"When they say weed causes depression, but it's your fav antidepressant": Knowledge-aware Attention Framework for Relationship Extraction

TL;DR

This paper introduces Gated-K-BERT, a deep learning framework that combines BERT and domain-specific knowledge from Drug Abuse Ontology to improve extraction of relationships between cannabis use and depression from social media data.

Contribution

The study presents a novel knowledge-infused deep learning model that enhances relation extraction accuracy by integrating domain knowledge with pre-trained language models.

Findings

Improved coverage in extracting cannabis-depression relationships.

Knowledge-aware attention enhances relation extraction performance.

Outperforms state-of-the-art relation extractors.

Abstract

With the increasing legalization of medical and recreational use of cannabis, more research is needed to understand the association between depression and consumer behavior related to cannabis consumption. Big social media data has potential to provide deeper insights about these associations to public health analysts. In this interdisciplinary study, we demonstrate the value of incorporating domain-specific knowledge in the learning process to identify the relationships between cannabis use and depression. We develop an end-to-end knowledge infused deep learning framework (Gated-K-BERT) that leverages the pre-trained BERT language representation model and domain-specific declarative knowledge source (Drug Abuse Ontology (DAO)) to jointly extract entities and their relationship using gated fusion sharing mechanism. Our model is further tailored to provide more focus to the entities mention in the sentence through entity-position aware attention layer, where ontology is used to locate the target entities position. Experimental results show that inclusion of the knowledge-aware attentive representation in association with BERT can extract the cannabis-depression relationship with better coverage in comparison to the state-of-the-art relation extractor.