NHS England Data Science PhD Internships

Augmenting Text Generation in Healthcare with Knowledge Retrieval Approaches

Keywords: NLP, GenerativeLanguage, TextData

Need: The ability to use the creativity of modern large-scale language models when working with and generating text, balanced with a need to supply curated information for robustness, is very important in solutions in healthcare settings. This project looks to explore recent approaches mixing factual knowledge input sources and generative language models (c.f. RAG) - frameworks looking at the Question/Answer space exist - are there other areas of text generation this could be extended to? How could different more structured forms of information be integrated such as ontologies?

Current Knowledge/Examples & Possible Techniques/Approaches:

Related Previous Internship Projects: May use outputs from the NHS Language Corpus and has similarity to NHS Semantic Search

Enables Future Work: Both work in understanding better generative language models and the integration of knowledge sources in healthcare solutions

Outcome/Learning Objectives: Identify and explore useful techniques/tools/frameworks for this type of task and how different sources of knowledge could be used

Datasets: There are various open healthcare text datasets and knowledge bases which could be explored

Desired skill set: When applying please highlight any experience around informatics, natural language processing, language modelling, neural networks, coding experience (including any coding in the open), any other data science experience you feel relevant.

Return to list of all available projects.