowledge from the LLM into an acoustics-only diarization system improves the overall speaker-attributed word error rate (SA-WER). The experimental results show that LLMs can provide complementary information to acoustic models for the speaker diarization task via the proposed beam search decoding approach showing up to 39.8% relative delta-SA-WER improvement from the baseline system. Thus, we substantiate that the proposed technique is able to exploit contextual information that is inaccessible to acoustics-only systems which is represented by speaker embeddings. In addition, these findings point to the potential of using LLMs to improve speaker diarization and other speech-processing tasks by capturing semantic and contextual cues.

关键词： Speaker Diarization Multi-speaker Speech Recognition Large language Model Beam Search Decoding

来源：评论

学校读者我要写书评

暂无评论

Multiclass Context Analysis of Hindi Statements Using natural language processing 1

Multiclass Context Analysis of Hindi Statements Using Natura...

引用

1st ieee international conference on Ambient Intelligence, knowledge Informatics and Industrial Electronics, AIKIIE 2023

作者： Vani, K.S. Nair, Aditya Mohib, Amaan Gupta, Prateek Das, Satwik Nitte Meenakshi Institute of Technology Information Science and Engineering Bangalore India

ISBN: (纸本)9798350316469

India has many different spoken languages. The majority of the populace communicates in their native tongues. In every device, support for these languages is available. Hindi language posts and material are becoming more and more prevalent. However, tools for categorizing and analyzing the context and intent have primarily been created for international languages like English. Because so many people increasingly utilize local languages on social media, there is a greater demand for support for text classification and analysis in local languages. In this work an application is created which can analyze the context of the particular hindi text entered. The application has XLM-ROBERTA model running in the background for which transfer learning is used to train it. © 2023 ieee.

关键词： BERT context classification genre classification Hindi language intent classification machine learning multiclass classification natural language processing text classification transformers

来源：评论

学校读者我要写书评

暂无评论

VTN-EG: CLIP-Based Visual and Textual Fusion Network for Entity Grounding 7

VTN-EG: CLIP-Based Visual and Textual Fusion Network for Ent...

引用

7th international conference on Machine Learning and natural language processing, MLNLP 2024

作者： Hao, Shiyi Wang, Linjie Zheng, Yifeng Wang, Chen Liu, Yunfei Li, Shengyang Center for Space Utilization Chinese Academy of Sciences Technology and Engineering Beijing China Key Laboratory of Space Utilization Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798350354973

In the field of space science and utilization, we have constructed a domain knowledge graph based on text data. However, a significant problem with this knowledge graph is the absence of a large number of domain-relevant multimodal data. Entity grounding is the principal approach to addressing this issue, which refers to aligning external images with corresponding text entities. Currently, entity grounding has issues of entity name ambiguity and entity image sparseness. In response to these issues, we propose a method called VTN-EG, within which we design three new modules: prompt network module, attention module and decision module. The initial two modules use prompt network and cross-attention mechanism respectively to augment the expressiveness of image and text encoding. In the decision module, we obtain the final results based on the strategy of using the prompt network in visual discrimination process and not using it in text discrimination process. To support algorithmic research, we construct a specialized entity grounding dataset called the Chinese Space Science and Utilization Entity Grounding (SSUEG) and select four deep learning methods for comparison. Extensive experiments on SSUEG and two public datasets have proved the advancement and generalization of VTN-EG. Finally, we demonstrate the effectiveness and necessity of algorithm improvements through ablation experiments. © 2024 ieee.

关键词： knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Survey on Neural Networks in natural language processing

Survey on Neural Networks in Natural Language Processing

引用

2023 ieee international conference on Control, Electronics and Computer Technology, ICCECT 2023

作者： Hu, Fei Chongqing University of Science and Technology School of Intelligent Technology and Engineering Chongqing401331 China

ISBN: (纸本)9798350399028

Neural Networks can learn natural language representations within levels of abstraction, and have recently shown much promise for natural language processing (NLP) applications. Kinds of Neural Network language Models (NNLMs) have gained a lot of success by predicting the next word given the other words in a context. These models have improved the state-of-the-art in word sense disambiguation, question answering, web search and many other domains in semantic parsing. Compared with "bag of word", Word Embedding has brought about breakthroughs in representations of words, sentences, or even documents. Recurrent Neural Network language Models (RNNLMs) have shone light. They can learn and store long-memory knowledge that would help extracting better representations for long documents. © 2023 ieee.

关键词： Embeddings

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 << < 15 16 17 18 19 20 21 22 23 24 > >>

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：