Completed
Minimum Description Length (MDL) Probes
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
CMU Neural Nets for NLP: Model Interpretation
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Why interpretability?
- 3 What is interpretability?
- 4 Two broad themes
- 5 Source Syntax in NMT
- 6 Why neural translations are the right length?
- 7 Fine grained analysis of sentence embeddings
- 8 What you can cram into a single vector: Probing sentence embeddings for linguistic properties
- 9 Issues with probing
- 10 Minimum Description Length (MDL) Probes
- 11 How to evaluate?
- 12 Explanation Techniques: gradient based importance scores
- 13 Explanation Technique: Extractive Rationale Generation
