Leveraging Unlabeled Data for Entity-Relation Extraction through Probabilistic Constraint Satisfaction

TL;DR

This paper introduces a novel method for entity-relation extraction that leverages symbolic domain knowledge using semantic loss, significantly improving performance in low-data scenarios by maintaining logical constraints.

Contribution

It proposes a semantic loss approach that accurately incorporates logical domain knowledge into entity-relation extraction, outperforming previous approximation methods.

Findings

Semantic loss effectively encodes logical constraints.

Method outperforms baselines in low-data regimes.

Maintains precise logical meaning through probability distributions.

Abstract

We study the problem of entity-relation extraction in the presence of symbolic domain knowledge. Such knowledge takes the form of an ontology defining relations and their permissible arguments. Previous approaches set out to integrate such knowledge in their learning approaches either through self-training, or through approximations that lose the precise meaning of the logical expressions. By contrast, our approach employs semantic loss which captures the precise meaning of a logical sentence through maintaining a probability distribution over all possible states, and guiding the model to solutions which minimize any constraint violations. With a focus on low-data regimes, we show that semantic loss outperforms the baselines by a wide margin.