Hi
Vittorio, thanks for reaching out and for trying that notebook out. If you have time to rerun it right now try replacing it with this link
https://ibm.box.com/shared/static/m780gey24zumz7kbyl3aazxextf9v1xq.zip (or try refreshing that colab session I just updated the notebook)
I have been having trouble with box links expiring and I'm speaking to their support about it now on a more permanent solution, but that link should work for at least the next 10 years. Also, feel free to skip that whole section, Download and Preprocess CORD-19, it's not necessary and complete the rest of the notebook, which have the more fun parts
------------------------------
Nick Acosta
------------------------------
Original Message:
Sent: Tue May 19, 2020 12:22 PM
From: Tim Bonnemann
Subject: May 12 Virtual Meetup: Introduction to Modern NLP with Hugging Face and CORD-19
Thanks, Vittorio. Looking into it...
------------------------------
Tim Bonnemann
Original Message:
Sent: Tue May 19, 2020 07:42 AM
From: Vittorio Carullo
Subject: May 12 Virtual Meetup: Introduction to Modern NLP with Hugging Face and CORD-19
Hello, I tried to run the notebook but the Box link pointing to CORD-19 zip dataset has apparently been removed: here is an extract to the "Download and unzip dataset" cell output:
HTTP request sent, awaiting response... 301 Moved PermanentlyLocation:
https://ibm.ent.box.com/public/static/7s46kjtquhsxetli0xlf2o7hx7c5fem0.zip [following]--2020-05-19 11:27:26--
https://ibm.ent.box.com/public/static/7s46kjtquhsxetli0xlf2o7hx7c5fem0.zipResolving ibm.ent.box.com (ibm.ent.box.com)... 107.152.27.211Connecting to ibm.ent.box.com (ibm.ent.box.com)|107.152.27.211|:443... connected.HTTP request sent, awaiting response... 404 Not Found2020-05-19 11:27:26 ERROR 404: Not Found.Archive: /content/CORD-19.zip End-of-central-directory signature not found. Either this file is not a zipfile, or it constitutes one disk of a multi-part archive. In the latter case the central directory and zipfile comment will be found on the last disk(s) of this archive.unzip: cannot find zipfile directory in one of /content/CORD-19.zip or /content/CORD-19.zip.zip, and cannot find /content/CORD-19.zip.ZIP, period.
Can you please re-enable the link or specify an alternate location?
Thanks, Vittorio
------------------------------
Vittorio Carullo
Original Message:
Sent: Sat May 16, 2020 03:08 AM
From: Tim Bonnemann
Subject: May 12 Virtual Meetup: Introduction to Modern NLP with Hugging Face and CORD-19
For those who weren't able to make it or wanted to take another look, the replay is now available. Enjoy!
------------------------------
Tim Bonnemann
Original Message:
Sent: Tue May 12, 2020 11:05 AM
From: Tim Bonnemann
Subject: May 12 Virtual Meetup: Introduction to Modern NLP with Hugging Face and CORD-19
Starts in 3 hours at 11am Pacific Time (2pm Eastern):
https://live.remo.co/e/virtual-meetup-introduction-to-m
------------------------------
Tim Bonnemann
Original Message:
Sent: Mon May 11, 2020 03:53 PM
From: Tim Bonnemann
Subject: May 12 Virtual Meetup: Introduction to Modern NLP with Hugging Face and CORD-19
Oops, here's the correct link to the calendar entry, which has more info about tomorrow's virtual meetup:
Virtual Meetup: Introduction to Modern NLP with Hugging Face and CORD-19
See you tomorrow!
------------------------------
Tim Bonnemann
Original Message:
Sent: Mon May 11, 2020 03:33 PM
From: Tim Bonnemann
Subject: May 12 Virtual Meetup: Introduction to Modern NLP with Hugging Face and CORD-19
Quick reminder we'll be kicking off our monthly virtual meetup series tomorrow!
Join us Tuesday, May 12 at 11am Pacific Time:
Introduction to Modern NLP with Hugging Face and CORD-19
In this session, attendees will be introduced to transformers, a modeling architecture that is changing the Natural Language Processing (NLP) field. The hands-on demonstration will provide some examples of the NLP tasks that transformers can perform, how tools like Hugging Face's transformer library can help developers and data scientists perform these tasks quickly, and provide an example of one such task utilizing the AI2's new CORD-19 dataset.
There will be plenty of opportunity to ask questions and talk directly with our presenter. If you have questions or comments before or after the event, just reply below.
Should be fun!
------------------------------
Tim Bonnemann
------------------------------
#GlobalAIandDataScience
#GlobalDataScience