Open-world knowledge embedding in a low-text resource environment

The objective of knowledge embedding (KE) is to represent entities and relations in a knowledge graph (KG) in a continuous low-dimensional vector space, thereby facilitating the integration of the KG into various downstream applications. Existing KE methods can be classified into two categories: closed-world knowledge embedding methods (CWKEs) and open-world knowledge embedding methods (OWKEs). CWKEs necessitate the re-training of the entire model upon the addition of new entities to the KG. In contrast, OWKEs offer greater practical application value as they do not require re-training due to their capacity to generate vector representations for new entities. The current major OWKEs employ the description text of new entities to generate vector representations for new entities. However, these methods are highly dependent on the richness of entity relationships and attribute information present in the text, and they are ineffective when there are only a few textual resources, such as entity names. In reality, most KGs have only a limited number of textual resources. For this reason, we propose the first open-world Knowledge Embedding method (LTKE) in a low textual resource environment. LTKE is designed to efficiently generate vector representations for new entities when KGs have only a few textual resources. By efficiently serializing the local structure of entities, LTKE can obtain information-rich text when an entity has only the entity name. Additionally, we develop a new scoring function to enhance model efficiency. Extensive experiments on real-world KG datasets (Freebase, WordNet) have demonstrated the effectiveness of the model.