YoVDO

Neural Nets for NLP 2020 - Structured Prediction with Local Independence Assumptions

Offered By: Graham Neubig via YouTube

Tags

Neural Networks Courses Natural Language Processing (NLP) Courses Normalization Courses Sequence Labeling Courses

Course Description

Overview

Explore structured prediction in natural language processing through a comprehensive lecture covering the fundamentals of conditional random fields, local independence assumptions, and their applications. Delve into the importance of modeling output interactions, understand the differences between local and global normalization, and learn about CRF training and decoding techniques. Gain insights into sequence labeling, recurrent decoders, and the calculation of partition functions in this in-depth exploration of advanced NLP concepts.

Syllabus

Intro
A Prediction Problem
Types of Prediction
Why Call it "Structured" Prediction?
Why Model Interactions in Output? . Consistency is important
Sequence Labeling as
Recurrent Decoder
Local Normalization vs. Global Normalization
Conditional Random Fields
CRF Training & Decoding
Revisiting the Partition Function
Forward Calculation: Final Part Finish up the sentence with the sentence final symbol


Taught by

Graham Neubig

Related Courses

Natural Language Processing
Columbia 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 tecnologĂ­as del lenguaje humano
Universidad de Alicante via MirĂ­adax
Natural Language Processing
Indian Institute of Technology, Kharagpur via Swayam