What Kenton Lee thinks about neural networks
One of the four authors of the 2018 paper "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding", at Google AI Language, the affiliation printed on the paper.
Kenton Lee did not write this page.
We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.
Filter neural networks · Newest first
Only Kenton Lee on neural networks. See everyone on neural networks
2 dated positions, 2018, in their own words. Our reading of what Kenton Lee has said — not written or endorsed by them.
-
Our readingPre-trained representations reduce the need for many heavily-engineered task-specific architectures.
Their wordsWe show that pre-trained representations reduce the need for many heavily-engineered task-specific architectures.
↗BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingarxiv.org All 16 from this paper
-
Their wordsIntuitively, it is reasonable to believe that a deep bidirectional model is strictly more powerful than either a left-to-right model or the shallow concatenation of a left-to-right and a right-to-left model.
↗BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingarxiv.org All 16 from this paper