Entity Recognition 

Entity Recognition also termed as Named-Entity Recognition (NER) is an approach of extracting the key information from the unstructured text, and tagging the extracted information with the predefined entities or labels such as the name of an organization, monetary values, locations, and others. With Entity recognition, you can also train a custom model to extract key entity information for your domain specific documents. 

To view the trained models for the Entity Recognizer List, navigate to Smart Bot > Entity Recognition.

The Entity Recognition page is displayed with two tabs - namely Dataset and Model.

• Dataset: Dataset page helps to upload datasets to the Smart Bot.

The Datasets section is displayed with the following details:

• Dataset Name: Specifies the name of the dataset.
• Description: Specifies the description of the dataset.
• File Name: Specifies a name to identify the dataset.
• Created Time: Specifies the date and time of the dataset when it was created.
• Created By: Specifies the name of the user who has created the dataset.
• Actions: Use the Actions column for performing the following operations: 
  • Download:  To download the uploaded dataset.
  • Delete:  To delete the uploaded dataset.

 

• Model: Model Page helps to select required dataset to train a model.

Model page displays following information:

Model page displays following information:

• Entity recognizer Name: Specifies the name of the predictor model.
• Dataset Name: Specifies the name of the selected dataset.
• Status: Specifies status of the classifier model.
  • Completed:  The model is trained successfully.
  • In Progress: The training is in progress.
  • Failed: the model failed to train.
• Description: Specifies the description of the classifier.
• Last Modified Time: Specifies the latest date and time when the text classification model was trained.
• Accuracy: Specifies the accuracy value of the trained model. The value is between 0 and 1. Higher value indicates higher confidence in the prediction. Accuracy helps choose the correct model.
• Actions: Use the Actions column for performing the following operations: 
  • Adapter:  To download default adapter. For more information, you can refer to the Working with Adapters Section. 
  • Delete:  To delete the Entity Recognizer model.
  • Download:  To download the trained Entity Recognizer model.
  • Predict:  Perform the Entity Recognition on the trained model.

 

• Adapter : For modifying the response format in the Python file. You can upload a new adapter file and download the existing adapter file for the specific model. To upload a new adapter file:
  1. Click the Adapter icon.
  2. The Adapter Configuration  window is displayed. Click Choose File to select the new adapter file in Python file format.

• Click Upload to upload a new adapter file to the existing model.
• Click Download to download the current adapter file.
• Click Reset to discard the selected file for uploading.