Simultaneously Linking Entities and Extracting Relations from Biomedical Text Without Mention-level Supervision

TL;DR

This paper introduces a joint model for entity linking and relation extraction in biomedical text that does not require mention-level supervision, improving accuracy and recall over traditional pipelined approaches.

Contribution

The proposed model simultaneously performs entity linking and relation extraction without mention-level annotations, reducing cascading errors and enhancing system recall.

Findings

Outperforms state-of-the-art pipelines on biomedical datasets

Drastically improves overall recall of entity relationships

Requires no mention-level supervision for training

Abstract

Understanding the meaning of text often involves reasoning about entities and their relationships. This requires identifying textual mentions of entities, linking them to a canonical concept, and discerning their relationships. These tasks are nearly always viewed as separate components within a pipeline, each requiring a distinct model and training data. While relation extraction can often be trained with readily available weak or distant supervision, entity linkers typically require expensive mention-level supervision -- which is not available in many domains. Instead, we propose a model which is trained to simultaneously produce entity linking and relation decisions while requiring no mention-level annotations. This approach avoids cascading errors that arise from pipelined methods and more accurately predicts entity relationships from text. We show that our model outperforms a state-of-the art entity linking and relation extraction pipeline on two biomedical datasets and can drastically improve the overall recall of the system.