@@ -122,22 +122,11 @@ curl -i -X POST https://<your-language-resource-endpoint>/language/analyze-text/
122
122
{
123
123
"kind": "AbstractiveSummarization",
124
124
"taskName": "Text Abstractive Summarization Task 1",
125
- "parameters": {
126
- "summaryLength": "short"
127
- }
128
125
}
129
126
]
130
127
}
131
128
'
132
129
```
133
- If you don't specify ` summaryLength ` , the model determines the summary length.
134
-
135
- ### Using the summaryLength parameter
136
- For the ` summaryLength ` parameter, three values are accepted:
137
- * oneSentence: Generates a summary of mostly 1 sentence, with around 80 tokens.
138
- * short: Generates a summary of mostly 2-3 sentences, with around 120 tokens.
139
- * medium: Generates a summary of mostly 4-6 sentences, with around 170 tokens.
140
- * long: Generates a summary of mostly over 7 sentences, with around 210 tokens.
141
130
142
131
2 . Make the following changes in the command where needed:
143
132
- Replace the value ` your-language-resource-key ` with your key.
@@ -260,22 +249,29 @@ curl -i -X POST https://<your-language-resource-endpoint>/language/analyze-text/
260
249
"kind": "ExtractiveSummarization",
261
250
"taskName": "Query_based Extractive Summarization",
262
251
"parameters": {
263
- "query": "XYZ-code",
264
- "sentenceCount": 3
252
+ "query": "XYZ-code"
265
253
}
266
254
}
267
255
]
268
256
}
269
257
'
270
258
```
271
259
272
- ### Using the summaryLength parameter
260
+ ### Summary length control
261
+
262
+ #### Using the summaryLength parameter in abstractive summarization
263
+
264
+ If you don't specify ` summaryLength ` , the model determines the summary length.
265
+
273
266
For the ` summaryLength ` parameter, three values are accepted:
274
267
* oneSentence: Generates a summary of mostly 1 sentence, with around 80 tokens.
275
268
* short: Generates a summary of mostly 2-3 sentences, with around 120 tokens.
276
269
* medium: Generates a summary of mostly 4-6 sentences, with around 170 tokens.
277
270
* long: Generates a summary of mostly over 7 sentences, with around 210 tokens.
278
271
272
+ #### Using the sentenceCount parameter in extractive summarization
273
+ For the ` sentenceCount ` parameter (extractive summarization only), you can input a value 1-20 to indicate the desired number of output sentences.
274
+
279
275
## Service and data limits
280
276
281
277
[ !INCLUDE [ service limits article] ( ../../includes/service-limits-link.md )]
0 commit comments