Главная
Study mode:
on
1
Intro
2
Sentence Representations
3
Calculating Attention (1)
4
A Graphical Example
5
Attention Score Functions (1)
6
Attention Score Functions (2)
7
Multi-headed Attention
8
Attention Tricks
9
Summary of the Transformer
10
Training Tricks
11
Masking for Training
12
Incorporating Markov Properties
13
Coverage
14
Input Sentence: Copy
15
Dictionary Probabilities
16
Previously Generated Things
17
Various Modalities
18
Multiple Sources
Description:
Learn about attention mechanisms in neural networks for natural language processing in this comprehensive lecture from CMU's Neural Networks for NLP course. Explore the "Attention is All You Need" paper, improvements to attention techniques, specialized attention varieties, and what neural networks actually attend to. Dive into topics like sentence representations, attention score functions, multi-headed attention, training tricks, and applications to various modalities. Gain insights on incorporating Markov properties, coverage, dictionary probabilities, and handling multiple sources in attention-based models.

Neural Nets for NLP 2021 - Attention

Graham Neubig
Add to list
0:00 / 0:00