On the Automatic Construction of Knowledge-Map from Handouts for MOOC Courses

2017 ◽  
pp. 107-114 ◽  
Author(s):  
Nen-Fu Huang ◽  
Chia-An Lee ◽  
Yi-Wei Huang ◽  
Po-Wen Ou ◽  
How-Hsuan Hsu ◽  
...  
Keyword(s):  
Knowledge Map ◽  
Automatic Construction ◽  
Construction Of Knowledge

scholarly journals Research on Dynamic Knowledge Map Service System Using Computer Big Data

2021 ◽  
Vol 2083 (4) ◽  
pp. 042001
Author(s):  
Nan Zhang ◽  
Wenqiang Zhang ◽  
Yingnan Shang
Keyword(s):  
Big Data ◽  
Data Model ◽  
Structured Data ◽  
Knowledge Network ◽  
Practical Significance ◽  
Data Publishing ◽  
Knowledge Map ◽  
Related Data ◽  
Construction Of Knowledge ◽  
Map Service

Abstract The emergence of computer big data related data provides a new method for the construction of knowledge links in the knowledge map. This realizes an objective knowledge network with practical significance that is easier to be understood by machines. The article combines the four principles of linked data publishing content objects and their semantic characteristics, and uses the RDF data model to convert unstructured data on the Internet and structured data that adopts different standards into unified standard structured data for association. The system forms a huge knowledge map with semantics, intelligence, and dynamics.

Low-Quality Error Detection for Noisy Knowledge Graphs

2021 ◽  
Vol 32 (4) ◽  
pp. 48-64
Author(s):  
*Chenyang Bu ◽  
Xingchen Yu ◽  
Yan Hong ◽  
Tingting Jiang
Keyword(s):  
Error Detection ◽  
Data Sources ◽  
Construction Process ◽  
Automatic Construction ◽  
Construction Of Knowledge ◽  
Unstructured Text ◽  
Multiple Data ◽  
Extraction Processes ◽  
Knowledge Graphs ◽  
Type Information

The automatic construction of knowledge graphs (KGs) from multiple data sources has received increasing attention. The automatic construction process inevitably brings considerable noise, especially in the construction of KGs from unstructured text. The noise in a KG can be divided into two categories: factual noise and low-quality noise. Factual noise refers to plausible triples that meet the requirements of ontology constraints. For example, the plausible triple <New_York, IsCapitalOf, America> satisfies the constraints that the head entity “New_York” is a city and the tail entity “America” belongs to a country. Low-quality noise denotes the obvious errors commonly created in information extraction processes. This study focuses on entity type errors. Most existing approaches concentrate on refining an existing KG, assuming that the type information of most entities or the ontology information in the KG is known in advance. However, such methods may not be suitable at the start of a KG's construction. Therefore, the authors propose an effective framework to eliminate entity type errors. The experimental results demonstrate the effectiveness of the proposed method.

scholarly journals Towards Technological Approaches for Concept Maps Mining from Text

2018 ◽  
Vol 21 (1) ◽  
Author(s):  
Camila Zacche Aguiar ◽  
Davidson Cury ◽  
Amal Zouaq
Keyword(s):  
Quantitative Analysis ◽  
Concept Maps ◽  
Concept Map ◽  
Graphic Representation ◽  
Data Bases ◽  
Automatic Construction ◽  
Construction Of Knowledge ◽  
Technological Advances ◽  
Direct Data ◽  
Data Source

Concept maps are resources for the representation and construction of knowledge. They allow showing, through concepts and relationships, how knowledge about a subject is organized. Technological advances have boosted the development of approaches for the automatic construction of a concept map, to facilitate and provide the benefits of that resource more broadly. Due to the need to better identify and analyze the functionalities and characteristics of those approaches, we conducted a detailed study on technological approaches for automatic construction of concept maps published between 1994 and 2016 in the IEEE Xplore, ACM and Elsevier Science Direct data bases. From this study, we elaborate a categorization defined on two perspectives, Data Source and Graphic Representation, and fourteen categories. That study collected 30 relevant articles, which were applied to the proposed categorization to identify the main features and limitations of each approach. A detailed view on these approaches, their characteristics and techniques are presented enabling a quantitative analysis. In addition, the categorization has given us objective conditions to establish new specification requirements for a new technological approach aiming at concept maps mining from texts.

Sign in / Sign up

Export Citation Format

Share Document