This directory contains the ready to use python scripts to find the similarity between any 2 given documents.

There are so many pre-trained word embeddings are available for representing the text data into vector form. Here I have written a code to find the distance/similarity between the 2 documents using several embeddings -

1. TF-IDF
2. word2vec
3. ELMO
4. Universal Sentence Encoder
5. Flair embeddings
6. Spacy embeddings
7. WMD (Word Movers Distance)
8. Sentence transformers

python libraries used - Tensorflow, Gensim, Sklearn, Flair, sentence_transformers, numpy