https://github.com/dark-art108/megatronbot

MegatronBot is a Full-Fledged ChatBot with some awesome Powers 🔥🔥
https://github.com/dark-art108/megatronbot

bert-model chat-application chatbot elmo nlp nlu

Last synced: 3 months ago
JSON representation

MegatronBot is a Full-Fledged ChatBot with some awesome Powers 🔥🔥

• Host: GitHub
• URL: https://github.com/dark-art108/megatronbot
• Owner: DARK-art108
• License: apache-2.0
• Created: 2021-04-11T08:52:49.000Z (almost 4 years ago)
• Default Branch: main
• Last Pushed: 2021-04-11T12:11:45.000Z (almost 4 years ago)
• Last Synced: 2024-05-01T20:21:47.144Z (9 months ago)
• Topics: bert-model, chat-application, chatbot, elmo, nlp, nlu
• Language: JavaScript
• Homepage: https://dark-art108.github.io/MegatronBot/
• Size: 13.3 MB
• Stars: 10
• Watchers: 2
• Forks: 5
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# MegatronBot - Let's Chat

MegatronBot is a fully fleged chatbot with easy to update, integrate with website, easy to deploy in any cloud services like AWS, GCP and azure with a capibility to work in production enviorment.Megatron accepts various formats of inputs you can give a text input, you can also give a Speech as a input.

## What is the need of ChatBot?

Megatron was build by the team of ineuron.ai where I have worked upon a task of Intent Classification and State Tracking.The need of the MegatronBot came as ineuron.ai has a overwhemling responses and queries asked by the student over their newly released courses, as their is a Skype Support team to clarify their queries always but they cant be available 24x7 hours due to this ineuron.ai wants to build a such a great solution where the user can clarify their queries anytime without waiting in a queue for hours.

## How I have apporached to such Solution?

Building a Megatron like ChatBot requires a huge amount of data and various state of the art components.So, the first task is to get a large data,The dataset was creatd by scaraping the queries and answers asked by students over a year to their Skype support team, the dataset include of 20k sentences which were transformed and added to CSV and json format.

I have tried many State of the art language models from BERT-large to DialoGPT to RoBERTa but got an awesome results over Distilled BERT Models with ELMO embeddings.The model then trained over the 20k queries after preprocessing then adding tokens like [SEP], [START], [END] and [EOS].

  

The Architecture of MegatronBot: -



  



Below are some results: