Language Learning with BERT - TensorFlow and Deep Learning Singapore

preview_player
Показать описание
Speaker: Martin Andrews


Produced by Engineers.SG

Help us caption & translate this video!

Рекомендации по теме
Комментарии
Автор

@10:05 - Excellent explanation of Byte-Pair Encodings, thanks.

rohitdhankar
Автор

The presenter says, these models "do not use RNNs" (correct), instead "they use CNNs" (incorrect, no use of convolution kernels). They use simple linear transformations of the type XW(transpose) + b

autripat
Автор

Thank you. This summary/introduction is very very helpful.

daewonyoon
Автор

wow engineers sg sure haz come a long way ha! great talk

archywillhe
Автор

Where to get this PPT; Please share the link

mkpandey
Автор

Could I extract word embeddings from BERT and use them for unsupervised learning, e.g. topic modeling? :)

monart
Автор

Does bpe also works well for non english languages like chinese and french?

janekou
Автор

BERT uses wordpiece. Albert uses sentence piece

zingg
Автор

what in gods name are you talking about?? what is an LSTM chain?? I came here because I need to know im writing the correct content for my website and I haven't a fucking clue what the hell you are on about.

chriscannon