Answering Complex Queries in Knowledge Graphs with Bidirectional Sequence Encoders
This addresses a limitation in knowledge graph representation learning for more complex queries beyond simple link prediction.
The paper tackles the problem of answering complex conjunctive queries with multiple missing entities in knowledge graphs, proposing BIQE which uses bidirectional attention mechanisms and achieves significant performance improvements over state-of-the-art baselines on a new dataset.
Representation learning for knowledge graphs (KGs) has focused on the problem of answering simple link prediction queries. In this work we address the more ambitious challenge of predicting the answers of conjunctive queries with multiple missing entities. We propose Bi-Directional Query Embedding (BIQE), a method that embeds conjunctive queries with models based on bi-directional attention mechanisms. Contrary to prior work, bidirectional self-attention can capture interactions among all the elements of a query graph. We introduce a new dataset for predicting the answer of conjunctive query and conduct experiments that show BIQE significantly outperforming state of the art baselines.