Improved Representation Learning for Predicting Commonsense Ontologies
This work addresses the challenge of learning structured knowledge from text for AI applications, but it is incremental as it builds on existing order-embedding methods.
The paper tackled the problem of predicting commonsense ontologies by extending the order-embedding model to incorporate raw text and exploit partial order structures, resulting in improved performance over baselines.
Recent work in learning ontologies (hierarchical and partially-ordered structures) has leveraged the intrinsic geometry of spaces of learned representations to make predictions that automatically obey complex structural constraints. We explore two extensions of one such model, the order-embedding model for hierarchical relation learning, with an aim towards improved performance on text data for commonsense knowledge representation. Our first model jointly learns ordering relations and non-hierarchical knowledge in the form of raw text. Our second extension exploits the partial order structure of the training data to find long-distance triplet constraints among embeddings which are poorly enforced by the pairwise training procedure. We find that both incorporating free text and augmented training constraints improve over the original order-embedding model and other strong baselines.