Explore convolutional networks for text processing in this comprehensive lecture from CMU's Neural Networks for NLP course. Dive into bag-of-words models, n-grams, and convolution techniques. Learn about context windows, sentence modeling, and advanced concepts like stacked and dilated convolutions. Discover structured convolution methods and approaches for modeling sentence pairs. Gain insights into visualizing convolutional neural networks for text analysis. Access accompanying slides and code examples to reinforce your understanding of these powerful techniques in natural language processing.
Overview
Syllabus
Intro
An Example Prediction Problem: Sentence Classification
A First Try: Bag of Words (BOW)
Continuous Bag of Words (CBOW) movie
What do Our Vectors Represent?
Why Bag of n-grams?
What Problems w/ Bag of n-grams?
Time Delay Neural Networks (Waibel et al. 1989)
Convolutional Networks (LeCun et al. 1997)
Standard conv2d Function
Stacked Convolution
Dilated Convolution (e.g. Kalchbrenner et al. 2016)
An Aside: Nonlinear Functions • Proper choice of a non-linear function is essential in stacked networks
Why (Dilated) Convolution for Modeling Sentences? • In contrast to recurrent neural networks (next class)
Example: Dependency Structure
Why Model Sentence Pairs?
Siamese Network (Bromley et al. 1993)
Taught by
Graham Neubig
Related Courses
-
Neural Nets for NLP 2019 - Convolutional Neural Networks for Language
-
Neural Nets for NLP 2020 - Convolutional Neural Networks for Text
-
Gen AI Foundational Models for NLP & Language Understanding
-
Machine Learning and NLP Basics
-
Neural Nets for NLP - Recurrent Networks for Sentence or Language Modeling
-
Neural Nets for NLP 2017 - Recurrent Neural Networks
