Abstract
The knowledge graph completion (KGC) task aims to predict missing links in knowledge graphs. Recently, several KGC models based on translational distance or semantic matching methods have been proposed and have achieved meaningful results. However, existing models have a significant shortcoming–they cannot train entity embedding when an entity does not appear in the training phase. As a result, such models use randomly initialized embeddings for entities that are unseen in the training phase and cause a critical decrease in performance during the test phase. To solve this problem, we propose a new approach that performs KGC task by utilizing the masked language model (MLM) that is used for a pre-trained language model. Given a triple ( head entity , relation , tail entity ), we mask the tail entity and consider the head entity and the relation as a context for the tail entity. The model then predicts the masked entity from among all entities. Then, the task is conducted by the same process as an MLM, which predicts a masked token with a given context of tokens. Our experimental results show that the proposed model achieves significantly improved performances when unseen entities appear during the test phase and achieves state-of-the-art performance on the WN18RR dataset.
Highlights
Knowledge graphs (KGs) are collections of real-world knowledge represented as a triple in the form of (h, r, t), denoting head entity, relation and tail entity, respectively
To leverage the effectiveness of the knowledge graph embedding (KGE) models and pre-trained language models, we propose the masked entity modeling for the knowledge graph completion (KGC) (MEM-KGC) method that enhances the KGC task using the process of the masked language modeling (MLM) task
The proposed method achieved better performances than existing models based on pre-trained language models, such as KG-bidirectional encoder representations from transformers (BERT) and the multi-task learning for knowledge graph completion (MTL-KGC) [7] while extremely reducing the inference time
Summary
Knowledge graphs (KGs) are collections of real-world knowledge represented as a triple in the form of (h, r, t), denoting head entity, relation and tail entity, respectively. A typical approach for the KGC task is the knowledge graph embedding (KGE) method, which represents entities and relations as embedding vectors and calculates the scores of triples using those embeddings These KGE models have achieved meaningful results, there is a fatal drawback that they can only learn entity embeddings when entities appear during the training phase. The proposed method achieved better performances than existing models based on pre-trained language models, such as KG-BERT and the multi-task learning for knowledge graph completion (MTL-KGC) [7] while extremely reducing the inference time. We calculate the loss of the entity prediction using the cross-entropy loss function
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
