Merge pull request #225438 from jboback/SummarizationBugsJan2023

Initial Commit

Author: prmerger-automator[bot]

articles/cognitive-services/language-service/summarization/how-to/document-summarization.md

@@ -112,12 +112,16 @@ curl -i -X POST https://<your-language-resource-endpoint>/language/analyze-text/
   "tasks": [
     {
       "kind": "AbstractiveSummarization",
-      "taskName": "Document Abstractive Summarization Task 1"
+      "taskName": "Document Abstractive Summarization Task 1",
+      "parameters": {
+        "sentenceCount": 1
+      }
     }
   ]
-}
 '
 ```
+If you do not specify `sentenceCount`, the model will determine the summary length. Note that `sentenceCount` is the approximation of the sentence count of the output summary, range 1 to 20.
+
 2. Make the following changes in the command where needed:
 - Replace the value `your-language-resource-key` with your key.
 - Replace the first part of the request URL `your-language-resource-endpoint` with your endpoint URL.

articles/cognitive-services/language-service/summarization/includes/quickstarts/rest-api.md

@@ -289,6 +289,8 @@ curl -i -X POST https://<your-language-resource-endpoint>/language/analyze-conve
 }
 '
 ```
+Only the `resolution` aspect supports sentenceCount. If you do not specify the `sentenceCount` parameter, the model will determine the summary's length. Note that `sentenceCount` is just the approximation of sentence count of output summary, range 1 to 7.
+
 2. Make the following changes in the command where needed:
 - Replace the value `your-language-resource-key` with your key.
 - Replace the first part of the request URL `your-language-resource-endpoint` with your endpoint URL.