检索结果-内蒙古大学图书馆

Continuous knowledge graph refinement With Confidence Propagation

IEEE ACCESS 2023年 11卷 59226-59237页

作者： Huseynli, Alisettar Akcayol, M. Ali Gazi Univ Fac Engn Grad Sch Nat & Appl Sci Dept Comp Engn TR-06560 Ankara Turkiye

Although knowledge graphs (KGs) are widely used, they suffer from hosting false information. In the literature, many studies have been carried out to eliminate this deficiency. These studies correct triples, relations, relation types, and literal values or enrich the KG by generating new triples and relations. The proposed methods can be grouped as closed-world approaches that take into account the KG itself or open-world approaches using external resources. The recent studies also considered the confidence of triples in the refinement process. The confidence values calculated in these studies affect either the triple itself or the ground rule for rule-based models. In this study, a propagation approach based on the confidence of triples has been proposed for the refinement process. This method ensures that the effect of confidence spreads over the KG without being limited to a single triple. This makes the KG continuously more stable by strengthening strong relationships and eliminating weak ones. Another limitation of the existing studies is that they handle refinement as a one-time operation and do not give due importance to process performance. However, real-world KGs are live, dynamic, and constantly evolving systems. Therefore, the proposed approach should support continuous refinement. To measure this, experiments were carried out with varying data sizes and rates of false triples. The experiments have been performed using the FB15K, NELL, WN18, and YAGO3-10 datasets, which are commonly used in refinement studies. Despite the increase in data size and false information rate, an average accuracy of 90% and an average precision of 98% have been achieved across all datasets.

关键词： Continuous refinement knowledge graph refinement propagation triple confidence

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Refining knowledge graphs: A Survey

引用

ACM COMPUTING SURVEYS 2024年第6期56卷 1页

作者： Subagdja, Budhitama Shanthoshigaa, D. Wang, Zhaoxia Tan, Ah-Hwee Singapore Management Univ Sch Comp & Informat Syst Singapore 178902 Singapore

knowledge graph (KG) refinement refers to the process of filling in missing information, removing redundancies, and resolving inconsistencies in KGs. With the growing popularity of KG in various domains, many techniques involving machine learning have been applied, but there is no survey dedicated to machine learning-based KG refinement yet. Based on a novel framework following the KG refinement process, this article presents a survey of machine learning approaches to KG refinement according to the kind of operations in KG refinement, the training datasets, mode of learning, and process multiplicity. Furthermore, the survey aims to provide broad practical insights into the development of fully automated KG refinement.

关键词： knowledge graphs knowledge graph refinement

来源：评论

学校读者我要写书评

暂无评论

AI Supported knowledge graph Design and Generation

AI Supported Knowledge Graph Design and Generation

引用

21st International Conference on The Semantic Web (ESWC)

作者： Ratta, Marco Open Univ Walton Hall Milton Keynes Bucks England

ISBN: (纸本)9783031789540;9783031789557

knowledge graphs (KG) have risen to be a powerful mechanism to represent data. Despite this most data sources are generally still represented via heterogeneous non-graph data structures. Converting these into KGs necessitates considerable effort from experts, proving this to be a time consuming process. While tools have been developed to aid KG builders, a gap still exists in terms of technologies that support the automation of designing KG building pipelines. Addressing this gap motivates this research. The aim is to first understand the problem at the knowledge level and, inspired by the recent release of generative tools such as GPT-Engineer, to put forward a conversational agent aimed at assisting the user in building their pipelines. We report on the preliminary findings that we have so far reached during the first year of research in deriving the requirements for building KG generating pipelines from the literature.

关键词： knowledge graph Generation knowledge graph Design Artificial Intelligence knowledge graph refinement

来源：评论

学校读者我要写书评

暂无评论

Evaluating Class Membership Relations in knowledge graphs Using Large Language Models

Evaluating Class Membership Relations in Knowledge Graphs Us...

引用

21st International Conference on The Semantic Web (ESWC)

作者： Allen, Bradley P. Groth, Paul T. Univ Amsterdam Amsterdam Netherlands

ISBN: (纸本)9783031789519;9783031789526

A backbone of knowledge graphs are their class membership relations, which assign entities to a given class. As part of the knowledge engineering process, we propose a new method for evaluating the quality of these relations by processing descriptions of a given entity and class using a zero-shot chain-of-thought classifier that uses a natural language intensional definition of a class. We evaluate the method using two publicly available knowledge graphs, Wikidata and CaLigraph, and 7 large language models. Using the gpt-4-0125-preview large language model, the method's classification performance achieves a macro-averaged F1-score of 0.830 on data from Wikidata and 0.893 on data from CaLigraph. Moreover, a manual analysis of the classification errors shows that 40.9% of errors were due to the knowledge graphs, with 16.0% due to missing relations and 24.9% due to incorrectly asserted relations. These results show how large language models can assist knowledge engineers in the process of knowledge graph refinement. The code and data are available on Github (https://***/bradleypallen/evaluating-kg-class-memberships-using-llms).

关键词： knowledge engineering large language models knowledge graph refinement natural language generation

来源：评论

学校读者我要写书评

暂无评论

Active Ensemble Learning for knowledge graph Error Detection 23

Active Ensemble Learning for Knowledge Graph Error Detection

引用

16th International Conference on Web Search and Data Mining

作者： Dong, Junnan Zhang, Qinggang Huang, Xiao Tan, Qiaoyu Zha, Daochen Zhao, Zihao Hong Kong Polytech Univ Hung Hom Hong Kong Peoples R China Texas A&M Univ College Stn TX USA Rice Univ Houston TX USA

ISBN: (纸本)9781450394079

knowledge graphs (KGs) could effectively integrate a large number of real-world assertions, and improve the performance of various applications, such as recommendation and search. KG error detection has been intensively studied since real-world KGs inevitably contain erroneous triples. While existing studies focus on developing a novel algorithm dedicated to one or a few data characteristics, we explore advancing KG error detection by assembling a set of state-of-the-art (SOTA) KG error detectors. However, it is nontrivial to develop a practical ensemble learning framework for KG error detection. Existing ensemble learning models heavily rely on labels, while it is expensive to acquire labeled errors in KGs. Also, KG error detection itself is challenging since triples contain rich semantic information and might be false because of various reasons. To this end, we propose to leverage active learning to minimize human efforts. Our proposed framework - KAEL, could effectively assemble a set of off-the-shelf error detection algorithms, by actively using a limited number of manual annotations. It adaptively updates the ensemble learning policy in each iteration based on active queries, i.e., the answers from experts. After all annotation budget is used, KAEL utilizes the trained policy to identify remaining suspicious triples. Experiments on real-world KGs demonstrate that we can achieve significant improvement when applying KAEL to assemble SOTA error detectors. KAEL also outperforms SOTA ensemble learning baselines significantly.

关键词： knowledge graphs ensemble learning knowledge graph refinement

来源：评论

学校读者我要写书评

暂无评论

Conversation-Driven refinement of knowledge graphs: True Active Learning with Humans in the Chatbot Application Loop 4th

Conversation-Driven Refinement of Knowledge Graphs: True Act...

引用

4th International Conference on Artificial Intelligence in HCI (AI-HCI) Held as Part of the 25th International Conference on Human-Computer Interaction (HCII)

作者： Buhl, Dominik Szafarski, Daniel Welz, Laslo Lanquillon, Carsten Heilbronn Univ Appl Sci D-74076 Heilbronn Germany

ISBN: (纸本)9783031358937;9783031358944

The value of knowledge-grounded cognitive agents is often limited by a lack of high-quality knowledge. Although advances in natural language processing have substantially improved knowledge-extraction capabilities, the demand for different types of knowledge fragments and the potential for error in extraction processes has created a next generation of the knowledge acquisition bottleneck. Instead of waiting for a perfect knowledge base, we propose a design for an agent that is aware of these issues and that actively seeks feedback from users in conversations to improve its knowledge and extraction processes. This approach allows for imperfection and incompleteness, and for the agent to improve over time. Any feedback provided by the users in this conversational application loop is used to not only refine the underlying knowledge graph, but also to improve the knowledge extraction processes. Eventually, the agent's knowledge and the quality of its answers rises while talking to its users.

关键词： Conversational AI Human-in-the-Loop AI knowledge-Grounded Cognitive Assistants knowledge graph refinement

来源：评论

学校读者我要写书评

暂无评论

A Survey on State-of-the-art Techniques for knowledge graphs Construction and Challenges ahead 4

A Survey on State-of-the-art Techniques for Knowledge Graphs...

引用

4th IEEE International Conference on Artificial Intelligence and knowledge Engineering (AIKE)

作者： Hur, Ali Janjua, Naeem Ahmed, Mohiuddin Edith Cowan Univ Sch Sci Comp & Secur Perth WA Australia Air Univ Fac Comp & AI Islamabad Pakistan

ISBN: (纸本)9781665437363

Global datasphere is increasing fast, and it is expected to reach 175 Zettabytes by 20251. However, most of the content is unstructured and is not understandable by machines. Structuring this data into a knowledge graph enables intelligent applications such as deep question answering, recommendation systems, semantic search, etc. The knowledge graph is an emerging technology that allows logical reasoning and uncovers new insights using content and context. Thereby, it provides necessary syntax and reasoning semantics that enable machines to solve complex healthcare, security, financial institutions, economics, and business problems. As an outcome, enterprises are putting their effort into constructing and maintaining knowledge graphs to support various downstream applications. Manual approaches are too expensive. Automated schemes can reduce the cost of building knowledge graphs up to 15-250 times. This paper critiques state-of-the-art automated techniques to produce knowledge graphs of near-human quality autonomously. Additionally, it highlights different research issues that need to be addressed to deliver high-quality knowledge graphs.

关键词： knowledge graph knowledge graph construction knowledge graph refinement

来源：评论

学校读者我要写书评

暂无评论

Using logical constraints to validate statistical information about disease outbreaks in collaborative knowledge graphs: the case of COVID-19 epidemiology in Wikidata

引用

PEERJ COMPUTER SCIENCE 2022年 8卷 e1085页

作者： Turki, Houcemeddine Jemielniak, Dariusz Taieb, Mohamed A. Hadj Gayo, Jose E. Labra Ben Aouicha, Mohamed Banat, Mus'ab Shafee, Thomas Prud'hommeaux, Eric Lubiana, Tiago Das, Diptanshu Mietchen, Daniel Univ Sfax Fac Sci Sfax Data Engn & Semant Res Unit Sfax Tunisia Kozminski Univ Dept Management Networked & Digital Soc Warsaw Masovia Poland Univ Oviedo Web Semant Oviedo WESO Res Grp Oviedo Asturias Spain Hashemite Univ Fac Med Zarqa Jordan La Trobe Univ Melbourne Vic Australia Swinburne Univ Technol Melbourne Vic Australia World Wide Web Consortium Cambridge MA USA Univ Sao Paulo Computat Syst Biol Lab Sao Paulo Brazil Inst Child Hlth ICH Kolkata West Bengal India Med Superspecialty Hosp Kolkata West Bengal India Ronin Inst Montclair NJ 07043 USA Leibniz Inst Freshwater Ecol & Inland Fisheries Dept Evolutionary & Integrat Ecol Berlin Germany Univ Virginia Sch Data Sci Charlottesville VA 22903 USA Inst Globally Distributed Open Res & Educ IGDORE Jena Germany

Urgent global research demands real-time dissemination of precise data. Wikidata, a collaborative and openly licensed knowledge graph available in RDF format, provides an ideal forum for exchanging structured data that can be verified and consolidated using validation schemas and bot edits. In this research article, we catalog an automatable task set necessary to assess and validate the portion of Wikidata relating to the COVID-19 epidemiology. These tasks assess statistical data and are implemented in SPARQL, a query language for semantic databases. We demonstrate the efficiency of our methods for evaluating structured non-relational information on COVID-19 in Wikidata, and its applicability in collaborative ontologies and knowledge graphs more broadly. We show the advantages and limitations of our proposed approach by comparing it to the features of other methods for the validation of linked web data as revealed by previous research.

关键词： SPARQL Wikidata Public health surveillance knowledge graph refinement COVID-19 epidemiology Validation constraints Data quality Shape Expressions Collaborative curation Public Health Emergency of International Concern

来源：评论

学校读者我要写书评

暂无评论

Unsupervised and Network-Aware Diagnostics for Latent Issues in Network Information Databases 38

Unsupervised and Network-Aware Diagnostics for Latent Issues...

引用

39th IEEE International Conference on Computer Communications (IEEE INFOCOM)

作者： Shao, Hua Chen, Li Zhao, Youjian Tsinghua Univ Beijing Peoples R China Huawei Future Network Theory Lab Shenzhen Guangdong Peoples R China

ISBN: (纸本)9781728164120

Network management database (NID) is essential in modern large-scale networks. Operators rely on NID to provide accurate and up-to-date data, however, NID-like any other databases-can suffers from latent issues such as inconsistent, incorrect, and missing data. In this work, we first reveal latent data issues in NIDs using real traces from a large cloud provider, Tencent. Then we design and implement a diagnostic system, NAuditor, for unsupervised identification of latent issues in NIDs. In the process, we design a compact and graph-based data structure to efficiently encode the complete NID as a knowledge graph, and model the diagnostic problems as unsupervised knowledge graph refinement problems. We show that the new encoding achieves superior performance than alternatives, and can facilitate adoption of state-of-the-art KGR algorithms. We also have used NAuditor in a production NID, and found 71 real latent issues, which all have been confirmed by operators.

关键词： Network Diagnostics knowledge graph refinement Unsupervised Learning Clustering graph Embedding

来源：评论

学校读者我要写书评

暂无评论

Network-Aware and Unsupervised Diagnostics for Latent Issues in Network Management Databases

Network-Aware and Unsupervised Diagnostics for Latent Issues...

引用

Conference of the ACM-Special-Interest-Group-on-Data-Communication (SIGCOMM)

作者： Chen, Li Shao, Hua Tencent Networking Platform TEG Shenzhen Peoples R China

ISBN: (纸本)9781450368865

Network management database (NMD) is essential in modern large-scale networks. Operators rely on NMD to provide accurate and up-to-date data, however, NMD-like any other databases-can suffers from latent issues such as inconsistent, incorrect, and missing data. In this work, we first reveal latent data issues in NMDs using real traces from a large cloud provider, Tencent. Then we design and implement an diagnostic system, NAuditor, for unsupervised identification of latent issues in NMDs. In the process, we design a compact and graph-based data structure to efficiently encode the complete NMD as a knowledge graph, and model the diagnostic problems as unsupervised knowledge graph refinement problems. We show that the new encoding achieves superior performance than alternatives, and can facilitate adoption of state-of-the-art KGR algorithms. We also have used NAuditor in a production NMD, and found 61 real latent issues, which all have been confirmed by operators.

关键词： Network Diagnostics knowledge graph refinement Unsupervised Learning

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：