Engine icon indicating copy to clipboard operation
Engine copied to clipboard

Implement a Doc2Vec mechanism for documents comparisson

Open liadmagen opened this issue 7 years ago • 0 comments

Create an easy way to compare documents through their contents, using Doc2Vec Read this blog post for background and details about this algorithm: https://medium.com/scaleabout/a-gentle-introduction-to-doc2vec-db3e8c0cce5e

To do so, you should first - have a REST API methods to:

  • convert a single document to a vector
  • convert multiple documents (array of strings) to an array of vectors
  • given two vectors, return the distance between them
  • given two documents, convert them to vectors and return the distance (similarity) between them

liadmagen avatar Aug 02 '18 12:08 liadmagen