Using ML/NLP to Identify Relationships and Similarities in Grant Proposal Texts

Description

Year: 2022

A team of students will work with Duke’s Office of Information Technology (OIT), Office for Research & Innovation (OR&I) and Computer Science faculty to develop a system that would enable OR&I to  get an objective answer to questions such as, How does the grant you’re proposing relate to other funded research of yours or of other faculty at Duke? or Is there overlap between my proposal and another proposal that a federal agency is reviewing? 

The students will use Machine Learning (ML)/Artificial Intelligence (AI) and Natural Language Processing (NLP) techniques on proposal abstracts and/or other grant-related materials to identify potential connections  and similar metrics among research proposals.

Watch the team's final presentation on YouTube.