I am now using "levenshtein distance" (fuzzywuzzy library) for our NLP Model instead of "cosine similarity" (spaCy library) as we found it's better for shorter texts which is relevant in our case.
.
.
.
I am now using "levenshtein distance" (fuzzywuzzy library) for our NLP Model instead of "cosine similarity" (spaCy library) as we found it's better for shorter texts which is relevant in our case.
Log in or sign up for Devpost to join the conversation.