Discovering the NLP built-in algorithms in Amazon SageMaker
SageMaker includes four NLP algorithms, enabling supervised learning (SL) and unsupervised learning (UL) scenarios. In this section, you'll learn about these algorithms, what kinds of problems they solve, and what their training scenarios are. Let's have a look at an overview of the algorithms we'll be discussing:
- BlazingText builds text classification models (SL) or computes word vectors (UL). BlazingText is an Amazon-invented algorithm.
- LDA builds UL models that group a collection of text documents into topics. This technique is called topic modeling.
- NTM is another topic modeling algorithm based on neural networks, and it gives you more insight into how topics are built.
- Sequence to Sequence (seq2seq) builds deep learning (DL) models, predicting a sequence of output tokens from a sequence of input tokens.
Discovering the BlazingText algorithm
The BlazingText algorithm was invented...
