Completed
Why do we Search?
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Neural Nets for NLP 2020: Advanced Search Algorithms
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 The Generation Problem
- 3 Ancestral Sampling
- 4 Why do we Search?
- 5 Search Errors, Model Errors example from Neubig (2015) • Search error: the search algorithm fails to find an output that optimizes its search criterion . Model error: the output that optimizes the se…
- 6 What beam size should I use?
- 7 Better Search can Hurt Results! (Koehn and Knowles 2017)
- 8 How to Fix Model Errors?
- 9 Minimum Bayes Risk Reranking
- 10 Improving Diversity in top N Choices
- 11 A Typical Model Error: Length Bias
- 12 Length Normalization
- 13 Predict the output length (Eriguchi et al. 2016)
- 14 Cautions about Sampling- based Search · Is sampling necessary for diversity?: questionable, we could do diverse beam search instead
