WelcomeWelcome
Episode 1: Introducing NLP
Episode 2: PreprocessingPreprocessing
Episode 3: Word embeddingsWhat are word embeddings?Word2vec model(Optional) Training a word2vec model on our dataset
Figure 1
Embedding of a cat - We measured its furriness
and found out it’s 70!
Figure 2
Embedding of a cat - We have described it along
two dimensions: furriness and number of legs
Figure 3
Embeddings of a cat and a dog
Figure 4
Embeddings of a cat and a dog and a
caterpillar
Figure 5
Figure 6
Embeddings of a cat and a dog and a caterpillar
- We can describe these animals in many dimensions!
Figure 7
Schematic representations of the different
prediction tasks that CBOW and Skip-gram try to solve
Figure 8
Embedding of king - word2vec model
Figure 9
Embedding of king vs queen - word2vec
model
Figure 10
Exercise solution - word2vec model
Figure 11
Analogy of King - Man + woman ~= Queen
Figure 12
2D visualisation of animal and vehicle word
embeddings