Active learning is, in essence, about maximizing the performance gain (of an underlying, supervised machine learning algorithm) per label. Some possible (query) strategies and the core problem emerging, being sampling bias, are discussed in the introduction to active learning. Then an effective way of circumventing it by balancing exploring and exploiting accordingly is given via […]
We are very pleased to announce a special edition of our Data Science Meetup that is dedicated to looking at COVID-19 from a data science perspective. Did I say “a” data science perspective? Well, it’s certainly not just one … This is again a double bill but with a twist as you will be drawn […]
The right path to making search relevant
Charlie’s talk describes three aspects of search quality, focusing on relevance, and describes how to measure and improve it and tools for doing so.
Thursday, 2019-10-31, 18:00, H26 (VG).
Using Games-With-A-Purpose to Label NLP Data: Lessons from the Last Ten Years
Read MoreMassimo Poesio…