Year 2021: COVID-19, Information Extraction and BERTization among the Hottest Topics in Medical Natural Language Processing

Abstract

Objectives: Analyze the content of publications within the medical natural language processing (NLP) domain in 2021. Methods: Automatic and manual preselection of publications to be reviewed, and selection of the best NLP papers of the year. Analysis of the important issues. Results: Four best papers have been selected in 2021. We also propose an analysis of the content of the NLP publications in 2021, all topics included. Conclusions: The main issues addressed in 2021 are related to the investigation of COVID-related questions and to the further adaptation and use of transformer models. Besides, the trends from the past years continue, such as information extraction and use of information from social networks.

Inclusive Digital Health

“…The authors listed NLP-based systems implemented in ten hospital departments to illustrate what they call "bedside applications", while specifying the different types of NLP tasks addressed. Check out the NLP synopsis by co-editors Natalia Grabar and Cyril Grouin, who conducted a thorough analysis of the 2021 biomedical NLP literature [38]. They noticed that transformer-based models are extensively studied, that there is a lot of work on dedicated applica-tions such as COVID-19 and mental health, and still many papers presenting information extraction methods.…”