Project

Knowledge Graph based Question Answeing for Numerical Queries

Objective

The work would be around exploring the following: explore state-of-the-art NLP models such as BERT to fine-tune to infuse numeric semantics and use it to learn KGEs. Define novel scoring function to enhance predictions for Numerical Quantities which is not been explored in the literature. Hands-on experiments to explore limitations of current Knowledge Graph based QA methods and benchmark them.

Outcome

The project will result in a good conference paper