Platform For AI:Text summarization predict

In Designer, configure component parameters in the UI.

• Input

  Input port (from left to right)	Type	Recommended upstream component	Required
  Prediction data	OSS	Read OSS Data	Yes
  Prediction model	Component output	Text Summarization Train	No

• Component configuration

  Tab	Parameter	Description
  Field Settings	Input data format	Text columns of the input file. The default value is target:str:1,source:str:1.
  	Source text column	Column name for source text in the input table. The default value is source.
  	Appended output columns	Specified text columns from the input file appended to output text columns. Separate multiple column names with a comma (,). The default value is source.
  	Output columns	Column names for the sink table. The default value is predictions,beams.
  	Prediction data output	OSS Bucket path where the prediction result file is stored.
  	Use custom model	Whether to use the default PAI model for direct prediction. Valid values: Yes No (default)
  	Is Megatron model	Only pre-trained models with the `mg` prefix listed in the Text Summarization Train component are supported. Valid values: Yes No (default)
  	Model path	Required only when Use custom model is set to Yes. Storage path of the custom model in an OSS Bucket.
  Parameter Settings	Batch size	Batch processing size during training. This is an INT type. The default value is 8. For multi-GPU servers, this parameter specifies the batch size for each GPU.
  	Maximum text length	Maximum length of the entire sequence. This is an INT type. The value must be in the range (1, 512). The default value is 512.
  	Language	Language for text processing: zh: Chinese. en: English.
  	Copy text from source	Whether to use a copy mechanism. Valid values: false (default) true
  	Minimum decoder length	Minimum length of the decoder. This is an INT type. The default value is 12. The model output length must be greater than this value.
  	Maximum decoder length	Maximum length of the decoder. This is an INT type. The default value is 32. The model output length must be less than this value.
  	Minimal Unique Field	Size of the non-repeating segment (n-gram). This is an INT type. The default value is 2.
  	Beam search size	Size for beam search. This is an INT type. The default value is 5.
  	Number of returned candidates	Number of results to return. This is an INT type. The default value is 5. Important This parameter must be the same as Beam search size.
  Execution Tuning	GPU type	GPU type of the compute resource. The default value is gn5-c8g1.2xlarge.

Build a workflow using the Text Summarization Predict component. Two methods are available:

• Method 1: Use a model fine-tuned by the Text Summarization Train component.

• Method 2: Use a custom model.

Configure the component and run the workflow:

1. Build a workflow. For more information, see the Example section of the Text Summarization Train topic.

2. Prepare data to summarize (predict_data.txt) and upload it to an OSS bucket. The test data in this example is a tab-delimited TXT file.

   CSV files are also supported. Use the Tunnel command of the MaxCompute client to upload the dataset to MaxCompute. For more information about how to install and configure the MaxCompute client, see Connect to MaxCompute using the client (odpscmd). For more information about the Tunnel command, see Tunnel commands.

3. Read the test dataset using the Read OSS Data-3 component in Method 1 or the Read OSS Data-1 component in Method 2. Set the OSS Data Path parameter to the OSS path where the test dataset is stored.

4. Connect the model file and test dataset to the Text Summarization Predict component and configure its parameters. For more information, see Configure component parameters in the UI.

   • For models fine-tuned by the Text Summarization Train component, connect the model output port of the Text Summarization Train component to the model input port of the Text Summarization Predict component.

   • For custom models, on the Field Settings tab, set the Use custom model parameter to Yes and set the Model path parameter to the OSS path where the model is stored.

5. Click the button to run the workflow. After successful execution, view the output summary in the OSS path specified for the Prediction data output parameter of the Text Summarization Predict component.