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

14,082 篇 会议
98 册 图书
64 篇 期刊文献
1 篇 资讯

馆藏范围

14,245 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

9,383 篇 工学
- 8,572 篇 计算机科学与技术...
- 6,863 篇 软件工程
- 1,927 篇 信息与通信工程
- 1,310 篇 控制科学与工程
- 1,209 篇 电气工程
- 906 篇 生物工程
- 418 篇 生物医学工程（可授...
- 417 篇 电子科学与技术（可...
- 413 篇 网络空间安全
- 307 篇 化学工程与技术
- 288 篇 仪器科学与技术
- 281 篇 机械工程
- 266 篇 光学工程
- 211 篇 安全科学与工程
- 196 篇 交通运输工程
3,131 篇 理学
- 1,227 篇 数学
- 932 篇 生物学
- 887 篇 物理学
- 486 篇 统计学（可授理学、...
- 460 篇 系统科学
- 355 篇 化学
2,812 篇 管理学
- 1,831 篇 图书情报与档案管...
- 1,191 篇 管理科学与工程(可...
- 463 篇 工商管理
567 篇 医学
- 408 篇 临床医学
- 365 篇 基础医学(可授医学...
- 312 篇 公共卫生与预防医...
- 163 篇 药学(可授医学、理...
450 篇 法学
- 418 篇 社会学
217 篇 教育学
- 213 篇 教育学
194 篇 文学
155 篇 经济学
98 篇 农学
11 篇 艺术学
9 篇 军事学
1 篇 哲学

主题

2,893 篇 natural language...
873 篇 natural language...
822 篇 natural language...
817 篇 semantics
552 篇 deep learning
537 篇 machine learning
514 篇 sentiment analys...
508 篇 data mining
390 篇 knowledge engine...
360 篇 computational mo...
358 篇 training
356 篇 large language m...
315 篇 speech recogniti...
310 篇 feature extracti...
302 篇 speech processin...
272 篇 signal processin...
261 篇 accuracy
239 篇 neural networks
235 篇 knowledge based ...
234 篇 transformers

机构

55 篇 institute of inf...
50 篇 school of cyber ...
50 篇 school of commun...
40 篇 maharishi school...
38 篇 chitkara univers...
35 篇 lovely professio...
34 篇 university of ch...
34 篇 school of comput...
32 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...
20 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
11 篇 li sheng
11 篇 yang yang
11 篇 tao zhang
11 篇 li ying
11 篇 arora chetan
11 篇 wang wei

语言

11,805 篇 英文
2,409 篇 其他
49 篇 中文
3 篇 土耳其文

检索条件"任意字段=IEEE International Conference on Natural Language Processing and Knowledge Engineering"

共 14245 条记录，以下是81-90 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：

Human review for post-training improvement of low-resource language performance in large language models 12

Human review for post-training improvement of low-resource l...

引用

12th ieee international conference on Healthcare Informatics (ieee-ICHI)

作者： Lewis, Delta-Marie Phiri, Everlisto DeRenzi, Brian Chifisi, Lyness Misomali, Amos Makwenda, Charles Nyirenda, Themba Lesh, Neal Dimagi Inc Cambridge MA 02139 USA Pachi Lilongwe Malawi Dimagi Inc Oxford England Dimagi Inc Lilongwe Malawi

ISBN: (纸本)9798350383744;9798350383737

Large language models (LLMs) have significantly improved natural language processing, holding the potential to support health workers and their clients directly. Unfortunately, there is a substantial and variable drop in performance for low-resource languages. This paper presents an exploratory case study in Malawi, aiming to enhance the performance of LLMs in Chichewa through innovative prompt engineering techniques. By focusing on practical evaluations over traditional metrics, we assess the subjective utility of LLM outputs, prioritizing end-user satisfaction. Our findings suggest that tailored prompt engineering may improve LLM utility in underserved linguistic contexts, offering a promising avenue to bridge the language inclusivity gap in digital health interventions.

关键词： Large language models prompt engineering low-resource languages

来源：评论

学校读者我要写书评

暂无评论

INTERPRETABLE VISUAL QUESTION ANSWERING REFERRING TO OUTSIDE knowledge 30

INTERPRETABLE VISUAL QUESTION ANSWERING REFERRING TO OUTSIDE...

引用

30th ieee international conference on Image processing (ICIP)

作者： Zhu, He Togo, Ren Ogawa, Takahiro Haseyama, Miki Hokkaido Univ Grad Sch Informat Sci & Technol Sapporo Hokkaido Japan Hokkaido Univ Fac Informat Sci & Technol Sapporo Hokkaido Japan

ISBN: (纸本)9781728198354

We present a novel multimodal interpretable VQA model that can answer the question more accurately and generate diverse explanations. Although researchers have proposed several methods that can generate human-readable and fine-grained natural language sentences to explain a model's decision, these methods have focused solely on the information in the image. Ideally, the model should refer to various information inside and outside the image to correctly generate explanations, just as we use background knowledge daily. The proposed method incorporates information from outside knowledge and multiple image captions to increase the diversity of information available to the model. The contribution of this paper is to construct an interpretable visual question answering model using multimodal inputs to improve the rationality of generated results. Experimental results show that our model can outperform state-of-the-art methods regarding answer accuracy and explanation rationality.

关键词： Visual question answering interpretable machine learning outside knowledge learning natural language explanations

来源：评论

学校读者我要写书评

暂无评论

HINT-ENHANCED IN-CONTEXT LEARNING WAKES LARGE language MODELS UP FOR knowledge-INTENSIVE TASKS 49

HINT-ENHANCED IN-CONTEXT LEARNING WAKES LARGE LANGUAGE MODEL...

引用

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

作者： Wang, Yifan Guo, Qingyan Ni, Xinzhe Shi, Chufan Liu, Lemao Jiang, Haiyun Yang, Yujiu Tsinghua Univ Tsinghua Shenzhen Int Grad Sch Shenzhen Peoples R China Tencent AI Lab Shenzhen Peoples R China

ISBN: (纸本)9798350344868;9798350344851

In-context learning (ICL) ability has emerged with the increasing scale of large language models (LLMs), enabling them to learn input-label mappings from demonstrations and perform well on downstream tasks. However, under the standard ICL setting, LLMs may sometimes neglect query-related information in demonstrations, leading to incorrect predictions. To address this limitation, we propose a new paradigm called Hint-enhanced In-Context Learning (HICL) to explore the power of ICL in open-domain question answering, an important form in knowledge-intensive tasks. HICL leverages LLMs' reasoning ability to extract query-related knowledge from demonstrations, then concatenates the knowledge to prompt LLMs in a more explicit way. Furthermore, we track the source of this knowledge to identify specific examples, and introduce a Hint-related Example Retriever (HER) to select informative examples for enhanced demonstrations. We evaluate HICL with HER on 3 open-domain QA benchmarks, and observe average performance gains of 2.89 EM score and 2.52 F1 score on gpt-3.5-turbo, 7.62 EM score and 7.27 F1 score on LLaMA-2-Chat-7B compared with standard setting.

关键词： Large language model in-context learning retrieval model open-domain question answering

来源：评论

学校读者我要写书评

暂无评论

A Graph Attention Network Combining Community Detection and natural language processing to Predict Metabolite-Disease Associations 5

A Graph Attention Network Combining Community Detection and ...

引用

5th international conference on Computer engineering and Application (ICCEA)

作者： Zhou, Jiejun Lanzhou Univ Technol Sch Comp & Commun Lanzhou Peoples R China

ISBN: (纸本)9798350386783;9798350386776

In view of the limitation of existing research, which primarily relies on similarity as input features for the model without considering the extraction of features from the intrinsic information of metabolite or disease, and only focuses on the existing associations between metabolite and disease while neglecting their potential associations, this study proposes the GCDNLP model, a graph attention network that combines community detection and natural language processing to predict metabolite-disease associations. Firstly, the Mol2Vec algorithm is employed to extract the ontological features of metabolite from the perspective of their molecular structures, which are then combined with the metabolite similarity features. Secondly, the Doc2Vec+ TF-IDF algorithm is introduced to compute the ontological features of disease. Finally, the prior probability matrix construction algorithm PPMCD based on community detection is proposed to uncover the unconfirmed potential associations between metabolite and disease within the network. The computed results, represented as prior probabilities, are then integrated with the graph attention network for further processing. Experimental results demonstrate the superiority of this model over existing algorithms in multiple evaluation metrics.

关键词： complex networks link prediction natural language processing community detection graph attention networks

来源：评论

学校读者我要写书评

暂无评论

Create, Explore and Analyse traceability knowledge graphs 31

Create, Explore and Analyse traceability knowledge graphs

引用

31st ieee international Requirements engineering conference (RE)

作者： Radhakrishnan, Sruthi Cecchettini, Ario Giancarlo Wendler, Svenja Graf, Andreas itemis AG CC Adv Engn Lunen Germany

ISBN: (纸本)9798350326918

"Glad you introduced a traceability process in your company. Now you are able to relate the various types of artifacts in order to build up a large traceability graph" - what are the next steps? How do you deal with the enormous amount of information? We provide use cases to create, analyse and explore traceability graphs, based on our experiences from itemis ANALYZE, our professional traceability management system, that connect your whole development toolchain, including modelling tools and code. Furthermore, we fine-grain the 'requirements' in traceability by emerging Machine learning (ML) techniques that aid in analysing their similarities thereby proposing a tailored solution which forms the basis for requirements -specific knowledge graph. Finally, we use graph-based algorithms to analyse different use-case of created knowledge graphs.

关键词： Traceability Graphs natural language processing Machine learning Graph analysis

来源：评论

学校读者我要写书评

暂无评论

The Impact of Large language Modeling on natural language processing in Legal Texts: A Comprehensive Survey 15

The Impact of Large Language Modeling on Natural Language Pr...

引用

15th international conference on knowledge and Systems engineering, KSE 2023

作者： Anh, Dang Hoang Do, Dinh-Truong Tran, Vu Minh, Nguyen Le Japan Advanced Institute of Science and Technology Japan The Institute of Statistical Mathematics Japan

ISBN: (纸本)9798350329742

natural language processing (NLP) has witnessed significant advancements in recent years, particularly with the emergence of large language models. These models, such as GPT-3.5 and its variants, have revolutionized various domains, including legal text processing (LTP). This survey explores the impact of large language modeling on NLP in the context of legal texts. By analyzing the latest research and developments, we seek to understand the benefits, challenges, and potential applications of large language models in the field of legal language processing. © 2023 ieee.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Towards Utilizing natural language processing Techniques to Assist in Software engineering Tasks 23

Towards Utilizing Natural Language Processing Techniques to ...

引用

45th ieee/ACM international conference on Software engineering (ICSE)

作者： Ding, Zishuo Concordia Univ Montreal PQ Canada

ISBN: (纸本)9798350322637

Machine learning-based approaches have been widely used to address natural language processing (NLP) problems. Considering the similarity between natural language text and source code, researchers have been working on applying techniques from NLP to deal with code. On the other hand, source code and natural language are by nature different. For example, code is highly structured and executable. Thus, directly applying the NLP techniques may not be optimal, and how to effectively optimize these NLP techniques to adapt to software engineering (SE) tasks remains a challenge. Therefore, to tackle the challenge, in this dissertation, we focus on two research directions: 1) distributed code representations, and 2) logging statements, which are two important intersections between the natural language and source code. For distributed code representations, we first discuss the limitations of existing code embedding techniques, and then, we propose a novel approach to learn more generalizable code embeddings in a task-agnostic manner. For logging statements, we first propose an automated deep learning-based approach to automatically generate accurate logging texts by translating the related source code into short textual descriptions. Then, we make the first attempt to comprehensively study the temporal relations between logging and its corresponding source code, which is later used to detect issues in logging statements. We anticipate that our study can provide useful suggestions and support to developers in utilizing NLP techniques to assist in SE tasks.

关键词： code embeddings logging natural language processing

来源：评论

学校读者我要写书评

暂无评论

Research and Applications of Large language Models for Converting Unstructured Data into Structured Data 3

Research and Applications of Large Language Models for Conve...

引用

3rd international conference on Cloud Computing, Big Data Application and Software engineering, CBASE 2024

作者： Liu, Xiangfeng Sun, Jianting Lei, Aidi Zhu, Junzhi Co. Ltd Chengdu610073 China University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu China

ISBN: (纸本)9798331506582

The rapid growth of data has led to a significant increase in unstructured data, such as text, audio, and images, which dominate modern information processing. However, the complexity of unstructured data presents challenges for automated analysis and processing. Converting unstructured data into structured formats is crucial for tasks like data mining, information extraction, and knowledge graph construction. Traditional methods that rely on manual rules or statistical models struggle with complex, context-dependent data. Recently, large language models (LLMs), such as GPT-4 and BERT, have demonstrated great potential in unstructured data processing due to their powerful natural language understanding and generation capabilities. This study explores the application of large language models in transforming unstructured data into structured formats. It begins by reviewing the limitations of traditional approaches and then presents a framework for unstructured data processing using LLMs, covering data preprocessing, information extraction, and structured representation. The study's experiments demonstrate the superior performance of LLMs in handling various types of unstructured data, particularly in tasks like named entity recognition, relation extraction, and contextual understanding. The results show that LLMs achieve higher accuracy and generalization while reducing reliance on manual rules. The paper discusses the strengths and limitations of this method, proposing future improvements, such as combining domain-specific knowledge for model optimization and expanding applications to multimodal data processing. The research highlights the promising role of large language models in converting unstructured data into structured formats. © 2024 ieee.

关键词： Structured Query language

来源：评论

学校读者我要写书评

暂无评论

knowledge Graph Indexing Enhanced Q&A System Based on Large language Model 4

Knowledge Graph Indexing Enhanced Q&A System Based on Large ...

引用

4th international conference on Electronic Information engineering and Computer Science, EIECS 2024

作者： Sun, Jiawei Zhang, Quan Zhi, Yongqi Ling, Weiqing Cims Research Center School of Electronic and Information Engineering Tongji University Shanghai China

ISBN: (纸本)9798331531409

With the advent of the digital age, the explosive growth of data has brought unprecedented opportunities and challenges to societal development. The rapid evolution of data science is driving innovation and progress across various industries. Both the business and academic communities recognize the immense potential hidden within vast amounts of data. Extracting truly valuable information from this data has become a critical issue that needs to be addressed. As technology advances swiftly and data accumulates rapidly, traditional processing and analysis methods can no longer keep up with the current volume and velocity of data. This has prompted data professionals to seek innovative solutions to handle increasingly complex and massive data relationships and quantities. Against this backdrop, two key technologies have emerged due to their exceptional performance-knowledge graphs and large language models © 2024 ieee.

关键词： knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Requirements Satisfiability with In-Context Learning 32

Requirements Satisfiability with In-Context Learning

引用

32nd ieee international Requirements engineering conference (RE)

作者： Santos, Sarah Breaux, Travis Norton, Thomas Haghighi, Sara Ghanavati, Sepideh Carnegie Mellon Univ Sch Comp Sci Pittsburgh PA 15213 USA Fordham Univ Sch Law New York NY 10023 USA Univ Maine Sch Comp & Informat Orono ME USA

ISBN: (纸本)9798350395129;9798350395112

language models that can learn a task at inference time, called in-context learning (ICL), show increasing promise in natural language inference tasks. In ICL, a model user constructs a prompt to describe a task with a natural language instruction and zero or more examples, called demonstrations. The prompt is then input to the language model to generate a completion. In this paper, we apply ICL to the design and evaluation of satisfaction arguments, which describe how a requirement is satisfied by a system specification and associated domain knowledge. The approach builds on three prompt design patterns, including augmented generation, prompt tuning, and chain-of-thought prompting, and is evaluated on a privacy problem to check whether a mobile app scenario and associated design description satisfies eight consent requirements from the EU General Data Protection Regulation (GDPR). The overall results show that GPT-4 can be used to verify requirements satisfaction with 96.7% accuracy and dissatisfaction with 93.2% accuracy. Inverting the requirement improves verification of dissatisfaction to 97.2%. Chain-of-thought prompting improves overall GPT3.5 performance by 9.0% accuracy. We discuss the trade-offs among templates, models and prompt strategies and provide a detailed analysis of the generated specifications to inform how the approach can be applied in practice.

关键词： requirements satisfaction arguments language models

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 << < 5 6 7 8 9 10 11 12 13 14 > >>

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：