Unsupervised Text Generation - Techniques and Applications
Offered By: Toronto Machine Learning Series (TMLS) via YouTube
Course Description
Overview
Explore a novel search-and-learning framework for unsupervised text generation in this 24-minute conference talk by Dr. Lili Mou, Assistant Professor at the University of Alberta and Alberta Machine Intelligence Institute Fellow. Discover how heuristic scoring functions and stochastic local search techniques like simulated annealing can be used to generate high-quality candidate sentences for various natural language processing tasks. Learn about the integration of sequence-to-sequence models to improve inference efficiency and reduce search noise. Gain insights into the practical applications of this framework for industrial use, particularly for startups and new task development. Delve into Dr. Mou's extensive research background in deep learning applied to natural language processing and programming language processing, and understand how this innovative approach achieves high unsupervised performance across various natural language generation applications.
Syllabus
Unsupervised Text Generation Techniques and Applications
Taught by
Toronto Machine Learning Series (TMLS)
Related Courses
Intro to Deep Learning with PyTorchFacebook via Udacity Natural Language Processing with Sequence Models
DeepLearning.AI via Coursera Deep Learning
Universidad AnĂ¡huac via edX Create a Superhero Name Generator with TensorFlow
Coursera Project Network via Coursera Natural Language Generation in Python
DataCamp