pull base content,head:MicrosoftDocs:main,into:wwlpublishsync

Author: wwlpublish

learn-pr/wwl-data-ai/get-started-language-azure/includes/3-azure-text-analysis.md

@@ -54,7 +54,7 @@ For example, suppose you use Azure AI Language to detect entities in the followi
 You can identify the language in which text is written with Azure AI Language's language detection capability. For each document submitted the service detects:
 
 - The language name (for example "English").
-- The ISO 639-1 language code (for example, "en").
+- The ISO 6391 language code (for example, "en").
 - A score indicating a level of confidence in the language detection.
 
 For example, consider a scenario where you own and operate a restaurant. Customers can complete surveys and provide feedback on the food, the service, staff, and so on. Suppose you received the following reviews from customers:

learn-pr/wwl-data-ai/introduction-language/includes/4-semantic-models.md

@@ -3,7 +3,7 @@ As the state of the art for NLP has advanced, the ability to train models that e
 Vectors represent lines in multidimensional space, describing direction and distance along multiple axes. Overall, the vector describes the direction and distance of the path from origin to end. Semantically similar tokens should result in vectors that have a similar orientation – in other words they point in the same direction. As a simple example, suppose the embeddings for our tokens consist of vectors with three elements, for example:
 
 ```
-- 4 ("dog"): [10.3.2]
+- 4 ("dog"): [10,3,2]
 - 5 ("bark"): [10,2,2]
 - 8 ("cat"): [10,3,1]
 - 9 ("meow"): [10,2,1]
@@ -36,4 +36,4 @@ For example, consider the following restaurant reviews, which are already labele
 - *Slow service and substandard food*: 0
 ```
 
-With enough labeled reviews, you can train a classification model using the tokenized text as *features* and the sentiment (0 or 1) a *label*. The model will encapsulate a relationship between tokens and sentiment - for example, reviews with tokens for words like `"great"`, `"tasty"`, or `"fun"` are more likely to return a sentiment of **1** (*positive*), while reviews with words like `"terrible"`, `"slow"`, and `"substandard"` are more likely to return **0** (*negative*).
+With enough labeled reviews, you can train a classification model using the tokenized text as *features* and the sentiment (0 or 1) a *label*. The model will encapsulate a relationship between tokens and sentiment - for example, reviews with tokens for words like `"great"`, `"tasty"`, or `"fun"` are more likely to return a sentiment of **1** (*positive*), while reviews with words like `"terrible"`, `"slow"`, and `"substandard"` are more likely to return **0** (*negative*).