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

26,554 篇 会议
407 册 图书
372 篇 期刊文献
3 篇 学位论文
1 篇 资讯

馆藏范围

27,336 篇 电子文献
2 种 纸本馆藏

日期分布

学科分类号

16,532 篇 工学
- 15,140 篇 计算机科学与技术...
- 11,306 篇 软件工程
- 2,792 篇 信息与通信工程
- 1,788 篇 控制科学与工程
- 1,560 篇 电气工程
- 1,411 篇 生物工程
- 626 篇 生物医学工程（可授...
- 610 篇 化学工程与技术
- 556 篇 机械工程
- 514 篇 电子科学与技术（可...
- 476 篇 网络空间安全
- 397 篇 仪器科学与技术
- 375 篇 光学工程
- 280 篇 安全科学与工程
5,083 篇 理学
- 2,074 篇 数学
- 1,471 篇 物理学
- 1,470 篇 生物学
- 786 篇 统计学（可授理学、...
- 620 篇 系统科学
- 617 篇 化学
4,742 篇 管理学
- 3,171 篇 图书情报与档案管...
- 1,852 篇 管理科学与工程(可...
- 775 篇 工商管理
839 篇 医学
- 611 篇 临床医学
- 569 篇 基础医学(可授医学...
- 393 篇 公共卫生与预防医...
- 250 篇 药学(可授医学、理...
684 篇 法学
- 602 篇 社会学
573 篇 文学
- 401 篇 外国语言文学
454 篇 教育学
- 443 篇 教育学
252 篇 经济学
177 篇 农学
19 篇 艺术学
17 篇 军事学
1 篇 哲学

主题

5,705 篇 natural language...
1,726 篇 natural language...
1,556 篇 semantics
1,445 篇 natural language...
1,195 篇 sentiment analys...
1,192 篇 machine learning
1,150 篇 deep learning
986 篇 accuracy
923 篇 training
812 篇 data mining
799 篇 computational mo...
799 篇 feature extracti...
772 篇 artificial intel...
543 篇 knowledge engine...
525 篇 speech recogniti...
523 篇 large language m...
514 篇 transformers
495 篇 data models
466 篇 information retr...
464 篇 support vector m...

机构

58 篇 chitkara univers...
52 篇 lovely professio...
49 篇 school of comput...
33 篇 university of ch...
32 篇 school of comput...
31 篇 centre of interd...
31 篇 xi'an university...
30 篇 school of comput...
30 篇 tsinghua univers...
28 篇 school of comput...
28 篇 microsoft resear...
27 篇 school of inform...
26 篇 zhejiang univers...
26 篇 school of comput...
24 篇 institute of inf...
23 篇 school of inform...
23 篇 department of co...
22 篇 beijing univ pos...
21 篇 college of compu...
21 篇 school of inform...

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 liu ying
14 篇 li sheng
14 篇 wu jin
14 篇 zhang lei
14 篇 liu jun
14 篇 lei li
13 篇 li yang
13 篇 li li
13 篇 shanmugasundaram...
13 篇 f. ren
12 篇 li peng

语言

26,360 篇 英文
874 篇 其他
152 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 27338 条记录，以下是551-560 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：

Case Study in Developing Extensible Virtual Assistant Using Genie Framework 1

引用

13th international conference on Frontier Computing, FC 2023

作者： Wu, Yi-Ting Chang, Albert Tsai, Yu Hung Wang, Po-Chuan Chen, Tinghao Lin, Jeng-Wei Tunghai University Taichung407224 Taiwan BSI Pacific Taiwan Branch Taipei11492 Taiwan

ISBN: (数字)9789819993420

ISBN: (纸本)9789819993413

Deep learning has made significant improvement in natural language processing. Nowadays virtual assistants or chatbots attract attention of many researchers and are expected to be applied in more and more areas. We had designed and implemented an extensible financial virtual assistant using Genie framework. A new device (or skill) is developed to offer financial services in backend server cloud. The device and supported APIs (Application Programming Interface) are registered in an open repository Thingpedia. When Genie receives user utterances, it translates them into ThingTalk programs using a large deep-learning neural networks. Then, Genie executes the ThingTalk programs, which may invoke the financial services through the registered APIs. ThingTalk is a declarative programming language. Domain experts can easily describe financial services in high-level viewpoint with minimal knowledge and experiences of computer programming and system development, while complex services are implemented in backend servers and access through APIs. As a result, domain experts and computer engineers together can fast and easily build a virtual assistant that support natural language interface. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Investigating on the External knowledge in RAG for Zero-Shot Cross-language Transfer 4

Investigating on the External Knowledge in RAG for Zero-Shot...

引用

4th IEEE international conference on Electronic Technology, Communication and Information, ICETCI 2024

作者： Wang, Wenmin Zhang, Peilin Liu, Ge Wu, Ruihua Song, Guixiang China Mobile Online Service Co. Ltd. Zhengzhou450000 China

ISBN: (纸本)9798350361643

In the field of multilingual natural language processing (NLP), zero-shot cross-language transfer is an important research direction, which aims to enable models to effectively learn and reason without target language training data. This study explores the role of external knowledge in the Retrieval-Augmented Generation (RAG) model to improve the performance of zero-shot cross-lingual transfer. This paper proposes a new model architecture that enriches the knowledge base of the RAG model by integrating external knowledge bases, thereby enhancing its information bridging capabilities between source and target languages. In the experimental section, this paper conducts experiments using multiple cross-language tasks, including machine translation, question answering, and text summarization, to evaluate the performancen and domain of the model in different languages. The experimental results indicate that introducing external knowledge sources significantly improves the accuracy and robustness of the model, especially in resource-scarce language pairs. This research not only provides an effective solution for zero-shot cross-language transfer, but also provides new insights into understanding the role of external knowledge in improving the performance of NLP models. © 2024 IEEE.

关键词： knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

Request for Information (RFI) Recommender System for Pre-Construction Design Review Application Using natural language processing, Chat-GPT, and Computer Vision

Request for Information (RFI) Recommender System for Pre-Con...

引用

ASCE international conference on Computing in Civil engineering (I3CE)

作者： Panahi, Roshan Kivlin, John-Paul Louis, Joseph Oregon State Univ Sch Civil & Construct Engn Corvallis OR 97331 USA Skanska Portland OR USA Oregon State Univ Dept Civil & Construct Engn Corvallis OR 97331 USA

ISBN: (数字)9780784485224

ISBN: (纸本)9780784485224

Design reviews are critical for construction projects to reduce costly reworks and future conflicts. However, this is a challenging task due to uncertainties during the initial stages of a project, which can lead to numerous requests for information (RFIs). With the recent advancements in language models and computer vision, a large volume of historical RFIs can be leveraged to aid design reviews. This study proposes a novel framework using natural language processing, ChatGPT API, and computer vision techniques to identify the RFIs from previous projects that are more likely to reoccur in the project under review. The framework was tested using RFI data from 19 healthcare construction projects, and a web application was used to evaluate user experiences with the tool. Successful implementation of the proposed framework could reduce the number of RFIs, change orders, rework by contractors, and the likelihood of time and cost overruns for construction projects.

关键词： design review request for information (RFI) natural language processing computer vision Chat-GPT

来源：评论

学校读者我要写书评

暂无评论

Adaptive Online Design knowledge Push Method Based on Context Navigation 2

Adaptive Online Design Knowledge Push Method Based on Contex...

引用

2nd international conference on Design Science, ICDS 2024

作者： Wei, Wei Liu, Meng-Hui Huang, Yu-Zhe Beihang University School of Mechanical Engineering & Automation Beijing China

ISBN: (纸本)9798350376289

To address the time-consuming issue of finding relevant design knowledge in product design, this study proposes a context-based adaptive online design knowledge push method. This method constructs a multi-dimensional design context model that includes task context models and user context models and proposes an update mechanism for these models. A database containing the mapping relationships and mapping values between knowledge ontologies and knowledge context models is established. Based on this, the TF-IDF algorithm is used to calculate the matching values between the required design knowledge context model and the actual design task context. Combining the mapping values of knowledge ontologies and knowledge context models, the relevance between the knowledge ontology and the actual design task is calculated. A knowledge list is generated in descending order of relevance and pushed to the user. Finally, this method is applied to a product adaptive online design technology platform, enabling the push of the most relevant knowledge to specific users at the right time, thereby reducing the time designers spend on knowledge retrieval and improving design efficiency and quality. © 2024 IEEE.

关键词： context models knowledge matching natural language processing Self-adaptive knowledge push

来源：评论

学校读者我要写书评

暂无评论

Med-Chat: Tuning ChatGLM3-6B with Chinese Medical Dialogue 6

Med-Chat: Tuning ChatGLM3-6B with Chinese Medical Dialogue

引用

6th international conference on Robotics, Intelligent Control and Artificial Intelligence, RICAI 2024

作者： Chu, Jiqing Sun, Youqiang Huang, He Liu, Yuan School of Electronic and Information Engineering Anhui Jianzhu University Anhui Hefei China Hefei Institutes of Physical Science Chinese Academy of Sciences Hefei China Co. Ltd. Hefei China

ISBN: (纸本)9798331541699

Large language models (LLMs) have demonstrated significant success across a range of natural language processing tasks in general-purpose domains. However, due to limited specialized knowledge, LLMs sometimes generate responses that inaccurately represent medical facts, commonly referred to as hallucinations. Hallucinations provide possible hazards while using LLM in a medical context, including the possibility of misdiagnosis. To address this issue, we utilize the publicly available medical dialogue dataset DISC-Med-SFT, fine-tune the general model ChatGLM3-6B employing the LoRA method, and construct a dedicated medical knowledge base to provide a reliable source of information. Additionally, cascade deduplication is applied to the model’s generated responses to further enhance accuracy and consistency. Experimental results indicate that, compared to the baseline model ChatGLM3-6B, Med-Chat shows notable improvements in both BLEU and F1 score metrics. The resulting Chinese medical LLM, Med-Chat, demonstrates the capability to produce accurate, coherent responses and possesses fundamental medical question-answering skills. © 2024 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

Designing an Interpretable Question Answering System for Vertical Domains Based on Large language Model and knowledge Graph 5

Designing an Interpretable Question Answering System for Ver...

引用

5th Asia-Pacific conference on Image processing, Electronics and Computers, IPEC 2024

作者： Huang, Xiaobin Ku, Chin Soon Xiamen University of Technology Xiamen China Department of Computer Science Universiti Tunku Abdul Rahman Kampar 31900 Malaysia

ISBN: (纸本)9781643685243

Given the low interpretability of large language models (LLMs) due to their extensive parameters and intricate features, this study aims to enhance the understandability and interpretability of automatic QA systems powered by LLMs, thereby addressing a critical gap in the field. To achieve this, we introduce an interpretable architecture for a domain-specific LLM-based question-answering (QA) system. The research decomposes the QA system into six modules: operation recognition, intent recognition, normalization, triplet structured data conversion, knowledge graph querying, and query result processing. Through this approach, the input and output of each module in the QA system are human-readable text data, enhancing the interpretability of the QA system's processing. The use of knowledge graph data increases the credibility of the answers provided by the QA system. The QA system architecture proposed in this study attempts to integrate the powerful natural language understanding capabilities of large language models with the data querying capacity of knowledge graphs, offering a reference for addressing the issue of low interpretability in automatic QA systems based on large language models (LLMs). © 2024 The Authors.

关键词： knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Research on Deaf-Mute People Translation System Based on natural language processing 5

Research on Deaf-Mute People Translation System Based on Nat...

引用

5th international conference on Artificial Intelligence and Computer engineering, ICAICE 2024

作者： Zhang, Tianyi Liao, Sherry Shanghai No.8 High School Shanghai China Qsi International School Shenzhen China

ISBN: (纸本)9798331528911

Sign language is a vital mode of communication for deaf individuals, yet it frequently proves challenging to convey messages to hearing people. The preceding two-way interaction system was found to be ineffective. Furthermore, convolutional neural network-based devices are also susceptible to interference in complex environments, which affects the recognition effect. The objective of the model proposed in this work is to address the communication barriers between deaf-mute and hearing-friendly people, primarily through the utilisation of sign language interpretation. The initial stage of the process involved the utilisation of a convolutional neural network (CNN) to facilitate gesture recognition, capture the intricate details of sign language actions, and integrate deep learning methodologies to extract the distinctive features of gesture images. Subsequently, a natural language processing model is employed to combine the visual features with the language model, thereby facilitating accurate translation from sign language to spoken language. To enhance recognition capabilities in complex settings, the system employs multimodal data fusion technology, integrating gesture actions and contextual semantic data to bolster the reliability and precision of translation. The experimental analysis demonstrates that the model exhibits high accuracy and efficiency in translation and interaction across a range of scenarios. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Analyzing And Editing Inner Mechanisms of Backdoored language Models 24

Analyzing And Editing Inner Mechanisms of Backdoored Languag...

引用

6th ACM conference on Fairness, Accountability, and Transparency (ACM FAccT)

作者： Lamparth, Max Reuel, Anka Stanford Univ Stanford CA 94305 USA

ISBN: (纸本)9798400704505

Poisoning of data sets is a potential security threat to large language models that can lead to backdoored models. A description of the internal mechanisms of backdoored language models and how they process trigger inputs, e.g., when switching to toxic language, has yet to be found. In this work, we study the internal representations of transformer-based backdoored language models and determine early-layer MLP modules as most important for the backdoor mechanism in combination with the initial embedding projection. We use this knowledge to remove, insert, and modify backdoor mechanisms with engineered replacements that reduce the MLP module outputs to essentials for the backdoor mechanism. To this end, we introduce PCP ablation, where we replace transformer modules with low-rank matrices based on the principal components of their activations. We demonstrate our results on backdoored toy, backdoored large, and non-backdoored open-source models. We show that we can improve the backdoor robustness of large language models by locally constraining individual modules during fine-tuning on potentially poisonous data sets. Trigger warning: Offensive language.

关键词： Interpretability Backdoor Attacks Backdoor Defenses natural language processing Safety

来源：评论

学校读者我要写书评

暂无评论

Extracting Domain Models from Textual Requirements in the Era of Large language Models

Extracting Domain Models from Textual Requirements in the Er...

引用

ACM/IEEE international conference on Model Driven engineering languages and Systems (MODELS)

作者： Arulmohan, Sathurshan Meurs, Marie-Jean Mosser, Sebastien McMaster Univ CAS Hamilton ON Canada McSCert Hamilton ON Canada Univ Quebec Montreal CIRST Montreal PQ Canada

ISBN: (纸本)9798350324983

Requirements engineering is a critical part of the software lifecycle, describing what a given piece of software will do (functional) and how it will do it (non-functional). Requirements documents are often textual, and it is up to software engineers to extract the relevant domain models from the text, which is an error-prone and time-consuming task. Considering the recent attention gained by Large language Models (LLMs), we explored how they could support this task. This paper investigates how such models can be used to extract domain models from agile product backlogs and compare them to (i) a state-of-practice tool as well as (ii) a dedicated natural language processing (NLP) approach, on top of a reference dataset of 22 products and 1, 679 user stories. Based on these results, this paper is a first step towards using LLMs and/or tailored NLP to support automated requirements engineering thanks to model extraction using artificial intelligence.

关键词： Domain Modeling natural language processing Large language Models Concept Extraction User stories

来源：评论

学校读者我要写书评

暂无评论

natural language processing Algorithms for Academic Content Generation 4

Natural Language Processing Algorithms for Academic Content ...

引用

4th IEEE international conference on Advanced Learning Technologies for Education and Research, ICALTER 2024

作者： Paredes-Vargas, Alfredo Salinas-Llorca, Piero Santisteban, Jose Information Systems Engineering Universidad Peruana de ciencias Aplicadas UPC Lima Peru Information Systems Engineering Universidad Peruana de Ciencias Aplicadas Lima Peru

ISBN: (纸本)9798331510244

This study has conducted several activities to analyze and compare the performance of five natural language processing (NLP) models: GPT-3, T5, ERNIE, BERT, and XLNet for generating academic content in universities located in Lima, Peru. Some NLP models, including GPT and BERT, were assessed based on accuracy, quality, speed, and customization capabilities. The research examined the use of various algorithms for academic tasks like essay and summary creation. The findings show that all models perform adequately;however, some excel in generating coherent content tailored to different academic styles, thereby optimizing the time of both students and teachers. In conclusion, the ERNIE model emerges as one of the best, as it enables the generation of diverse and high-quality content efficiently. © 2024 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 << < 52 53 54 55 56 57 58 59 60 61 > >>

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：