I am very glad to see my first research paper published with Rakhshanda Rukham.


Chatbots became a common customer service and e-commerce tool in recent years. Most of the chat platforms offer chatbot integration opportunities. Natural Language Processing (NLP) is powering chatbots worldwide and is at a well-developed stage for English and major languages. Still, lots of improvement and regular retraining are required as use cases for chatbots can be very different and evolving every day. Retraining is also important for languages that don’t have very strong NLP. In this paper, a crowdsourced, user-generated retraining system is being suggested to make the chatbot NLPs auto-retrained by the users who are actually using it. Experiments result in an average of 17% improvement in the NLP results.

Link: Crowdsourced NLP Retraining Engine in Chatbots

Share via
Copy link
Powered by Social Snap