search

MicrosoftDocs / azure-docs

Open source documentation of Microsoft Azure
https://docs.microsoft.com/azure
Creative Commons Attribution 4.0 International
10.25k stars 21.41k forks source link

More information about the model #86277

Closed EmanueleGusso closed 2 years ago

EmanueleGusso commented 2 years ago

Good morning, First of all I'd like to thank you for the amazing work done. I'm writing because I want to ask you if you can provide further information about the deep learning model which performs the text summarization task. Is there a paper or something similar? In particular I'm interested in the kind of sentence segmentation which is performed as preprocessing step. Do you use an external sentence segmentation (e.g. spacy)? Besides I would like to know if you are planning to increase the number of maximum sentences (which is 20 at the moment). I thank you in advance and I apologize for bothering you!

Document Details

⚠ Do not edit this section. It is required for docs.microsoft.com ➟ GitHub issue linking.

ram-msft commented 2 years ago

@EmanueleGusso Thanks for the question. We are investigating the issue and will update you shortly.

ram-msft commented 2 years ago

We have developed the NLP-recipes github repo and it has included many SOTA algorithms, like BERT-SUM, PRESUM and abstractive summarization methods from Microsoft Research like UniLM. Our repo uses pytorch and Hugging Faces’s transformer. We have many examples here: https://github.com/microsoft/nlp-recipes/tree/master/examples/text_summarization Please check it out.

We have roadmap to support more sentences in the near future.

We will now proceed to close this thread. If there are further questions regarding this matter, please tag me in your reply. We will gladly continue the discussion and we will reopen the issue.