Inspiration
We have tens and thousands of document in our organization. But its difficult to find a specific document as no one keeps track of what a document contains. This might lead to problem when we want some documents for some specific purpose or for model training.
What it does
This project uses Google's BERT model to train on the provided PDF documents. Once the model is trained, we can query the keyword which will be used to find the document which has the keyword along with the paragraph which has the keyword.
How we built it
This project is build using closed domain QA system with pandas and BERT model.
Challenges we ran into
Initial code/project setup.
Accomplishments that we're proud of
Having to think of a solution for a problem which might present itself in the future.
Log in or sign up for Devpost to join the conversation.