Semantic databases or entity index in graph form
Posted: Wed Feb 19, 2025 8:48 am
The entities in a semantic database such as the Knowledge Graph are recorded as nodes and the relationships are represented as edges. The entities can be supplemented with labels, e.g. for entity types , classes, attributes and information about content and digital images related to the entity, such as websites, author profiles or profiles in social networks.
To clarify, here is a concrete example of entities that are related to each other. The main entities are Taylor Swift and her boyfriend Joe Alwyn and other entities are the parents, siblings and songs with which they are semantically related.
Example: Relationships between entities in a knowledge graph, ©Olaf Kopp
Entities are not just a string of letters, but are things with a south korea cell phone number list clearly identifiable meaning. The search term "jaguar" has several meanings. It can mean the car brand, the animal or the tank. Simply using the character string in search queries and/or content is not enough to understand the context. In combination with other attributes or entities such as Rover, Coventry, PS, car... the clear meaning becomes clear through the context in which the entity moves. The meaning of entities can be determined by the context in which they are mentioned or used in content and search queries.
Using vector space analysis and machine learning for better semantic understanding
Vector space analyses can be used to place search queries and content in a thematic context. Entities, content or search queries can be located in a vector space. The distance between the different terms provides information about the thematic context in which the vectors are used. This can be used to determine thematic ontologies or categories in which keywords or entities can be located.
Google officially introduced the method of transforming words into machine-readable vectors (Word2Vec) in 2015 with Rankbrain, in order to better understand search queries in particular. Rankbrain was introduced as an innovation for so-called query processing, i.e. the process of interpreting search queries. Rankbrain was also the first time that Google confirmed that machine learning is being used for Google searches.
To clarify, here is a concrete example of entities that are related to each other. The main entities are Taylor Swift and her boyfriend Joe Alwyn and other entities are the parents, siblings and songs with which they are semantically related.
Example: Relationships between entities in a knowledge graph, ©Olaf Kopp
Entities are not just a string of letters, but are things with a south korea cell phone number list clearly identifiable meaning. The search term "jaguar" has several meanings. It can mean the car brand, the animal or the tank. Simply using the character string in search queries and/or content is not enough to understand the context. In combination with other attributes or entities such as Rover, Coventry, PS, car... the clear meaning becomes clear through the context in which the entity moves. The meaning of entities can be determined by the context in which they are mentioned or used in content and search queries.
Using vector space analysis and machine learning for better semantic understanding
Vector space analyses can be used to place search queries and content in a thematic context. Entities, content or search queries can be located in a vector space. The distance between the different terms provides information about the thematic context in which the vectors are used. This can be used to determine thematic ontologies or categories in which keywords or entities can be located.
Google officially introduced the method of transforming words into machine-readable vectors (Word2Vec) in 2015 with Rankbrain, in order to better understand search queries in particular. Rankbrain was introduced as an innovation for so-called query processing, i.e. the process of interpreting search queries. Rankbrain was also the first time that Google confirmed that machine learning is being used for Google searches.