Explore neural representation learning in natural language processing through this comprehensive lecture from the CMU Low Resource NLP Bootcamp 2020. Delve into various methods for learning neural representations of language, covering topics such as word and sentence representations, supervised and unsupervised learning approaches, and case studies on NNLM, Glove, ELMO, and BERT. Gain insights into different structural biases, clusters of approaches, and must-know points about RNN, CNN, and Transformer models. Learn when to use non-contextualized versus contextualized representations and understand the importance of software, models, and corpora in neural representation learning for NLP.
Overview
Syllabus
Neural Representation Learning in Natural Language Processing
Neural Representation Learning for NLP
What is the word representation ?
Why should we learn word representation
How can we get word representations?
Symbolic or Distributed?
Supervised or Unsupervised?
Count-based or Prediction-based?
Case Study: NNLM
Case Study: Glove
Case Study: ELMO
Case Study: BERT
Software, Model, Corpus
Using non-contextualized when ...
Using contextualized when ...
What is the sentence representation
Why do we need sentence representations
How can we learn sentence representations?
Different Structural Biases
Clusters of Approaches
Case Study: Must-know Points about RN
CNN: 1d and 2d Convolution
CNN: Narrow/Equal/Wide Convolution
CNN: Multiple Filter Convolution
Case Study: Must-know Points about Transforme
Taught by
Graham Neubig
Related Courses
-
Mastering Natural Language Processing (NLP) with Deep Learning
-
Sequence Models
4.8 -
Neural Nets for NLP 2019: Sentence and Contextualized Word Representations
-
AI Workflow: Machine Learning, Visual Recognition and NLP
-
CMU Neural Nets for NLP - Distributional Semantics and Word Vectors
-
Natural Language Processing in TensorFlow
4.0
