Merge pull request #49336 from GraemeMalcolm/main

Updated embeddings info for accuracy

Author: JamesJBarnett

learn-pr/wwl-data-ai/analyze-images-computer-vision/includes/2b-computer-vision-models.md

@@ -32,13 +32,13 @@ CNNs have been at the core of computer vision solutions for many years. While th
 
 ### Transformers
 
-Most advances in computer vision over the decades have been driven by improvements in CNN-based models. However, in another AI discipline - *natural language processing* (NLP), another type of neural network architecture, called a *transformer* has enabled the development of sophisticated models for language. Transformers work by processing huge volumes of data, and encoding language *tokens* (representing individual words or phrases) as vector-based *embeddings* (arrays of numeric values). You can think of an embedding as representing a set of dimensions that each represent some semantic attribute of the token. The embeddings are created such that tokens that are commonly used in the same context are closer together dimensionally than unrelated words.
+Most advances in computer vision over the decades have been driven by improvements in CNN-based models. However, in another AI discipline - *natural language processing* (NLP), another type of neural network architecture, called a *transformer* has enabled the development of sophisticated models for language. Transformers work by processing huge volumes of data, and encoding language *tokens* (representing individual words or phrases) as vector-based *embeddings* (arrays of numeric values). You can think of an embedding as representing a set of dimensions that each represent some semantic attribute of the token. The embeddings are created such that tokens that are commonly used in the same context define vectors that are more closely aligned than unrelated words.
 
 As a simple example, the following diagram shows some words encoded as three-dimensional vectors, and plotted in a 3D space:
 
 ![Diagram of token vectors in a 3D space.](../media/language-encoder.png)
 
-Tokens that are semantically similar are encoded in similar positions, creating a semantic language model that makes it possible to build sophisticated NLP solutions for text analysis, translation, language generation, and other tasks.
+Tokens that are semantically similar are encoded in similar directions, creating a semantic language model that makes it possible to build sophisticated NLP solutions for text analysis, translation, language generation, and other tasks.
 
 > [!NOTE]
 > We've used only three dimensions, because that's easy to visualize. In reality, encoders in transformer networks create vectors with many more dimensions, defining complex semantic relationships between tokens based on linear algebraic calculations. The math involved is complex, as is the architecture of a transformer model. Our goal here is just to provide a *conceptual* understanding of how encoding creates a model that encapsulates relationships between entities.