CRIS Projects Details -
Accept Cookies

Cookies: How we use information on our website:

We use cookies on our website to make it clear, useful and reliable. In order to achieve this and to provide certain personalised features we store a small amount
of data about you. Click Here to learn more. By navigating from the front page to other sections of our website, you are consenting to information being stored.


CRIS Projects Details

Project Details

 

Using unsupervised Natural Language Processing methods for understanding and modeling vocabulary use in CRIS

Lead Applicant Name :
Sumithra Velupillai
Project Type :
Research
Approval Date :
25-Apr-2019
References :
Lay Summary :
Natural language processing (NLP) techniques have been successfully developed to extract clinical concepts such as symptoms (hallucinations), treatments (clozapine) and diagnoses (schizophrenia) from health record text such as data from CRIS, but these methods don’t currently capture more complex concepts such as phrases, idioms and figures of speech. They are also usually developed from specific pre-defined keywords or concepts, which means that synonyms and variants are missed.We will seek to develop methods that can model more complex concepts using unsupervised, data-driven NLP approaches that automatically learn from large sets of text data.

< Back to search