A challenge for named entity disambiguation (NED), the task of mapping textual mentions to entities in a knowledge base, is how to disambiguate entities that appear rarely in the training data, termed tail entities. Humans use subtle reasoning patterns based on knowledge of entity facts, relations, and types to disambiguate unfamiliar entities. Inspired by these patterns, we introduce Bootleg, a self-supervised NED system that is explicitly grounded in reasoning patterns for disambiguation. We define core reasoning patterns for disambiguation, create a learning procedure to encourage the self-supervised model to learn the patterns, and show how to use weak supervision to enhance the signals in the training data. Encoding the reasoning patterns in a simple Transformer architecture, Bootleg meets or exceeds state-of-the-art on three NED benchmarks. We further show that the learned representations from Bootleg successfully transfer to other non-disambiguation tasks that require entity-based knowledge: we set a new state-of-the-art in the popular TACRED relation extraction task by 1.0 F1 points and demonstrate up to 8% performance lift in highly optimized production search and assistant tasks at a major technology company

Awesome Games Done Quick is back again for a video game speedrunning extravaganza. Players are beating dozens of games as quickly as possible for a week straight -- all for charity. ET and running nonstop until Jan. 15 at 1 a.m., speedrunners are racing through over 150 different games at AGDQ 2017, and every minute of it is being broadcast live on Twitch. Proceeds raised during the marathon will go to the Prevent Cancer Foundation. SEE ALSO: Watch a 5-Minute Playthrough of'Super Mario Bros.' Break a Record Assuming you might not be tuning in for every single run, we compiled a list of what may be some of the most entertaining ones of AGDQ this year. Check out the official schedule for the full roster.