KRL model will answer the following four questions

1. ” Which representation space to choose?”
2. ”How to measure the plausibility of triplets in a specific space?”
3. “Which encoding model to use for modeling relational interaction ?”
4. ”Whether to utilize auxiliary information?”


KRL Model 

The space where entities and relations are represented after analysis. Representation space is also called embedding space. The embedding space should satisfy three conditions differentiability, calculation possibility, and definability of a scoring function. The representation space can be categorized into

 - Point-Wise Space
 - Complex Vector Space
 - Gaussian Distribution
 - Manifold and Group:


Representation Space 

Scoring function is used to measure the credibility of facts, it is also referred to as energy function There are two types of scoring functions to measure the plausibility of facts.

 - Distance-based Scoring Function
 - Semantic Matching


Scoring Function

Various architecture models are used to capture the interaction between entities and relations.

 - Linear/Bilinear Models
 - Factorization Models
 - Neural Networks
 - Convolutional Neural Networks
 - Recurrent Neural Networks
 - Transformers
 - Graph Neural Networks (GNNs)


Encoding Models

In this form of knowledge representation extra information like text descriptions, type constraints, visual information ,relational paths along with knowledge graphs are used to learn embeddings. The external information needed can be categorized into

 - Textual Description
 - Type Information
 - Visual Information
 - Uncertain Information


Embedding with Auxiliary Information

Summary of recent KRL Models

Knowledge representation learning(KRL) maps entities and relations onto a low dimensional vector space by capturing its semantic meaning. KRL is also called multi-relation learning or statistical relational learning. The recent advancement in distributed representation learning can be categorized into four scopes

 - Representation Space 
 - Scoring Function 
 - Encoding Models 
 - Embedding with Auxiliary Information


San Jose State University

Research on knowledge graph are categorized into

 - Knowledge representation learning
 - Knowledge acquisition
 - Temporal knowledge graph
 - Knowledge -aware applications


Research on Knowledge Graph in NLP

A Survey on Knowledge Graphs: Representation, Acquisition and Applications

Knowledge Representation Learning /Knowledge Graph Embedding

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

Temporal knowledge graph takes consideration of  temporal knowledge into KRL and KGC. The different areas where temporal information accounted are

 - Temporal Information Embedding
 - Entity Dynamics 
 - Temporal Relational Dependency
 - Temporal Logical Reasoning 


Temporal Knowledge Graph

The application of structured data in knowledge graphs are useful in applications like link prediction, entity prediction ,relation extraction ,question answering applications and recommendation systems. The various applications of knowledge graphs are  in 

 - Language Representation Learning
 - Question Answering 
 - Recommender Systems


Learn Before

Related

Learn After