NLM IRP Seminar Schedule

Abstract:

Plain language in medicine has long been advocated as a way to improve patient understanding and engagement. As the field of Natural Language Processing has progressed, increasingly sophisticated methods have been explored for the automatic simplification of existing biomedical text for consumers. Though Deep Learning methods have unsurprisingly become dominant over rule-based systems in the open domain for simplification, the biomedical domain has special considerations that have impeded the progress of neural systems. I will discuss these challenges and how researchers have addressed them thus far, including the continued development of rule-based and hybrid systems. I will also discuss progress our group has made so far and our plans for addressing the current inadequacies of biomedical text simplification systems moving forward.