Neural Nets for NLP 2020: Advanced Search Algorithms
Offered By: Graham Neubig via YouTube
Course Description
Overview
Syllabus
Intro
The Generation Problem
Ancestral Sampling
Why do we Search?
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 search criterion does not optimize accuracy
What beam size should I use?
Better Search can Hurt Results! (Koehn and Knowles 2017)
How to Fix Model Errors?
Minimum Bayes Risk Reranking
Improving Diversity in top N Choices
A Typical Model Error: Length Bias
Length Normalization
Predict the output length (Eriguchi et al. 2016)
Cautions about Sampling- based Search · Is sampling necessary for diversity?: questionable, we could do diverse beam search instead
Taught by
Graham Neubig
Related Courses
Natural Language ProcessingColumbia University via Coursera Natural Language Processing
Stanford University via Coursera Introduction to Natural Language Processing
University of Michigan via Coursera moocTLH: Nuevos retos en las tecnologías del lenguaje humano
Universidad de Alicante via Miríadax Natural Language Processing
Indian Institute of Technology, Kharagpur via Swayam