search

hitvoice / DrQA

A pytorch implementation of Reading Wikipedia to Answer Open-Domain Questions.
401 stars 109 forks source link

Adding Evidence as Database (like wikipedia ) #14

Closed augmen closed 6 years ago

augmen commented 6 years ago

say once your model is trained and you export the model for prediction. you want to add all the evidence as database in "id", "txt" format.So multiple users can run the queries on the dataset for Answers . how to add such datasets ? would we require another python script like dataset / document reader.py ?

hitvoice commented 6 years ago

You can treat DrQA as a separate agent and feed evidence-question pairs to it. Query handling and data storage are other independent modules of your project.

augmen commented 6 years ago

so its not possible to add the extra database like evidence ?

hitvoice commented 6 years ago

It's possible, but out of the scope of this project. :)

augmen commented 6 years ago

any guidance on other repo . that we can utilise ?

hitvoice commented 6 years ago

I've never tried that before so there's nothing I can suggest. If you have some questions about your own project but unrelated to DrQA, please post them on more general tech forums like StackOverflow/StackExchange. A lot more experienced people will help you there.