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

26,206 篇 会议
406 册 图书
373 篇 期刊文献
3 篇 学位论文
1 篇 资讯

馆藏范围

26,989 篇 电子文献
2 种 纸本馆藏

日期分布

学科分类号

16,309 篇 工学
- 14,939 篇 计算机科学与技术...
- 11,116 篇 软件工程
- 2,698 篇 信息与通信工程
- 1,672 篇 控制科学与工程
- 1,472 篇 电气工程
- 1,408 篇 生物工程
- 614 篇 生物医学工程（可授...
- 609 篇 化学工程与技术
- 557 篇 机械工程
- 475 篇 网络空间安全
- 430 篇 电子科学与技术（可...
- 389 篇 仪器科学与技术
- 365 篇 光学工程
- 276 篇 安全科学与工程
5,060 篇 理学
- 2,060 篇 数学
- 1,467 篇 生物学
- 1,465 篇 物理学
- 776 篇 统计学（可授理学、...
- 620 篇 系统科学
- 617 篇 化学
4,691 篇 管理学
- 3,144 篇 图书情报与档案管...
- 1,819 篇 管理科学与工程(可...
- 760 篇 工商管理
825 篇 医学
- 597 篇 临床医学
- 557 篇 基础医学(可授医学...
- 380 篇 公共卫生与预防医...
- 250 篇 药学(可授医学、理...
674 篇 法学
- 592 篇 社会学
573 篇 文学
- 401 篇 外国语言文学
440 篇 教育学
- 429 篇 教育学
249 篇 经济学
176 篇 农学
19 篇 艺术学
17 篇 军事学
1 篇 哲学

主题

5,603 篇 natural language...
1,694 篇 natural language...
1,537 篇 semantics
1,441 篇 natural language...
1,181 篇 machine learning
1,162 篇 sentiment analys...
1,113 篇 deep learning
906 篇 accuracy
897 篇 training
802 篇 data mining
774 篇 feature extracti...
758 篇 computational mo...
753 篇 artificial intel...
544 篇 knowledge engine...
519 篇 speech recogniti...
494 篇 large language m...
487 篇 transformers
471 篇 data models
462 篇 information retr...
460 篇 support vector m...

机构

57 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 beijing univ pos...
22 篇 school of inform...
22 篇 institute of inf...
21 篇 college of compu...

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 f. ren
12 篇 li peng
12 篇 wang jing
12 篇 chang yi

语言

26,127 篇 英文
763 篇 其他
149 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 26991 条记录，以下是141-150 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：

Part-of-Speech and Confusion-Set Constrained language Model for Vietnamese Spelling Correction Corpus Construction 13th

Part-of-Speech and Confusion-Set Constrained Language Model ...

引用

13th international conference on natural language processing and Chinese Computing

作者： Li, Ying Chen, Xin Liu, Xiao Dong, Ling Yu, Zhengtao Mao, Cunli Kunming Univ Sci & Technol Fac Informat Engn & Automat Kunming Yunnan Peoples R China Kunming Univ Sci & Technol Yunnan Key Lab Artificial Intelligence Kunming Yunnan Peoples R China

ISBN: (纸本)9789819794393;9789819794409

Supervised spelling error correction models have achieved outstanding performances on rich-source languages. However, these models are difficult to directly apply to Vietnamese spelling correction due to the corpus scarcity. To address this issue, we first construct a basic high-quality Vietnamese Spelling Correction (ViSC) corpus via automatic speech recognition (ASR) generation and human annotation. Then, we propose a part-of-speech and confusion-set double-constrained method to mimic the practical error distribution and use them as external knowledge to guide the large language models (LLMs) to construct diverse pseudo data. Finally, we exploit pseudo corpora to pre-train and ViSC corpus to fine-tune spelling error correction models. Experiments on the benchmark dataset show that our proposed corpus construction method consistently outperforms various baselines, leading to state-of-the-art results on all Vietnamese-specific pre-trained language model-enhanced spelling correction models. Detailed analysis demonstrates that part-of-speech and confusion-set are complementary and significant in controlling a stable and diverse corpus generation. In-depth comparison experiments reveal that the proper utilization of pseudo corpus is essential for improving Vietnamese spelling error correction. Besides, we release our codes and constructed corpus at https://***/DarkFanta3y/VSEC_corpus to facilitate future research.

关键词： Vietnamse spelling correction Double-constrained corpus construction Large language model

来源：评论

学校读者我要写书评

暂无评论

HGAIS 2024 - Proceedings of the Special Session on Harmonising Generative AI and Semantic Web Technologies, co-located with the 23rd international Semantic Web conference, ISWC 2024

HGAIS 2024 - Proceedings of the Special Session on Harmonisi...

引用

2024 Harmonising Generative AI and Semantic Web Technologies, HGAIS 2024

The proceedings contain 14 papers. The topics discussed include: LLM-based SPARQL query generation from natural language over federated knowledge graphs;a benchmark for the detection of metalinguistic disagreements between LLMs and knowledge graphs;assessing large language models for SPARQL query generation in scientific question answering;benchmarking ontology validation capabilities of LLMs;ontology corpora for LLM-based knowledge engineering research;information for conversation generation: proposals utilizing knowledge graphs;OAEI-LLM: a benchmark dataset for understanding large language model hallucinations in ontology matching;a comprehensive benchmark for evaluating LLM-generated ontologies;and hybrid evaluation of Socratic dialogue for teaching.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of Pre-Trained Transformer-based Models for the Nepali language 1

Development of Pre-Trained Transformer-based Models for the ...

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： Thapa, Prajwal Nyachhyon, Jinu Sharma, Mridul Bal, Bal Krishna Kathmandu University Nepal

ISBN: (纸本)9798891762015

Transformer-based pre-trained language models have dominated the field of natural language processing (NLP) for quite some time now. However, the Nepali language, spoken by approximately 32 million people worldwide, remains significantly underrepresented in this domain. This underrepresentation is primarily attributed to the scarcity of monolingual data corpora and limited available resources for the Nepali language. While existing efforts have predominantly concentrated on basic encoder-based models, there is a notable gap in the exploration of decoder-based architectures. To address this gap, we have collected 27.5 GB of Nepali text data, approximately 2.4x larger than any previously available Nepali language corpus. Leveraging this data, we pre-trained three different models i.e., BERT, RoBERTa, and GPT-2, exclusively for the Nepali language. Furthermore, we performed instruction tuning and explored its potential for monolingual Nepali data, providing a foundation for future research. Our models outperformed the existing best model by 2 points on Nep-gLUE benchmark, scoring 95.60 and also outperformed existing models on text generation tasks, demonstrating improvements in both understanding and generating Nepali text. © 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

Confront Insider Threat: Precise Anomaly Detection in Behavior Logs Based on LLM Fine-Tuning 31

Confront Insider Threat: Precise Anomaly Detection in Behavi...

引用

31st international conference on Computational Linguistics, COLING 2025

作者： Song, Shuang Zhang, Yifei Gao, Neng Institute of Information Engineering Chinese Academy of Sciences China School of Cyber Security University of Chinese Academy of Sciences China Key Laboratory of Cyberspace Security Defense China

ISBN: (纸本)9798891761964

Anomaly-based detection is effective against evolving insider threats but still suffers from low precision. Current data processing can result in information loss, and models often struggle to distinguish between benign anomalies and actual threats. Both issues hinder precise detection. To address these issues, we propose a precise anomaly detection solution for behavior logs based on Large language Model (LLM) fine-tuning. By representing user behavior in natural language, we reduce information loss. We fine-tune the LLM with a user behavior pattern contrastive task for anomaly detection, using a two-stage strategy: first learning general behavior patterns, then refining with user-specific data to improve differentiation between benign anomalies and threats. We also implement a fine-grained threat tracing mechanism to provide behavior-level audit trails. To the best of our knowledge, our solution is the first to apply LLM fine-tuning in insider threat detection, achieving an F1 score of 0.8941 on the CERT v6.2 dataset, surpassing all baselines. © 2025 Association for Computational Linguistics.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Native vs Non-native language Prompting: A Comparative Analysis 25th

Native vs Non-native Language Prompting: A Comparative Analy...

引用

25th international conference on Web Information Systems engineering, WISE 2024

作者： Kmainasi, Mohamed Bayan Khan, Rakif Shahroor, Ali Ezzat Bendou, Boushra Hasanain, Maram Alam, Firoj Qatar University Doha Qatar University of Doha for Science and Technology Doha Qatar Liverpool John Moores University Doha Qatar Carnegie Mellon University in Qatar Ar-Rayyan Qatar Qatar Computing Research Institute Ar-Rayyan Qatar

ISBN: (纸本)9789819605750

Large language models (LLMs) have shown remarkable abilities in different fields, including standard natural language processing (NLP) tasks. To elicit knowledge from LLMs, prompts play a key role, consisting of natural language instructions. Most open and closed source LLMs are trained on available labeled and unlabeled resources-digital content such as text, images, audio, and videos. Hence, these models have better knowledge for high-resourced languages but struggle with low-resourced languages. Since prompts play a crucial role in understanding their capabilities, the language used for prompts remains an important research question. Although there has been significant research in this area, it is still limited, and less has been explored for medium to low-resourced languages. In this study, we investigate different prompting strategies (native vs. non-native) on 11 different NLP tasks associated with 11 different Arabic datasets (8.7K data points). In total, we conducted 198 experiments involving 3 open and closed LLMs (including an Arabic-centric model), and 3 prompting strategies. Our findings suggest that, on average, the non-native prompt performs the best, followed by mixed and native prompts. All prompts will be made available to the community through the LLMeBench (https://***/) framework. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Translation (languages)

来源：评论

学校读者我要写书评

暂无评论

natural language processing in Geographic Information Systems 3

Natural Language Processing in Geographic Information System...

引用

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

作者： Kushmitha, S. Kathrine, Jaspher W. Abisha, M.B. Department of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India

ISBN: (纸本)9798331527549

The integration of Geographic Information Systems (GIS) with natural language processing (NLP) has transformed how spatial data is accessed and utilized. By enabling GIS interfaces to interpret natural language queries, NLP enhances user experience, democratizes geospatial data, and improves query accuracy. This paper reviews state-of-the-art methodologies for geo-parsing, geo-coding, and spatial query interpretation, addressing challenges like geographic ambiguity, imprecise spatial relationships, and scalability limitations. Key contributions include a systematic literature review identifying research gaps such as insufficient context-awareness and a lack of annotated datasets, alongside case studies demonstrating the benefits of NLP integration in applications like disaster management and urban planning. Future opportunities are explored in leveraging deep learning, multimodal data integration, and adaptive user interfaces to further enhance GIS accessibility and usability. Future opportunities are explored in leveraging deep learning for spatial reasoning, integrating multimodal data sources for enhanced decision-making, and developing adaptive user interfaces tailored for diverse audiences. Furthermore, the paper highlights the potential of NLP in generating geo-descriptions for distributed sensor networks, supporting accessibility for impaired users, and enhancing real-time data analysis in smart city initiatives. Addressing these gaps and building scalable frameworks will pave the way for GIS systems that are not only powerful but also inclusive, fostering global accessibility and broader adoption of geospatial technologies. © 2025 IEEE.

关键词： Structured Query language

来源：评论

学校读者我要写书评

暂无评论

A KG-LLM-Based Product2inspection Mapping Approach for Module Prefabrication

A KG-LLM-Based Product2inspection Mapping Approach for Modul...

引用

2024 international conference on Construction and Real Estate Management: ESG Development in the Construction Industry, ICCREM 2024

作者： Dong, Qing Li, Xiao Chen, Taicong Wu, Chengke Dept. of Civil Engineering Univ. of Hong Kong Hong Kong Dept. of Civil Engineering South China Univ. of Technology Guangzhou China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China

ISBN: (数字)9780784485910

ISBN: (纸本)9780784485910

Quality inspection in the production of modular construction (MC) is paramount for the success of MC projects (e.g., geometry errors are sensitive for installation). However, automatic and accurate inspection task generation is still challenging in planning and control, particularly in mass production. To this end, this study aims to develop a knowledge Graph-Large language Model (KG-LLM) based product2inspection mapping approach for MC production. First, a knowledge graph of inspection tasks, MC products, inspection tools, inspection frequencies, operators, and corresponding production tasks is established to enhance LLM with domain knowledge. Then, a prompt-based product2inspection mapping approach using KG-LLM is developed. Finally, the effectiveness of product2inspection is tested on an MC case project within controlled experiments. This study can improve quality inspection collaboration in module prefabrication while exploring the potential of applying Large language Models in the construction domain. © ASCE.

关键词： knowledge graph

来源：评论

学校读者我要写书评

暂无评论

AutoProteinEngine: A Large language Model Driven Agent Framework for Multimodal AutoML in Protein engineering 31

AutoProteinEngine: A Large Language Model Driven Agent Frame...

引用

31st international conference on Computational Linguistics, COLING 2025

作者： Liu, Yungeng Chen, Zan Wang, Yu Guang Shen, Yiqing Toursun Synbio Shanghai China City University of Hong Kong Hong Kong Shanghai Jiao Tong University Shanghai China Johns Hopkins University Baltimore United States

ISBN: (纸本)9798891761971

Protein engineering is important for biomedical applications, but conventional approaches are often inefficient and resource-intensive. While deep learning (DL) models have shown promise, their training or implementation into protein engineering remains challenging for biologists without specialized computational expertise. To address this gap, we propose AutoProteinEngine (AutoPE), an agent framework that leverages large language models (LLMs) for multimodal automated machine learning (AutoML) for protein engineering. AutoPE innovatively allows biologists without DL backgrounds to interact with DL models using natural language, lowering the entry barrier for protein engineering tasks. Our AutoPE uniquely integrates LLMs with AutoML to handle model selection for both protein sequence and graph modalities, automatic hyperparameter optimization, and automated data retrieval from protein databases. We evaluated AutoPE through two real-world protein engineering tasks, demonstrating substantial performance improvements compared to traditional zero-shot and manual fine-tuning approaches. By bridging the gap between DL and biologists’ domain expertise, AutoPE empowers researchers to leverage DL without extensive programming knowledge. ©2025 Association for Computational Linguistics.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing LLMs Contextual knowledge with Ontologies for Personalised Food Recommendation 25th

Enhancing LLMs Contextual Knowledge with Ontologies for Pe...

引用

25th international conference on Web Information Systems engineering, WISE 2024

作者： Bagozi, Ada Bianchini, Devis Melchiori, Michele Rula, Anisa University of Brescia Brescia Italy

ISBN: (纸本)9789819605729

Food recommendation systems help consumers make sustainable and nutritionally complete choices, promoting healthy eating habits and addressing the growing interest in food sustainability and waste reduction. Large language Models (LLMs), such as ChatGPT, are increasingly used for food recommendations due to their natural language processing capabilities. However, providing personalised and contextually relevant suggestions remains challenging because of the lack of a robust conceptualisation of healthy and sustainable food aligned with users’ dietary and lifestyle preferences. Ontologies can address this by offering a structured and semantically rich framework for organising information. In this paper, we propose a modular ontology to enhance the contextual knowledge of LLMs, enabling them to deliver personalised, contextually relevant food recommendations. The ontology’s modules are based on competency questions derived from a research project focused on sustainable and healthy food recommendations. To evaluate the effectiveness of this approach, we conducted experiments where ChatGPT-4 answered these competency questions with and without ontology integration. The answers were then assessed in a user study. Preliminary experimental results indicate significant improvements in the quality and relevance of recommendations when the ontology is employed. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Consumer Empowerment Large language Models Multi-perspective Ontology engineering Sustainable Food Recommendation

来源：评论

学校读者我要写书评

暂无评论

Topology-of-Question-Decomposition: Enhancing Large language Models with Information Retrieval for knowledge-Intensive Tasks 31

Topology-of-Question-Decomposition: Enhancing Large Language...

引用

31st international conference on Computational Linguistics, COLING 2025

作者： Li, Weijie Wang, Jin Yu, Liang-Chih Zhang, Xuejie School of Information Science and Engineering Yunnan University Yunnan China Department of Information Management Yuan Ze University Taiwan

ISBN: (纸本)9798891761964

Large language models (LLMs) are increasingly deployed for general problem-solving across various domains yet remain constrained to chaining immediate reasoning steps and depending solely on parametric knowledge. Integrating an information retrieval system directly into the reasoning process of LLMs can improve answer accuracy but might disrupt the natural reasoning sequence. Consequently, LLMs may underperform in complex, knowledge-intensive tasks requiring multiple reasoning steps, extensive real-world knowledge, or critical initial decisions. To overcome these challenges, we introduce a novel framework, Topology-of-Question-Decomposition (ToQD), which activates retrieval only when necessary. Globally, ToQD guides LLMs in constructing a topology graph from the input question, each node representing a subquestion. Locally, ToQD employs self-verify inference to determine whether a sub-question should retrieve relevant documents, necessitate further decomposition, or directly provide an answer. Experiments demonstrate that ToQD achieves superior performance and robustness in complex, knowledge-intensive tasks, significantly enhancing system response efficiency. The code repository is accessible at https://***/DCVDB/ToQD. © 2025 Association for Computational Linguistics.

关键词： Topology

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 << < 11 12 13 14 15 16 17 18 19 20 > >>

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：