Explore a comprehensive lecture on neural networks for natural language processing, focusing on predicting the next word in a sentence. Delve into topics such as describing words by their context, counting and prediction techniques, skip-grams and Continuous Bag of Words (CBOW) models, and methods for evaluating and visualizing word vectors. Learn about advanced techniques for word vector creation and gain practical insights through provided slides and code examples. This lecture, part of CMU's CS 11-747 course, offers a deep dive into the fundamentals of word embeddings and their applications in NLP tasks.
Neural Nets for NLP 2017 - A Simple Exercise - Predicting the Next Word in a Sentence
Graham Neubig via YouTube
Overview
Syllabus
Introduction
Evaluation
Language Models
Feature Eyes Models
Example
Converting Scores to Probabilities
Computation Graph
Lookup
Loss Function
Perimeter Update
Unknown Words
Vocabulary
Unfair Advantage
Problems of Previous Model
Neural Language Models
Code
InputOutput Embedding
Training Tricks
Learning Rate Decay
Taught by
Graham Neubig
Related Courses
-
Neural Nets for NLP 2021 - Distributional Semantics and Word Vectors
-
CMU Neural Nets for NLP - Distributional Semantics and Word Vectors
-
Neural Nets for NLP 2019 - Word Vectors
-
Neural Nets for NLP 2017 - Convolutional Networks for Text
-
Neural Nets for NLP 2020 - Convolutional Neural Networks for Text
-
Neural Nets for NLP 2019 - Convolutional Neural Networks for Language
