Medical Knowledge-enriched Textual Entailment Framework

TL;DR

This paper introduces a medical knowledge-enriched framework for textual entailment that leverages domain-specific knowledge graphs to improve understanding and outperform state-of-the-art models on a medical question answering benchmark.

Contribution

The paper proposes a novel framework that integrates medical knowledge graphs with dual-encoding to enhance textual entailment detection in medical texts.

Findings

Achieved 8.27% absolute improvement over SOTA models on MEDIQA-RQE dataset.

Utilized domain-specific knowledge graphs for better semantic understanding.

Demonstrated effectiveness of knowledge-enriched dual-encoding mechanism.

Abstract

One of the cardinal tasks in achieving robust medical question answering systems is textual entailment. The existing approaches make use of an ensemble of pre-trained language models or data augmentation, often to clock higher numbers on the validation metrics. However, two major shortcomings impede higher success in identifying entailment: (1) understanding the focus/intent of the question and (2) ability to utilize the real-world background knowledge to capture the context beyond the sentence. In this paper, we present a novel Medical Knowledge-Enriched Textual Entailment framework that allows the model to acquire a semantic and global representation of the input medical text with the help of a relevant domain-specific knowledge graph. We evaluate our framework on the benchmark MEDIQA-RQE dataset and manifest that the use of knowledge enriched dual-encoding mechanism help in achieving an absolute improvement of 8.27% over SOTA language models. We have made the source code available here.