Joint Representation Learning of Text and Knowledge for Knowledge Graph Completion
This addresses the problem of incomplete knowledge graphs for AI applications, but it is incremental as it builds on existing embedding methods.
The paper tackled knowledge graph completion by jointly learning representations of text and knowledge in a unified semantic space, resulting in significant and consistent performance improvements on entity prediction, relation prediction, and relation classification tasks compared to baselines.
Joint representation learning of text and knowledge within a unified semantic space enables us to perform knowledge graph completion more accurately. In this work, we propose a novel framework to embed words, entities and relations into the same continuous vector space. In this model, both entity and relation embeddings are learned by taking knowledge graph and plain text into consideration. In experiments, we evaluate the joint learning model on three tasks including entity prediction, relation prediction and relation classification from text. The experiment results show that our model can significantly and consistently improve the performance on the three tasks as compared with other baselines.