Configuring the input component

Configuring the input component - 7.3

Natural Language Processing

Version

7.3

Language

English

Product

Talend Big Data Platform

Talend Data Fabric

Talend Real-Time Big Data Platform

Module

Talend Studio

Content

Data Governance > Third-party systems > Natural Language Processing

Data Quality and Preparation > Third-party systems > Natural Language Processing

Design and Development > Third-party systems > Natural Language Processing

You annotated the named entities in the CoNLL files to be used for training the model.

Double-click the tFileInputDelimited component to open its Basic settings view and define its properties.
1. Set the Schema as Built-in and click Edit schema to define the desired schema.
  
  The first column in the output schema must be tokens and the last one must be labels. In between, you can have columns for features you added manually.
2. In the Folder/file field, specify the path to the training data.
3. Leave the Die on error check box selected.
In the Advanced settings view of the component, select the Custom encoding check box if you encounter issues when processing the data.
From the Encoding list, select the encoding to be used, UTF-8 in this example.