News for hackers. Stuff that matters.

A comment on Building a Better Search Engine for Semantic Scholar (2020). Parent comment

Re:Building a Better Search Engine for Semantic Scholar (2020) by dunefox on Sunday August 29, 2021 @01:25PM (#28348638)
> pre-trained on Google News Collection like most Transformer models are

BERT for example was trained on Wikipedia and Book corpora. Do you have a source for this claim?

[ Parent | on HN ]

There are no comments on this comment yet.