This course covers the following topics:
- Recurrent Networks and their application in sentence or language modeling
- Understanding Vanishing Gradient and Long Short-Term Memory (LSTM) networks
- Exploring the strengths and weaknesses of recurrence in sentence modeling
- Pre-training techniques for Recurrent Neural Networks (RNNs)
The course teaches skills such as:
- Modeling sentence pairs using Siamese Networks and Convolutional Matching Models
- Utilizing Convolutional Features and Matrix-based Pooling in Natural Language Processing (NLP)
- Implementing RNNs for tasks like language modeling and handling long sequences
The teaching method involves a lecture format, with a focus on theoretical concepts and practical applications in neural networks for NLP.
The intended audience for this course includes students or professionals interested in neural networks, natural language processing, and recurrent networks for sentence modeling.
Neural Nets for NLP - Recurrent Networks for Sentence or Language Modeling
Graham Neubig via YouTube
Overview
Syllabus
Intro
Why Model Sentence Pairs?
Siamese Network (Bromley et al. 1993)
Convolutional Matching Model (Hu et al. 2014) • Concatenate sentences into a 30 tensor and perform convolution
Convolutional Features + Matrix-based Pooling in and Schutze 2015
NLP and Sequential Data
Long-distance Dependencies in Language
Can be Complicated!
Recurrent Neural Networks (Elman 1990)
Unrolling in Time • What does processing a sequence look like?
What Can RNNs Do?
Representing Sentences
e.g. Language Modeling
RNNLM Example: Loss Calculation and State Update
Vanishing Gradient • Gradients decrease as they get pushed back
LSTM Structure
What can LSTMs Learn? (2) (Shi et al. 2016, Radford et al. 2017) Count length of sentence
Handling Long Sequences
Taught by
Graham Neubig
