Recipes for automatic text summarization using Google BERT and Microsoft UniLM

Re:Recipes for automatic text summarization using Google BER... by sharatsc on Tuesday March 31, 2020 @01:30PM (#22739983)

It is at the token level. The length of the results can be changed.

[ Parent | on HN ]

Re:Recipes for automatic text summarization using Google BER... by Der_Einzige on Wednesday April 01, 2020 @12:53AM (#22745823)

It looks like according to the notebook recepies that it's actually working at the sentence level (despite your claim). The way you train these is to mark a sentence as "1" or "0" based on if it's selected.

Oh well, the world waits longer for a word-level (willing to skip around in sentences) and grammatically correct extractive summarizer. You got my hopes up though.

https://github.com/microsoft/nlp-recipes/blob/master/example...

My (failed) attempt to build what I was actually looking for:

https://github.com/Hellisotherpeople/CX_DB8

[ Parent | on HN ]

Re:Recipes for automatic text summarization using Google BER... by sharatsc on Tuesday March 31, 2020 @01:50PM (#22740283)

https://techcommunity.microsoft.com/t5/ai-customer-engineeri...

[ Parent | on HN ]