:Labeling templates for text

Text classification

Text classification is used to find one or more labels from a set of labels to match the content of the input text and attach the labels to the text. The category template supports single-label and multi-label text classification.

• Scenarios

  News recommendation, knowledge management, and junk content filtering.

• Data structure
  • Input data
    Each row in the manifest file contains a topic. The topic must contain the content field.

    {"data":{"content":"Welcome to Machine Learning Platform for AI! "}}

  • Output data
    Each row in the manifest file contains a topic and the labeling result. The following code provides an example of the JSON string in each row:

    {
      "data": {
        "content": "Welcome to Machine Learning Platform for AI! "
      },
      "label-p9fypszvupm9bh****": {
        "results": [{
          "data": [{
            "data": "Positive content",
            "id": 112****,
            "type": "survey/value"
          }],
          "id": "112****",
          "type": "survey"
        }]
      }
    }