beekbin/bert-cosine-sim

Fine-tune BERT to generate sentence embedding for cosine similarity

bert-cosine-sim's Issues

Multilingual embeddings based on similarity of translated pairs

Hey,

How would you go on generating embeddings in a language agnostic way based on the multi-BERT model using "bert-base-multilingual-cased" instead of "bert-base-uncased" ?

A similar approach based on translated pairs instead of pairs of similar sentences in english could improve the embeddings from the current multilingual one.
What is your view around that?

Nice library btw! :D

How to use this library??

please, can u describe how to use this library?
Which dataset u used and how to prepare it in such a way that it can be feed directly to BERT and generate embeddings.

train data and extract feature

Hi:
can you provide the train data? how i extract sentence feature?
thanks