This course aims to teach learners about effective transfer learning for natural language processing (NLP. The learning outcomes include understanding transfer learning mechanisms using sequence representations, practical improvements on real-world tasks, and the use of the Enso library for benchmarking transfer learning methods. The course covers topics such as representation learning, deep learning, small data problems, logistic regression, second-order optimization, feature engineering, and more. The teaching method involves exploring parameter and data-efficient mechanisms for transfer learning and demonstrating practical improvements. The intended audience for this course includes individuals interested in NLP, machine learning, and transfer learning techniques.
Effective Transfer Learning for NLP - Madison May - ODSC East 2018
Overview
Syllabus
Introduction
Training Data Requirements
Representation Learning
Word Tyvek
Simple Vector Arithmetic
Deep Learning
Deep Learning Problems
Small Data Problems
Transfer Learning
Transfer Learning Diagram
Practical Recommendations
Quality of Embedding
Source Tasks
Logistic Regression
Second Order Optimization
Measuring Variance
Class Balance
Feature Engineering
Enzo
Workflow
Visualization
Documentation
Machine Learning Research
Good Papers
Deep contextualized word representations
Source model
Average Representations
Data Problems
Questions
Taught by
Open Data Science
Related Courses
-
Transfer Learning for NLP with TensorFlow Hub
-
Introduction to Machine Learning
3.5 -
Transfer Learning in NLP and the Birth of the Transformers Library
-
Deep Learning and Transfer Learning for NLP
-
An Introduction to Transfer Learning in NLP and HuggingFace
-
CMU Multilingual NLP 2020 - Multilingual Training and Cross-Lingual Transfer
