Abstract

In this talk, I will argue that many phenomena studied in machine learning and natural language processing may be byproducts derived from simpler, more fundamental principles. There will never be a complete list of all rules in a given language, nor a complete list of objects or relationships. The language itself would better be viewed as an evolving, ever-changing complex system. This should be reflected in the machine learning models we use to describe it.

This talk will be given live during the GeCKo symposium (May 18th; 14:30, UTC+2). In order to watch it and participate in the discussion, you will need to register.

Slides

Thank you for watching! What's next?

• Attend the live discussion session for this keynote on May 18th! Check the program and consider registering in advance.
• Leave comments/questions on our keynote talks in the #keynotequestions channel on geckosympo.slack.com. !! To access it you need to register for GeCKo !! You will then receive an invitation to Slack.
• Explore! Watch the other keynote talks and check out the posters.