DOLORES: Deep Contextualized Knowledge Graph Embeddings
This addresses the challenge of contextual representation in knowledge graphs for AI applications, offering a novel method with strong specific gains.
The authors tackled the problem of learning knowledge graph embeddings by capturing contextual cues and dependencies among entities and relations, resulting in significant state-of-the-art improvements, such as at least 9.5% gains on tasks like link prediction.
We introduce a new method DOLORES for learning knowledge graph embeddings that effectively captures contextual cues and dependencies among entities and relations. First, we note that short paths on knowledge graphs comprising of chains of entities and relations can encode valuable information regarding their contextual usage. We operationalize this notion by representing knowledge graphs not as a collection of triples but as a collection of entity-relation chains, and learn embeddings for entities and relations using deep neural models that capture such contextual usage. In particular, our model is based on Bi-Directional LSTMs and learn deep representations of entities and relations from constructed entity-relation chains. We show that these representations can very easily be incorporated into existing models to significantly advance the state of the art on several knowledge graph prediction tasks like link prediction, triple classification, and missing relation type prediction (in some cases by at least 9.5%).