Lifted Rule Injection for Relation Embeddings
This work addresses the scalability issue of incorporating first-order logic rules into knowledge base construction models, offering a domain-specific improvement for automated inference tasks.
The paper tackles the challenge of efficiently incorporating commonsense knowledge into representation learning models for knowledge base inference by introducing a method that maps entity-tuple embeddings into an approximately Boolean space and enforces a partial ordering based on implication rules, achieving a 2 percentage point increase in mean average precision over a baseline with negligible runtime increase.
Methods based on representation learning currently hold the state-of-the-art in many natural language processing and knowledge base inference tasks. Yet, a major challenge is how to efficiently incorporate commonsense knowledge into such models. A recent approach regularizes relation and entity representations by propositionalization of first-order logic rules. However, propositionalization does not scale beyond domains with only few entities and rules. In this paper we present a highly efficient method for incorporating implication rules into distributed representations for automated knowledge base construction. We map entity-tuple embeddings into an approximately Boolean space and encourage a partial ordering over relation embeddings based on implication rules mined from WordNet. Surprisingly, we find that the strong restriction of the entity-tuple embedding space does not hurt the expressiveness of the model and even acts as a regularizer that improves generalization. By incorporating few commonsense rules, we achieve an increase of 2 percentage points mean average precision over a matrix factorization baseline, while observing a negligible increase in runtime.