# Extracting adverse drug reactions and their context using sequence labelling ensembles in TAC2017

## TL;DR

This paper develops ensemble sequence labeling methods combining rule-based, machine learning, and deep learning techniques to extract adverse drug reactions and related entities from text, achieving high accuracy in a shared task.

## Contribution

It introduces a set of ensemble taggers that integrate multiple methodologies for extracting ADRs and related entities, improving extraction performance.

## Key findings

- Achieved F1-scores of 76.00 and 75.61 in the shared task.
- Demonstrated effectiveness of combined rule-based and deep learning approaches.
- Enhanced extraction of ADRs and related factors from biomedical text.

## Abstract

Adverse drug reactions (ADRs) are unwanted or harmful effects experienced after the administration of a certain drug or a combination of drugs, presenting a challenge for drug development and drug administration. In this paper, we present a set of taggers for extracting adverse drug reactions and related entities, including factors, severity, negations, drug class and animal. The systems used a mix of rule-based, machine learning (CRF) and deep learning (BLSTM with word2vec embeddings) methodologies in order to annotate the data. The systems were submitted to adverse drug reaction shared task, organised during Text Analytics Conference in 2017 by National Institute for Standards and Technology, archiving F1-scores of 76.00 and 75.61 respectively.