Skip to main content Skip to complementary content

Converting the tokenized text to the CoNLL format

To be able to learn a classification model from a text, you must divide this text into tokens and convert it to the CoNLL format using tNormalize.

Procedure

  1. Double-click the tNLPPreprocessing component to open its Basic settings view and define its properties.
    1. Click Sync columns to retrieve the schema from the previous component connected in the Job.
    1. From the NLP Library list, select the library to be used for tokenization. In this example, ScalaNLP is used.
  2. From the Column to preprocess list, select the column that holds the text to be divided into tokens, which is message in this example.
  3. Double-click the tFilterColumns component to open its Basic settings view and define its properties.
  4. Click Edit schema to add the tokens column in the output schema because this is the column to be normalized, and click OK to validate.
  5. Double-click the tNormalize component to open its Basic settings view and define its properties.
    1. Click Sync columns to retrieve the schema from the previous component connected in the Job.
    2. From the Column to normalize list, select tokens.
    3. In the Item separator field, enter "\t" to separate tokens using a tab in the output file.
  6. Double-click the tFileOutputDelimited component to open its Basic settings view and define its properties.
    1. Click Sync columns to retrieve the schema from the previous component connected in the Job.
    2. In the Folder field, specify the path to the folder where the CoNLL files will be stored.
    3. In the Row Separator field, enter "\n".
    4. In the Field Separator field, enter "\t" to separate fields with a tab.
  7. Press F6 to save and execute the Job.

Results

The output files are created in the specified folder. The files contain a single column with one token per row.

You can then manually label person names with PER and the other tokens with O before you can learn a classification model from this text data:

Did this page help you?

If you find any issues with this page or its content – a typo, a missing step, or a technical error – please let us know!

Leave your feedback here