I'm a linguist, I'm new to AI and
I would like to know if BERT is able to get the meaning of each word based on context.
I've done some searches and found that BERT is able to do that and that if I'm not wrong, it recognizes them/ converts them into unique vectors, but that's not the output I want.
What I want is to get the meaning/ or the components that constitute the meaning of each word, written in plain English, is this possible?
No, you can not get the meaning of the word in plain english. The whole idea of the BERT is to convert plain english into meaningful numerical representations.
Unfortunately, these vectors are not interpretable. It is a general limitation of Deep Learning compared to other traditional ML models that use self-extracted features.
But note that you can use these representation to find out certain relationships between words. For example the words that are close to each other (in terms of some distance measure), have similar meanings. Have a look at this link for more information.
https://opensource.googleblog.com/2013/08/learning-meaning-behind-words.html
