Global AI and Data Science

 View Only

Replay Available! Text Extensions for Pandas

By Tim Bonnemann posted Fri March 04, 2022 03:09 PM

  

We enjoyed another great talk at our February 24 virtual meetup. Thanks to Fred Reiss for sticking around an extra 15 minutes to answer all of your excellent questions.

Description:
Most areas of Python data science have standardized Pandas DataFrames for representing and manipulating structured data in memory. Natural Language Processing, though, not so much. In this presentation, we’ll explain why you should be using Pandas for NLP. Pandas DataFrames make every phase of NLP easier, from creating new models to evaluating their effectiveness to building applications that integrate those models. We’ll talk about our open source library, Text Extensions for Pandas, which adds special data types and library integrations specifically geared to NLP use cases. We’ll also explain how these extensions connect to some basic NLP concepts, and then we’ll finish with an example of using Pandas to build an NLP application.

Speaker bio:
Fred Reiss is a Principal Research Staff Member at IBM Research and Chief Architect at IBM’s Center for Open-Source Data and AI Technologies (CODAIT). He is also one of the authors of the Text Extensions for Pandas library. Fred received his Ph.D. from U.C. Berkeley in 2006 and immediately IBM Research, joining the CODAIT center in 2015. Fred has written multiple peer-reviewed papers in the areas of natural language processing, database systems, and machine learning.

For those of you who missed it, here’s the recording:


And here are Fred’s slides.

Announcements (updated):

  • Details for our March virtual meetup have been announced. Join us Wednesday, March 16 to learn about Trustworthy Machine Learning. Check the calendar for details and to RSVP.
  • Check out two recent member spotlights and let us know who we should feature next!
  • Please make sure to subscribe to IBM Community on YouTube!
  • The new worldwide User Group for Artificial Intelligence, Data, and Analytics (AIDAUG) is hosting an AI marathon on Pi Day, March 14. Learn more: https://aidaug.org/piday
  • Want to help organize your local IBM Community meetup? Join our Slack!
  • As always, let us know which topics you’d like us to cover at upcoming events. Thanks!

Have a great weekend! Hope to see you March 16 at our next event!



#GlobalAIandDataScience
#GlobalDataScience
#virtualmeetup
0 comments
13 views

Permalink