The goal for this project is to answer questions from a large amount of text which was not possible before. Have you ever wanted to answer questions from a book without reading it. Using these models it will make answering question of book by simply scanning through the large text document and answering questions.
This project uses Google Natural Language dataset (42 GB) worth of text data and trains 2 models from it.
- Yes_No Model
- Which will scan through each paragraph from the dataset
- Give an answer (YES/NO) on whether the answer of the question is in the paragraph
- Question Answering Model
- Takes the Paragraph from the Yes_No Model which are predicted YES/NO
- Answer the question in Words