Resume extraction

Service activation and resource plan purchase

Before you use a pre-trained model, you must activate the NLP Self-Learning Platform service. After you activate the service, you can purchase a resource plan.

NLP Self-Learning Platform: Activation URL

Self-Learning Platform Resource Plan: Purchase URL

1. Create a project

The NLP Self-Learning Platform supports multiple basic projects and application algorithms. This tutorial shows you how to create a Resume Extraction project on the platform. To begin, Go to the Self-Learning console.

Navigate to My Projects and click Create Project. In the Application Algorithms section, select Resume Extraction and click Create.

On the next page, enter a project name and description.

2. Data preparation

After you create a project, you can manage its data in the Data Center. You can create a dataset in two ways:

1. Create an annotation task. 2. Upload a dataset.

2.1 Create an annotation task

Step 1: Upload documents to annotate and add annotators

RAM user logon instructions:

1. Go to the RAM user logon page: https://signin.aliyun.com/login.htm

2. After you log on, go to My Projects > Create Annotation Task.

Note: Only data files with UTF-8 encoding are supported.

Step 2: Add custom tags

Select the preset fields to use for this annotation task. Then, add the field names for the custom tags that you need to annotate.

Step 3: Annotate data

2.2 Upload a dataset

A model learns patterns from annotated data. Therefore, you must first prepare a labeled dataset.

If you have existing annotated data, you must format it as required by the NLP Self-Learning Platform before you upload it.

The annotated data that you upload must be in JSON format and conform to the following structure. Place the text content in the "content" field. Place the label content in the "records" field. In the records field, the key is the entity name, and the value is the offset of the annotated content in the original text.

{
  "51979692":
   {
     "records":
      {
        "Name":[{"offset":[0,2],"span":"Zhang Mou"}],
        "Mobile Number":[{"offset":[15,26],"span":"1390000****"}],
        "Date of Birth":[{"offset":[53,63],"span":"1990/07/27"}],
        "Home Address":[{"offset":[68,74],"span":"Nanjing-** District"}],
        "Desired Position":[{"offset":[86,93],"span":"Software Test Engineer"}],
        "Email Address":[{"offset":[27,44],"span":"z****@example.com"}],
        "Gender":[{"offset":[45,46],"span":"Male"}]
      },
        "content":"Zhang Mou ID:6111****\n1390000****\nz****@example.com\nMale|29 years old (1990/07/27)|Currently lives in Nanjing-** District|8 years of work experience\nPosition: Software Test Engineer\n"
   }
}

3. Create a model

In the Model Hub, click Create Model.

To view the details of a model, click the View button next to the model.

Model details page

Model testing

After the model is trained, you can test its performance online.

Platform model testing

You can test text using the models that are already trained on the platform. You can also train specific labels separately to improve their accuracy.