/Question-Answering-system-

It uses extensive NLP and ML techniques at its backend for answering descriptive type queries ( currently, the model has been trained only for Data science and Machine Learning Domain ).

Primary LanguageJupyter Notebook

Question-Answering-system-

The search (user's question input) interface and its output...

The model is predicting all the related tags that the user's question can be in. Note that the tags need not to be mutually exclusive i.e., a question can belong to multiple (overlapping) tags (topics). and then, we are retrieving the top 5 most relevant documents corresponding to that user's query.

Data - https://archive.org/details/stackexchange

output of Q&A system (question tag prediction part) -

https://cloud.githubusercontent.com/assets/9404205/20704556/c0e5a0fc-b645-11e6-9194-5b3fa778f08f.jpg

https://cloud.githubusercontent.com/assets/9404205/20704750/7500cada-b646-11e6-8fc0-3d80417d3a1c.jpg

https://cloud.githubusercontent.com/assets/9404205/20704579/e0752082-b645-11e6-83b5-4e7ced569aff.jpg