Given a set of words, return words that are similar with them. I also implemented three type of vector embedings(term-context, term-document, and word2vedc) along with PPMI weighting(Positive Pointwise Mutual Information) and tf-idf weighting. Besides cosine similarity, I implemented jaccard similarity and dice similarty function to see, which one could return a result that is more similar with the orginal words set.
-
Notifications
You must be signed in to change notification settings - Fork 0
YuhaoT/NLP-Text-Similarity
About
Given a set of words, return words that are similar with them.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published