Svoboda | Graniru | BBC Russia | Golosameriki | Facebook
Jump to content

Talk:BERT (language model)

Page contents not supported in other languages.
From Wikipedia, the free encyclopedia
WikiProject iconComputer science
WikiProject iconThis article is within the scope of WikiProject Computer science, a collaborative effort to improve the coverage of Computer science related articles on Wikipedia. If you would like to participate, please visit the project page, where you can join the discussion and see a list of open tasks.
???This article has not yet received a rating on the project's importance scale.
Things you can help WikiProject Computer science with:

WikiProject iconLinguistics: Applied Linguistics
WikiProject iconThis article is within the scope of WikiProject Linguistics, a collaborative effort to improve the coverage of linguistics on Wikipedia. If you would like to participate, please visit the project page, where you can join the discussion and see a list of open tasks.
???This article has not yet received a rating on the project's importance scale.
Taskforce icon
This article is supported by Applied Linguistics Task Force.

Title

[edit]

This page should probably be moved to BERT (language representation model) rather than language model. A language model has a specific meaning in that it models the joint probability distribution of words, whereas BERT doesn't do that, although it can predict a masked word it can't give you the probability distribution.

This would also be consistent with Wikipedia's own definition of a language model.

I agree. Let us move it unless we see substantial protests. Trondtr (talk) 14:03, 1 October 2021 (UTC).[reply]