Lifted Rule Injection for Relation Embeddings

TL;DR

This paper introduces a scalable and efficient method to incorporate implication rules into relation embeddings for knowledge base inference, improving accuracy without significant computational overhead.

Contribution

It proposes a novel approach that maps entity-tuple embeddings into a Boolean space and enforces a partial order over relation embeddings based on mined implication rules, enhancing knowledge base models.

Findings

Achieves 2% higher mean average precision over baseline.

Maintains negligible increase in runtime.

Entity-tuple embedding space acts as a regularizer.

Abstract

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.