blazingeagle1002 / DocumentSimilarity

DocumentSimilarity

This repository containes the various methods that have been tried to find the similarity between documents. The dataset used is MIMICIII. The various methods used are:

1. Doc2vec using gensim
2. Tf-Idf method
3. Lda coupled with Topic Modelling using gensim
4. Document similarity using Facebook Infersent model