Contents
0:00 - Introduction
2:21 - NLP projects are like start-ups
6:12 - Machile Learning Hierarchy of Needs
11:45 - Making modelling decision that are simple, obvious and wrong (Problem #1)
17:05 - Compose generic models into novel solutions (Solution #1)
19:05 - Workflow #1
22:35 - Big annotation projects make evidence collection expensive (Problem #2)
24:00 - Run your own micro-experiments (Solution #2)
27:38 - It is hard to get good data by boring out underpaid people (Problem #3)
28:43 - Smaller teams, better workflows (Solution #3)
31:29 - End of lecture
31:50 - Questions
logankilpatrick
commented
2 years ago
https://youtu.be/jpWqz85F_4Y
Contents 0:00 - Introduction 2:21 - NLP projects are like start-ups 6:12 - Machile Learning Hierarchy of Needs 11:45 - Making modelling decision that are simple, obvious and wrong (Problem #1) 17:05 - Compose generic models into novel solutions (Solution #1) 19:05 - Workflow #1 22:35 - Big annotation projects make evidence collection expensive (Problem #2) 24:00 - Run your own micro-experiments (Solution #2) 27:38 - It is hard to get good data by boring out underpaid people (Problem #3) 28:43 - Smaller teams, better workflows (Solution #3) 31:29 - End of lecture 31:50 - Questions