Completed
Ensemble Distillation (e.g. Kim et al. 2016)
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Neural Nets for NLP 2021 - Conditioned Generation
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Language Models • Language models are generative models of text
- 3 Conditioned Language Models
- 4 Calculating the Probability of a Sentence
- 5 Conditional Language Models
- 6 One Type of Language Model Mikolov et al. 2011
- 7 How to Pass Hidden State?
- 8 The Generation Problem
- 9 Ancestral Sampling
- 10 Greedy Search
- 11 Beam Search
- 12 Ensembling . Combine predictions from multiple models
- 13 Linear Interpolation • Take a weighted average of the M model probabilities
- 14 Log-linear Interpolation • Weighted combination of log probabilities, normalize
- 15 Linear or Log Linear?
- 16 Parameter Averaging
- 17 Ensemble Distillation (e.g. Kim et al. 2016)
- 18 Stacking
- 19 Still a Difficult Problem!
- 20 From Speaker/Document Traits (Hoang et al. 2016)
- 21 From Lists of Traits (Kiddon et al. 2016)
- 22 From Word Embeddings (Noraset et al. 2017)
- 23 Basic Evaluation Paradigm
- 24 Human Evaluation Shared Tasks
- 25 Embedding-based Metrics
- 26 Perplexity
- 27 Which One to Use?
