We have been working on BERT based QnA system for more than a year now. What started with a small experiment to create a QnA demo using BERT has spanned out to a big project thanks to superior capabilities of BERT NLP model.
Let’s see how we have progressed thus far!
The first version of our QnA was very basic one. You input one paragraph, pose some questions and the system will find answer from the paragraph.
The demo of first version of QnA: https://www.pragnakalp.com/demos/BERT-NLP-QnA-Demo/
More details about how it was created can be found in the case study: https://www.pragnakalp.com/case-study/question-answering-system-in-python-using-bert-nlp/
Currently it is available in 13 languages including English, Hindi, Arabic, Spanish, French, German, Chinese, Portuguese, Italian, Turkish, Russian, Korean and Japanese. The limitation of this demo is that it takes around 20 seconds to find the answer from the paragraph of 1000 characters length.
We improved upon first version and got success to find the answer within 3-4 seconds which was huge jump from the version 1 in terms of result time. As the responses are fast, we call this version closed-domain chatbot using BERT.
The demo can be accessed at https://demos.pragnakalp.com/bert-chatbot-demo
More details can be found on case study: https://www.pragnakalp.com/case-study/chatbot-using-bert-in-python/
This closed-domain chatbot is available in 12 languages and again limitation is that if we increase the paragraph length then it takes longer to find the answer.
We have also prepared API access of this chatbot. So if anyone wants to use it from their system then they can make call to API by passing paragraph and question. The API will respond with answer.
In our latest demo, we have eliminated the text length limitation.
You can check our large-text demo at https://demos.pragnakalp.com/bert-chatbot-demo-large-text.
In this demo, the text length is nearly 500,000 characters and result is generated in 2-3 seconds. We have used the book “India Under British Rule” as a context for this demo. (The link of the book and sample questions are provided on the demo page for reference.)
All above demos are working without GPU. If we add more RAM/CPU and GPU then result speed will increase further and also we can take extract answers from longer text.
As the result generation time has reduced tremendously, our Machine Learning based QnA system could be used at many places and scenarios. Some of them are:
From the progress we have done so far, there seems to be large number of use cases we can create using this system.
As our case studies and demos got popular, we started ranking higher on Google search. For many of the keywords related to “BERT”, now we are on top spot or in top 5!
This is bringing in lot of NLP enthusiasts on our site.
We are committed to take this project on new level. As the training of model, research and development, dataset creation are time and resource consuming tasks, we are actively seeking investors to fund our project. This is becoming a profound commercial product and we have already got couple of paying customers.
If you find it worth investing, then do get in touch with us at letstalk@pragnakalp.com.
