Gentle Introduction to Natural Language Processing
In this session, we will be presenting the basic prerequisites and foundational concepts of natural language processing (NLP) that are relevant for understanding the current state of the art applications of NLP for medicine. The topics covered will cover how distributional models of word representation are developed, concepts of parsing, basics of language models along with practical preprocessing steps. This session is targeted for those with no previous exposure to natural language processing.
State of the Art NLP Models and their Applications
A bird’s eye view of the state of the techniques in NLP will be presented, along with their major applications. The applications have been carefully curated to reflect the intersection between NLP and Biology related applications that will be described in the third session. Major topics in this session include automatic summarisation, entity/relation identification, sentiment analysis, translation and so on. This will be followed by a discussion on evaluation methods and practical considerations. This session will also have a practical demonstration component.
Natural Language Processing and Biomedical Applications
Starting from the basic concept that many biomedical applications and NLP applications have a large intersection, this session will have a high level overview of these similarities. The session will have a broad discussion of issues in biomedical data for machine learning and natural language processing. This will be followed by the mapping of NLP applications to biomedical tasks such as transcription, medical text modelling, application of NLP models for gene sequencing, handling multi modal data and so on. This session will also have a practical component.