A korrentour readingWhat is a korrent?
Unidirectional restrictions are sub-optimal for sentence-level tasks and harmful for token-level tasks that need bidirectional context.
Drawn from what Kristina Toutanova, Kenton Lee and 2 others said
What they actually said
Word for word, with the source under each one. They did not write this page.
Kristina Toutanova Such restrictions are sub-optimal for sentence-level tasks, and could be very harmful when applying fine-tuning based approaches to token-level tasks such as question answering, where it is crucial to incorporate context from both directions. arxiv.org
One of the four authors of the 2018 paper "BERT:…
Their wordsSuch restrictions are sub-optimal for sentence-level tasks, and could be very harmful when applying fine-tuning based approaches to token-level tasks such as question answering, where it is crucial to incorporate context from both directions.
Where this was said
↗BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingarxiv.org
All 16 korrents from this piecethis one is 8th
Kenton Lee Such restrictions are sub-optimal for sentence-level tasks, and could be very harmful when applying fine-tuning based approaches to token-level tasks such as question answering, where it is crucial to incorporate context from both directions. arxiv.org
One of the four authors of the 2018 paper "BERT:…
Their wordsSuch restrictions are sub-optimal for sentence-level tasks, and could be very harmful when applying fine-tuning based approaches to token-level tasks such as question answering, where it is crucial to incorporate context from both directions.
Where this was said
↗BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingarxiv.org
All 16 korrents from this piecethis one is 7th
Ming-Wei Chang Such restrictions are sub-optimal for sentence-level tasks, and could be very harmful when applying fine-tuning based approaches to token-level tasks such as question answering, where it is crucial to incorporate context from both directions. arxiv.org
One of the four authors of the 2018 paper "BERT:…
Their wordsSuch restrictions are sub-optimal for sentence-level tasks, and could be very harmful when applying fine-tuning based approaches to token-level tasks such as question answering, where it is crucial to incorporate context from both directions.
Where this was said
↗BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingarxiv.org
All 16 korrents from this piecethis one is 6th
Jacob Devlin Such restrictions are sub-optimal for sentence-level tasks, and could be very harmful when applying fine-tuning based approaches to token-level tasks such as question answering, where it is crucial to incorporate context from both directions. arxiv.org
One of the four authors of the 2018 paper "BERT:…
Their wordsSuch restrictions are sub-optimal for sentence-level tasks, and could be very harmful when applying fine-tuning based approaches to token-level tasks such as question answering, where it is crucial to incorporate context from both directions.
Where this was said
↗BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingarxiv.org
All 16 korrents from this piecethis one is 5th
Added to korrents 11 Oct 2018 · How quotes work · Something wrong? Tell us
Do you hold this korrent?Do you also believe this?
Related korrents
Our reading — they may agree, disagree or merely touch the same thing. Closest first: a shared subject counts for most, then how near the wording is.