Tagging of entities in a text is entity recognition.

Entity Recognition

Entity linking to corresponding entities mentions a knowledge graph.

Entity Disambiguation 

Entity typing helps to find coarse and fine grained typing of entities.

Entity Typing

Entity alignment aims to fuse knowledge among various knowledge graphs.

 Entity Alignment

Learning of entity related knowledge from text under various settings. Entity-based knowledge acquisition can be categorized into 

 - Entity recognition
 - Entity disambiguation 
 - Entity typing
 - Entity alignment


San Jose State University

Knowledge acquisition aims to build new knowledge graphs from structured ,semi structured and unstructured text. It also helps to complete existing knowledge graphs, discover and recognize entities and relations. Three categories of knowledge acquisition techniques are 

 - knowledge  graph completion 
 - entity discovery
 - relation extraction.


Knowledge Acquisition

A Survey on Knowledge Graphs: Representation, Acquisition and Applications

KGC adds new triples to the existing knowledge graph and also accomplishes subtasks like link prediction, entity prediction and relation prediction. KGC also learns low dimensional embedding for triple prediction with recent advancement on capturing multi step relationship paths. KGC also do triple classification which evaluates the correctness of factual triple.

 - Embedding-based Models:
 - Relation Path Reasoning
 - RL-based Path Finding
 - Rule-based Reasoning
 - Meta Relational Learning:
 - Triple Classification


Knowledge Graph Completion 

Entity Discovery

Unknown relations are extracted from text  and added to the knowledge graph.The various methods used for relation extraction are 

 - Neural Relation Extraction
 - Attention Mechanism
 - Graph Convolutional Networks 
 - Adversarial Training
 - Reinforcement Learning
 - Other Advances
 - Joint Entity and Relation Extraction


Learn Before

Related

Learn After