Entity Context Graph: Learning Entity Representations fromSemi-Structured Textual Sources on the Web

TL;DR

This paper introduces a novel method for learning high-quality entity embeddings directly from semi-structured web sources, bypassing the need for traditional knowledge graph construction, and demonstrating superior or comparable performance to existing models.

Contribution

The authors propose a new approach that extracts triples from textual sources without predefined relationship labels to learn effective entity embeddings, reducing complexity and cost.

Findings

Embeddings are comparable to traditional knowledge graph-based embeddings.

Embeddings outperform contextual language model-based entity embeddings.

Method is easy to compute and adaptable to domain-specific applications.

Abstract

Knowledge is captured in the form of entities and their relationships and stored in knowledge graphs. Knowledge graphs enhance the capabilities of applications in many different areas including Web search, recommendation, and natural language understanding. This is mainly because, entities enable machines to understand things that go beyond simple tokens. Many modern algorithms use learned entity embeddings from these structured representations. However, building a knowledge graph takes time and effort, hence very costly and nontrivial. On the other hand, many Web sources describe entities in some structured format and therefore, finding ways to get them into useful entity knowledge is advantageous. We propose an approach that processes entity centric textual knowledge sources to learn entity embeddings and in turn avoids the need for a traditional knowledge graph. We first extract triples into the new representation format that does not use traditional complex triple extraction methods defined by pre-determined relationship labels. Then we learn entity embeddings through this new type of triples. We show that the embeddings learned from our approach are: (i) high quality and comparable to a known knowledge graph-based embeddings and can be used to improve them further, (ii) better than a contextual language model-based entity embeddings, and (iii) easy to compute and versatile in domain-specific applications where a knowledge graph is not readily available