Completed
Rule of Thumb 1: Multitask to Increase Data
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Neural Nets for NLP 2017 - Multilingual and Multitask Learning
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Remember, Neural Nets are Feature Extractors!
- 3 Types of Learning
- 4 Plethora of Tasks in NLP
- 5 Rule of Thumb 1: Multitask to Increase Data
- 6 Rule of Thumb 2
- 7 Standard Multi-task Learning
- 8 Examples of Pre-training Encoders
- 9 Regularization for Pre-training (e.g. Barone et al. 2017)
- 10 Selective Parameter Adaptation
- 11 Soft Parameter Tying
- 12 Supervised/Unsupervised Adaptation
- 13 Supervised Domain Adaptation through Feature Augmentation
- 14 Unsupervised Learning through Feature Matching
- 15 Multilingual Inputs
- 16 Multilingual Structured Prediction/ Multilingual Outputs
- 17 Teacher-student Networks for Multilingual Adaptation (Chen et al. 2017)
- 18 Types of Multi-tasking
- 19 Multiple Annotation Standards
