InfoCoBuild

CS224U - Natural Language Understanding

CS224U: Natural Language Understanding. Instructors: Prof. Christopher Potts, Prof. Bill MacCartney, and Omar Khattab, Department of Linguistics and Computer Science, Stanford University. From conversational agents to automated trading and search queries, natural language understanding underpins many of today's most exciting technologies. How do we build these models to understand language efficiently and reliably? In this project-oriented course, you will develop systems and algorithms for robust machine understanding of human language. The course draws on theoretical concepts from linguistics, natural language processing, and machine learning. You can find more information about this course, such as lecture slides and syllabus, here. (from Stanfordonline)

Lecture 09 - Distributed Word Representations: Static Representations from Contextual Models

Go to the Course Home or watch other lectures:

Lecture 01 - Course Overview

Lecture 02 - Homework 1: Word Relatedness

Lecture 03 - Distributed Word Representations: High-Level Goals and Hypotheses

Lecture 04 - Distributed Word Representations: Matrix Designs

Lecture 05 - Distributed Word Representations: Vector Comparison

Lecture 06 - Distributed Word Representations: Basic Reweighting

Lecture 07 - Distributed Word Representations: Dimensionality Reduction

Lecture 08 - Distributed Word Representations: Retrofitting

Lecture 09 - Distributed Word Representations: Static Representations from Contextual Models

Lecture 10 - Homework 2: Sentiment Analysis

Lecture 11 - Overview of Supervised Sentiment Analysis

Lecture 12 - Supervised Sentiment Analysis: General Practical Tips

Lecture 13 - Supervised Sentiment Analysis: Stanford Sentiment Treebank

Lecture 14 - Supervised Sentiment Analysis: DynaSent

Lecture 15 - Supervised Sentiment Analysis: sst.py

Lecture 16 - Supervised Sentiment Analysis: Hyperparameter Search

Lecture 17 - Supervised Sentiment Analysis: Feature Representation

Lecture 18 - Supervised Sentiment Analysis: RNN Classifiers

Lecture 19 - Contextual Representation Models

Lecture 20 - Contextual Word Representations: Transformers

Lecture 21 - Contextual Word Representations: BERT

Lecture 22 - Contextual Word Representations: RoBERTa

Lecture 23 - Contextual Word Representations: ELECTRA

Lecture 24 - Contextual Word Representations: Practical Fine-tuning

Lecture 25 - Homework 3: Colors

Lecture 26 - Grounded Language Understanding

Lecture 27 - Grounded Language Understanding: Speakers

Lecture 28 - Grounded Language Understanding: Listeners

Lecture 29 - Grounded Language Understanding: Varieties of Contextual Grounding

Lecture 30 - Grounded Language Understanding: The Rational Speech Acts Model

Lecture 31 - Grounded Language Understanding: Neural RSA

Lecture 32 - Natural Language Inference: Overview

Lecture 33 - Natural Language Inference: SNLI, MultiNLI, and Adversarial NLI

Lecture 34 - Natural Language Inference: Adversarial Testing

Lecture 35 - Natural Language Inference: Modeling Strategies

Lecture 36 - Natural Language Inference: Attention

Lecture 37 - NLU and Information Retrieval: Overview

Lecture 38 - NLU and Information Retrieval: Classical IR

Lecture 39 - NLU and Information Retrieval: Neural IR, Part 1

Lecture 40 - NLU and Information Retrieval: Neural IR, Part 2

Lecture 41 - NLU and Information Retrieval: Neural IR, Part 3

Lecture 42 - Relation Extraction: Overview

Lecture 43 - Relation Extraction: Data Resources

Lecture 44 - Relation Extraction: Problem Formulation

Lecture 45 - Relation Extraction: Evaluation

Lecture 46 - Relation Extraction: Simple Baselines

Lecture 47 - Relation Extraction: Directions to Explore

Lecture 48 - Overview of Analysis Methods in NLP

Lecture 49 - Analysis Methods in NLP: Adversarial Testing

Lecture 50 - Analysis Methods in NLP: Adversarial Training (and Testing)

Lecture 51 - Analysis Methods in NLP: Probing

Lecture 52 - Analysis Methods in NLP: Feature Attribution

Lecture 53 - Overview of Methods and Metrics

Lecture 54 - Methods and Metrics: Classifier Metrics

Lecture 55 - Methods and Metrics: Natural Language Generation Metrics

Lecture 56 - Methods and Metrics: Data Organization

Lecture 57 - Methods and Metrics: Model Evaluation

Lecture 58 - Presenting Your Work: Final Papers

Lecture 59 - Writing NLP Papers

Lecture 60 - NLP Conference Submissions

Lecture 61 - Giving Talks

Lecture 62 - Conclusions