A novel deep learning architecture for drug named entity recognition

Abstract

Drug named entity recognition (DNER) becomes the prerequisite of other medical relation extraction systems. Existing approaches to automatically recognize drug names includes rule-based, machine learning (ML) and deep learning (DL) techniques. DL techniques have been verified to be the stateof-the-art as it is independent of handcrafted features. The previous DL methods based on word embedding input representation uses the same vector representation for an entity irrespective of its context in different sentences and hence could not capture the context properly. Also, identification of the n-gram entity is a challenge. In this paper, a novel architecture is proposed that includes a sentence embedding layer that works on the entire sentence to efficiently capture the context of an entity. A hybrid model that comprises a stacked bidirectional long short-term memory (Bi-LSTM) with residual LSTM has been designed to overcome the limitations and to upgrade the performance of the model. We have contrasted the achievement of our proposed approach with other DNER models and the percentage of improvements of the proposed model over LSTM-conditional random field (CRF), LIU and WBI with respect to micro-average F1-score are 11.17, 8.8 and 17.64 respectively. The proposed model has also shown promising result in recognizing 2-and 3-gram entities.

Pre-trained Bi-LSTM model for automated classification of ventricular arrhythmias using 1-D and 2-D ECG

“…Asmae et al [13], a synthetic minority oversampling strategy is used to address issues with imbalanced classes. To conduct an empirical assessment, many researchers employed long short-term memory (LSTM), bidirectional long short-term memory (Bi-LSTM) [14]- [19]. Using an unbalanced dataset, atrial fibrillation (Afib) was automatically classified in [20] using a hybrid convolutional neural network (CNN)-LSTM approach.…”

Biomedical-named entity recognition using CUDA accelerated KNN algorithm

“…When training with test data that isn't part of the training data, supervised learning techniques use data with a variety of features based on several linguistic criteria. Mathu and Raimond [26] used Bi-LSTM with residuals for a drug-named entity recognition task with only a 40% recognition rate for 4-gram entities. Ramachandran and Arutchelvan [27] have implemented a hybrid model in which the annotated entities are trained by a blank Spacy ML model validated by this dictionary and human.…”