Getting only 55% accuracy using 6B.50 word embeddings

Getting only 55% accuracy using 6B.50 word embeddings and following the exact same procedure as in the video.
How to improve this? Leaderboard has 100% accuracy

Hey @Saurabh-Mittal-1729567117136176, since this is part of leaderboard challenge its not ethical to share the solution code directly. This is the real time when you learnings comes to test. Also since in this challenge there is no model involved. You simply need to find cosine similarity between all words, i can just guide you to find cosine similarity with all remaining words and take its average. Repeat this process for all other words. And than to predict odd one, take the one having minmum average similarity.

Hope this cleared your doubt. :blush:

I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.

On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.