Want to create a Python script that can compare two text strings and decide how simular they are. Best method I found for comparison is cosine-similarity.
To understand the words in each string I started locking at Word2vec but read that numberbatch method is better.
Did find an older post with some good implementations in the answers. But this only supports the English language and I need Swedish. Calculate cosine similarity given 2 sentence strings
Is there any better way of comparing similarities between two short strings?
And how to do it for Swedish language?
