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

14,416 篇 会议
650 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

15,207 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

10,942 篇 工学
- 10,282 篇 计算机科学与技术...
- 5,394 篇 软件工程
- 1,487 篇 信息与通信工程
- 960 篇 电气工程
- 898 篇 控制科学与工程
- 446 篇 生物工程
- 239 篇 网络空间安全
- 222 篇 化学工程与技术
- 192 篇 机械工程
- 173 篇 生物医学工程（可授...
- 144 篇 电子科学与技术（可...
- 109 篇 安全科学与工程
- 104 篇 交通运输工程
2,490 篇 理学
- 1,167 篇 数学
- 652 篇 物理学
- 518 篇 生物学
- 396 篇 统计学（可授理学、...
- 241 篇 系统科学
- 232 篇 化学
2,426 篇 管理学
- 1,757 篇 图书情报与档案管...
- 763 篇 管理科学与工程(可...
- 239 篇 工商管理
- 109 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
515 篇 医学
- 300 篇 临床医学
- 281 篇 基础医学(可授医学...
- 117 篇 公共卫生与预防医...
274 篇 法学
- 247 篇 社会学
236 篇 教育学
- 223 篇 教育学
100 篇 农学
97 篇 经济学
9 篇 艺术学
7 篇 哲学
4 篇 军事学

主题

3,531 篇 natural language...
1,755 篇 natural language...
952 篇 computational li...
736 篇 semantics
686 篇 machine learning
610 篇 deep learning
520 篇 natural language...
345 篇 computational mo...
334 篇 training
333 篇 sentiment analys...
329 篇 accuracy
323 篇 large language m...
319 篇 feature extracti...
311 篇 data mining
290 篇 speech processin...
265 篇 speech recogniti...
251 篇 transformers
237 篇 neural networks
217 篇 iterative method...
211 篇 support vector m...

机构

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

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
27 篇 lapata mirella
26 篇 wen ji-rong
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

14,595 篇 英文
500 篇 其他
102 篇 中文
18 篇 法文
15 篇 土耳其文
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 15208 条记录，以下是261-270 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：

Anchored Monotonic Alignment and Representation Substitution for Rare Spontaneous Behaviors in Spontaneous Speech Synthesis

Anchored Monotonic Alignment and Representation Substitution...

引用

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

作者： Wu, Ning-Qian Hu, Ya-Jun Chen, Liping Ling, Zhen-Hua National Engineering Research Center of Speech and Language Information Processing University of Science and Technology of China Hefei China iFLYTEK Research iFLYTEK Co. Ltd. China MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition University of Science and Technology of China China

ISBN: (纸本)9798350368741

Spontaneous behaviors in speech pose significant challenges for speech synthesis. Existing research has not adequately addressed these behaviors, with most studies relying on specially recorded datasets. In contrast, real-world data more accurately reflects the natural, spontaneous speaking styles in everyday life and encompasses a wider range of spontaneous behaviors. However, such data is often of lower quality, and the distribution of spontaneous behaviors is highly imbalanced. In this study, we explore spontaneous speech synthesis using real-world data within the VITS2 framework. To overcome these challenges, we introduce two techniques: anchored monotonic alignment and spontaneous hidden representation substitution. Experimental results demonstrate that these methods enhance model alignment and improve the naturalness of the generated speech. Our proposed approach successfully addresses the challenge of synthesizing rare spontaneous behaviors and offers users flexible control over the synthesized speech. © 2025 IEEE.

关键词： real-world data speech synthesis spontaneous behaviors spontaneous speech synthesis VITS

来源：评论

学校读者我要写书评

暂无评论

Assessing Large language Models Effectiveness in Outdated Method Renaming 22nd

Assessing Large Language Models Effectiveness in Outdated Me...

引用

22nd International conference on Service Oriented Computing

作者： Ben Mrad, Ali Thiombiano, Abdoul Majid O. Mkaouer, Mohamed Wiem Hnich, Brahim Qassim Univ Coll Comp Dept Comp Sci Buraydah Saudi Arabia Univ Sfax CES Lab ENIS Sfax 3038 Tunisia Univ Monastir FSM Monastir 5000 Tunisia Univ Michigan Flint Flint MI USA

ISBN: (纸本)9789819608041;9789819608058

Identifying effective methods for automatic method renaming after code modifications is crucial for maintaining developer productivity and enhancing the performance of source code analysis tools. In this study, we focus on benchmarking the effectiveness of the ChatGPT large language model (LLM) in predicting new method names after code modifications. Leveraging a dataset of method code snippets along with their original and modified names, we conducted experiments on 116 samples to assess the prediction accuracy of ChatGPT. Using Jaccard similarity as the metric, we varied the similarity threshold to evaluate the classification performance of predicted names. However, the Jaccard similarity does not retain the magnitude or direction of the vectors, reflecting the strength and polarity of the similarity. In addition, it ignores the order and context of the words, which results in missing potential syntactic or semantic variations. To solve this problem, we propose another validation process which not only detects whether or not an LLM captured semantic changes of a method, but also its structural changes in order to be able to generate a suitable name for this given method. Our results indicate that ChatGPT achieves a high success rate in predicting method names, obtaining 98% (Resp. 94%) when the threshold is set to 0.5 for the Cosine (resp. Jaccard) similarity. For a threshold of 1 (maximum similarity), ChatGPT maintains a notable performance with 49% (Resp. 74%) Cosine (resp. Jaccard) similarity. This demonstrates the potential of ChatGPT for automating method renaming tasks in software development workflows.

关键词： API Renaming Benchmarking Large language Models Machine Learning natural language processing

来源：评论

学校读者我要写书评

暂无评论

RGR-KBQA: Generating Logical Forms for Question Answering Using Knowledge-Graph-Enhanced Large language Model 31

RGR-KBQA: Generating Logical Forms for Question Answering Us...

引用

31st International conference on Computational Linguistics, COLING 2025

作者： Feng, Tengfei He, Liang School of Computer Science and Technology Xinjiang University Urumqi830017 China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

ISBN: (纸本)9798891761964

In the field of natural language processing, Knowledge Base Question Answering (KBQA) is a challenging task that involves accurately retrieving answers from structured knowledge. Existing methods often face issues when generating query statements using LLMs, as the knowledge introduced may be imprecise and the models themselves may exhibit hallucination problems, leading to low accuracy, particularly when dealing with complex questions. To address these challenges, we introduce a novel semantic parsing approach called RGR-KBQA, which adopts a Retrieve-Generate-Retrieve framework. The first retrieval step introduces factual knowledge from a knowledge graph to enhance the semantic understanding capabilities of LLMs, thereby improving generation accuracy of logical form. The second step uses a fine-tuned model to generate the logical form, and the final step involves unsupervised relation and entity retrieval to further enhance generation accuracy. These two retrieval steps help alleviate the hallucination problems inherent in LLMs. Experimental results show that RGR-KBQA demonstrate promising performance on CWQ and WebQSP datasets. © 2025 Association for Computational Linguistics.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Improving Arabic Fake News Detection Across Context-Aware Attention Deep Model Based on natural language processing 3rd

Improving Arabic Fake News Detection Across Context-Aware At...

引用

3rd International conference on language processing and Knowledge Management, LPKM 2024

作者： Khudair, Enas Tariq O., Lazzez T.M., Hamdani A.T., Sadiq A.M., Alimi BP 1173 Sfax3038 Tunisia Avenue 5 August Rue Said Aboubaker Sfax3002 Tunisia Computer Science Department University of Monastir Monastir Tunisia Department of Electrical and Electronic Engineering Science University of Technology-Iraq Baghdad Iraq Faculty of Engineering and the Built Environment University of Johannesburg Johannesburg South Africa

ISBN: (纸本)9783031850660

With the enormous growth of social data in recent years, fake news detection has gained increasing research attention and has been widely explored in various languages. Arabic language nature imposes various challenges, such as the complicated morphological structure and the limited resources. Therefore, the current state-of-the-art methods for fake news detection remain to be enhanced, which inspired us to explore the application of the emerging deep-learning architecture to Arabic text classification. In this paper, we present an ensemble model that enhances the attention mechanism to detect fake news in Arabic sentences. An attention mechanism unit is incorporated to highlight the critical information from the contextual feature vectors. The context-related vectors generated by the attention mechanism layers are then concatenated and passed into a classifier to predict the final label. The experimental results show that the attention mechanism improves the model’s performance while yielding 99.8% in accuracy. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Arabic Fake News Detection Arabic language Fake News Social Network

来源：评论

学校读者我要写书评

暂无评论

Webcam-Based Real-Time Indian Sign language Recognition for Inclusive Communication 15th

Webcam-Based Real-Time Indian Sign Language Recognition for ...

引用

15th International conference on Intelligent Computing and Networking, IC-ICN 2024

作者： Shetty, Aanshula Wadekar, Vedanti Worah, Nidhi Patil, Megharani Thakur College of Engineering and Technology Mumbai India

ISBN: (纸本)9789819786305

Everybody involved in a conversation must put effort into the conversation to be successful. People with normal hearing and speech capabilities can easily communicate with one another. However, the majority of the population has always found it difficult to communicate with people who have differing abilities without the help of a translator. This is why using sign language becomes essential. Widespread usage of sign language helps overcome this barrier of communication and ensures that those with special needs are able to effectively communicate and share their feelings with the general public. These are typically employed by people with hearing and speech impairments who rely heavily on nonverbal modes of communication to communicate with one another and others. Sign language Recognition involves recognizing and interpreting hand gestures and being able to understand their meaning. There are multiple sign language systems used in different parts of the globe. Objective: This research aims to examine the various advancements made to the Indian Sign language system to facilitate communication between the general public and individuals with speech and hearing impairments. methods: The system presented employs natural language processing and emerging technologies like Computer Vision to detect hand signs using Convolutional Neural Networks (CNN), Artificial Neural Networks (ANN), Support Vector Machines (SVM), Recurrent Neural Networks (RNN), LSTM (Long Short-Term Memory). Once the hand poses are captured by the webcam, various steps are performed on it, they are classified and lastly translated into English words. © 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

Automated Framework for Constructing Knowledge Graphs Oriented for Standard Analysis Using Large language Models 24

Automated Framework for Constructing Knowledge Graphs Orient...

引用

2nd International conference on Electronics, Computers and Communication Technology, CECCT 2024

作者： Zhu, Sitong Xia, Baobing Duan, Fangwei Zhao, Zhenyang Zhao, Zhenxia Xiao, Teliang Liu, Zhicheng Liu, Xia State Grid Liaoning Electric Power Co. LTD. Electric power Research Institute Liaoning Shenyang China Beijing State Grid Communication Accenture Information Technology Co. Ltd. Beijing China

ISBN: (纸本)9798400710193

In an era characterized by rapid technological growth and digital transformation, the necessity for efficient and structured knowledge representation has grown more crucial. Standards serve as fundamental cornerstones that offer guidelines, specifications, and frameworks to ensure the quality and interoperability of products, services, as well as systems. Nonetheless, the complexity and extensive nature of standard documents present significant challenges in extraction, alignment, and organization. Traditional manual processing methods frequently prove labor-intensive and susceptible to errors, impeding the capturing of intricate relationships and hierarchies within these standards. Knowledge Graphs (KGs) provide a robust methodology for organizing information, facilitating improved functionalities for advanced search, reasoning, and analytics. Despite their potential, structuring KGs from standard documents continues to be challenging because of unstructured text, domain-specific terminology, and the intricacies in accurate information extraction. Recent advancements in natural language processing (NLP), particularly the emergence of Large language Models (LLMs) like GPT-3, have opened new avenues for automating the extraction and structuring of information from unstructured content. These models exhibit exceptional proficiency in comprehending and producing human-like text, positioning them as feasible solutions for addressing the complexities associated with standard documents. This paper presents an automated framework named StandardKG Builder, which utilizes LLMs to construct knowledge graphs tailored for standard analysis from multiple perspectives for complex information extraction. Our evaluation on a comprehensive dataset of standard documents highlights the framework’s effectiveness and scalability. By merging sophisticated knowledge representation with advanced NLP techniques, our work significantly enhances the accessibility and analysis of standard docu

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Harnessing Large language Models for Precision Topic Extraction and Technology Patent Nomination: A GPT-centric Methodology 16

Harnessing Large Language Models for Precision Topic Extract...

引用

16th International conference on Ambient Systems, Networks and Technologies Networks, ANT 2025 / 8th International conference on Emerging Data and Industry 4.0, EDI40 2025

作者： Nkolongo, Franck Tshibanda Echchakoui, Said Mehdi, Adda Department of Mathematics Computer Science and Engineering University of Quebec at Rimouski Canada Management Sciences Departmental Unit University of Quebec at Rimouski (Lévis) Canada

Topic modeling is widely used for analyzing large textual datasets, particularly in technology patent nomination. Traditional methods, such as Latent Dirichlet Allocation (LDA) and Non-Negative Matrix Factorization (NMF), often struggle with semantic comprehension, scalability, and adaptability. This study investigates Large language Models (LLMs) to overcome these limitations. Leveraging their advanced language understanding, GPT models generate coherent and contextually relevant topics, outperforming conventional methods. They also excel in identifying emerging trends, enhancing patent nomination processes. Our findings demonstrate the potential of GPT-based approaches to streamline patent analysis and accelerate technological discovery. © 2025 Elsevier B.V.. All rights reserved.

关键词： GPT Applications Large language Models (LLMs) natural language processing (NLP) Patent Analysis Topic Modeling

来源：评论

学校读者我要写书评

暂无评论

Diffusion Models are Zero-Shot Generative Text-Vision Retrievers

Diffusion Models are Zero-Shot Generative Text-Vision Retrie...

引用

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

作者： Li, Bao Xie, Zeke Zhang, Xiaomei Zhu, Xiangyu Lei, Zhen MAIS Institute of Automation Chinese Academy of Sciences Beijing China School of Artifical Intelligence University of Chinese Academy of Sciences Beijing China Guangzhou China CAIR HKISI Chinese Academy of Sciences Hong Kong

ISBN: (纸本)9798350368741

Large-scale text-to-image diffusion models have demonstrated impressive capabilities for downstream tasks by leveraging strong vision-language alignment from generative pre-training. Recently, a number of works have explored how to use the power of text-to-image diffusion models for text-image matching tasks. While previous generative text-image matching methods have shown potential in retrieving the most challenging candidates, they still suffer from extremely slow retrieval speeds and lack the ability to handle temporal dimensions, making them impractical for text-video retrieval. In this paper, we propose ZSGenRet, a simple yet effective zero-shot generative text-vision retrieval framework for both text-image and text-video tasks, based on pre-trained text-to-image diffusion models. We further incorporate inversion saliency detection to identify key frames in videos and enhance the semantic representation of the vision encoder. Experimental results demonstrate that ZSGenRet significantly improves text-video retrieval performance and achieves competitive results on text-image retrieval while remarkably improving efficiency. To the best of our knowledge, the proposed ZSGenRet is the first to explore zero-shot text-video retrieval based on diffusion models. © 2025 IEEE.

关键词： diffusion models Text-vision retrieval vision-language models zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis Using Dialogue Data: A Taxonomy of Literature 58

Sentiment Analysis Using Dialogue Data: A Taxonomy of Litera...

引用

58th Hawaii International conference on System Sciences, HICSS 2025

作者： Äyräväinen, Laura E.M. Hinds, Joanne Davidson, Brittany I. University of Bath United Kingdom

ISBN: (纸本)9780998133188

In a rapidly advancing world of artificial intelligence and natural language processing, the need to understand human dialogue with information systems is ever more pressing. This paper presents a taxonomy of sentiment analysis using dialogue data, developed via a scoping literature review and employment of a widely recognized taxonomy method. By synthesizing the diverse approaches across 18 papers (comprising 22 dimensions and 328 categories), we present a framework that highlights the components underpinning current work, including application domains, data characteristics, sentiment analysis pipelines, methods and dialogue-specific information utilized. By offering a detailed, method-focused view of the existing research, our taxonomy aims to guide future studies that seek to integrate sentiment analysis into dialogue systems. We discuss issues in the current state of the literature and conclude by providing directions for future research. © 2025 IEEE Computer Society. All rights reserved.

关键词： dialogue natural language processing sentiment analysis taxonomy

来源：评论

学校读者我要写书评

暂无评论

Mongolian-Chinese Cross-Lingual Topic Detection Based on Knowledge Distillation and Contrastive Learning methods 21st

Mongolian-Chinese Cross-Lingual Topic Detection Based on Kn...

引用

21st Pacific Rim International conference on Artificial Intelligence, PRICAI 2024

作者： Wang, Yanli Ji, Yatu Sun, Baolei Wu, Nier Ren, Qing-Dao-Er-Ji Wang, Bailun School of Information Engineering Inner Mongolia University of Technology Hohhot China

ISBN: (纸本)9789819601189

Most topic detection research focuses on cross-language information processing in languages with abundant resources, such as English-Chinese, English-German, and others. There are also some studies targeting low-resource languages such as Vietnamese-Chinese and Tibetan-Chinese cross-language topic detection research. However, there is very little research on Mongolian-Chinese cross-language studies. The primary reasons are the lack of corpora in the Mongolian language and the limitations of conventional topic detection methods in text representation, clustering, and topic representation within the Mongolian language domain. Therefore, this paper proposes a Mongolian-Chinese cross-lingual topic detection method based on knowledge distillation and contrastive learning. Firstly, the pre-trained language model is fine-tuned through knowledge distillation tasks to enable the model to integrate the semantic representation of Mongolian-Chinese cross-lingual texts. Then, the effect of cross-lingual topic detection is improved by combining contrastive learning training between news of different topics. Experimental results show that the proposed method combining knowledge distillation and contrastive learning outperforms other baseline models, achieving at least 2, 0.8, and 3% points higher in F1 score, topic diversity, and topic consistency, respectively. This approach effectively enhances the accuracy of Mongolian-Chinese cross-lingual topic detection. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive Learning

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 << < 23 24 25 26 27 28 29 30 31 32 > >>

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：