Skip to content

Madhavsingla1/Semantically_Similar_Question_Detection_System

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Capstone_Project

Project was based on nlp techniques for checking similarity between a pair of questions

Techniques

We used four different techniques for checking the similarity

  • Bag Of Words (BOW)
  • TF-IDF (Term frequency and inverse document frequency)
  • Word2Vec
  • Glove

Classifiers

  • XGBOOST
  • ADABOOST

The best results are given by glove and word2vec as we didn't have a powerful system so we were not able to take glove to its full potential.

DataSet

The data set that we used was taken from kagle Dataset which was based on quora website

Future Work

We are currently working on the deeplearning techiques to improve the model.

About

Project on checking the semantically similar questions from a Q/A site database and giving the best answers for the asked question

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published