How to Generate a Summary

How to Add the Summary Generator to AutoClassifier

  1. Open AutoClassifier and go to the Features page.

    See the features.
  2. Expand the New Feature section.

    See the feature field.
  3. Enter a name such as New.
  4. Click Add and Apply to see the New Component.
  5. Expand New Component

    See the available features.
  6. Component Name: Enter a name such as BA<feature name>.
  7. Use the scroll bar to select your feature.
  8. Click Add and Apply to save the feature in the configuration.
  9. Existing Components > Name > <name of your component>: Click to see <name of your component> - Features page.

    See the Settings UI.
  10. Settings > Component is Enabled: Make sure that this checkbox is selected.
  11. Go to the Configure section on this page to continue configuring this feature.

How to Configure Your Summary Generator

  1. Feature page > Existing Components: Click the named link for the Summary Generator feature to see the Configuration section:


  2. Input Property:
    1. Specify the input metadata that the provided entities and sentences were extracted from.
    2. Example: body
  3. Sentences Property:
    1. Specify the input property containing the sentences extracted from the text metadata that are used for summary generation.
    2. These properties can be extracted by any other previous feature that you set up in the feature, if one of these features extracts sentences.
    3. For example, you might add the Natural Language Processor, which also extracts sentences, prior to this feature.
      1. Example: MicrosoftExtractedSentences
      2. If no Sentences Property is specified or the value of the provided sentences property is empty, the Summary Generator component will automatically extract sentences. 
  4. Entities Property:
    1. Specify the input property containing the entities used for the summary generation.
      1. Example:
        • MSSerializedEntitiesJson
        • ComprehendSerializedEntitiesJson
        • AmazonMedicalSerializedEntitiesJson
        • SpacySerializedEntitiesJson
        • SciSpacySerializedEntitiesJson
  5. Minimum length to process summary:
    1. If the input property character length is smaller than the specified value, the component will return the entire input as summary without processing.
  6. Summery percentage:
    1. Specify the summary size as a percentage (%) of the total text size.
  7. Summary lines:
    1. Specify the total number of sentences used to build the summary.
    2. This value is used only if the Summary percentage is set to 0.
  8. Language property:
    1. Specify the input metadata containing the previously extracted data in the document.
    2. If no property is specified, or an empty value is received, this feature uses English.
    3. Example: MicrosoftExtractedLanguages
Input Property Description
Input Text
Sentences Text – Multi (Optional)

Entities

JSON - Text

Minimum Length Numeric
Summary Percentage Numeric
Summary Lines Numeric
Language Text (Optional)


Output Property Description
DocumentSummary Text

Note: Summary Generator works with the following NLP provider components: