A Sui Generis QA Approach using RoBERTa for Adverse Drug Event Identification

Hence, researchers have started Extraction of adverse drug events from biomedical literature moving towards more automated approaches in machine and other textual data is an important component to learning. There has been a gradual shift towards using natural monitor drug-safety and this has attracted attention of many language processing (NLP) based methods. Early attempts researchers in healthcare. Existing works are more pivoted have incorporated the use of resources like NLM's MetaMap, around entity-relation extraction using bidirectional long Unified Medical Language System (UMLS) etc. [24] to extract short term memory networks (Bi-LSTM) which does not drugs for ADE identification tasks. However, a major limitation attain the best feature representations. In this paper, we introduce of these approaches is that they are not able to capture a question answering framework that exploits the the causal relationships between drug and ADE properly.