Explore neural network applications in natural language processing through this comprehensive lecture series from Carnegie Mellon University taught by Graham Neubig. Begin with foundational concepts including an introduction to neural networks for NLP and practical exercises in next-word prediction, then progress through essential topics like word vectors and convolutional neural networks for language processing. Master recurrent networks for sentence and language modeling, conditioned generation techniques, and attention mechanisms that form the backbone of modern NLP systems. Delve into advanced representations including sentence and contextualized word embeddings, learn debugging strategies specific to neural NLP models, and understand structured prediction fundamentals. Advance to sophisticated topics including reinforcement learning applications, model interpretation techniques, and latent random variables in NLP contexts. Study parsing methodologies through transition-based approaches and dynamic programming, explore unsupervised and semi-supervised structure learning, and examine dialog system modeling. Investigate document-level processing, knowledge graph integration, and machine reading comprehension using neural networks. Conclude with multi-task and multi-lingual learning strategies, plus advanced search algorithms for neural NLP applications, providing a thorough foundation in both theoretical concepts and practical implementation techniques for neural network-based natural language processing.

Syllabus

CMU Neural Nets for NLP 2019 (1): Intro/Why Neural Nets for NLP
CMU Neural Nets for NLP 2019 (2): A Simple (?) Exercise - Predicting the Next Word
CMU Neural Nets for NLP 2019 (3): Word Vectors
CMU Neural Nets for NLP 2019 (4): Convolutional Neural Networks for Language
CMU Neural Nets for NLP 2019 (5): Recurrent Networks for Sentence or Language Modeling
CMU Neural Nets for NLP 2019 (6): Conditioned Generation
CMU Neural Nets for NLP 2019 (7): Attention
CMU Neural Nets for NLP 2019 (8): Sentence and Contextualized Word Representations
CMU Neural Nets for NLP 2019 (9): Debugging Neural Nets (for NLP)
CMU Neural Nets for NLP 2019 (10): Structured Prediction Basics
CMU Neural Nets for NLP 2019 (11): Reinforcement Learning
CMU Neural Nets for NLP 2019 (12): Structured Prediction with Local Independence Assumptions
CMU Neural Nets for NLP 2019 (13): Model Interpretation
CMU Neural Nets for NLP 2019 (14): Latent Random Variables
CMU Neural Nets for NLP 2019 (15): Transition-based Parsing
CMU Neural Nets for NLP 2019 (16): Parsing w/ Dynamic Programs
CMU Neural Nets for NLP 2019 (18): Unsupervised and Semi-supervised Learning of Structure
CMU Neural Nets for NLP 2019 (19): Models of Dialog
CMU Neural Nets for NLP 2019 (20): Document Level Models
CMU Neural Nets for NLP 2019 (21): Learning from/for Knowledge Graphs
CMU Neural Nets for NLP 2019 (22): Machine Reading w/ Neural Nets
CMU Neural Nets for NLP 2019 (23): Multi-task, Multi-lingual Learning
CMU Neural Nets for NLP 2019 (25): Advanced Search Algorithms