Artificial Intelligence Stack Exchange is a question and answer site for people interested in conceptual questions about life and challenges in a world where "cognitive" functions can be mimicked in purely digital environment. It only takes a minute to sign up.
Sign up to join this community
I'm trying to compare Glove, Fasttext, Bert on the basis of similarity between 2 words using Pre-trained Models. Glove and Fasttext had pre-trained models that could easily be used with gensim word2vec in python.
Does BERT have any such models?
Is it possible to check the similarity between two words using BERT?
1. Does BERT have any such models?
If you mean the pretrained model, then the answer is YES.
BERT has Cased and Uncased models and also models for other language (BERT-Base, Multilingual Cased and BERT-Base, Multilingual Uncased, trained in 104 languages). You can check those models here.
2. Is it possible to check similarity between two words using BERT?
Refer to this Google Colab Notebook, it is not appopriate with BERT Embeddings for Word-Level similarity comparisons.
However, doing sentence embedding similarity comparisons are still valid with BERT.
That's it, hope it helps you :)
