Teneo Developers

Class Manager

Introduction

The Class Manager allows to built an Intent Classifier directly in Teneo Studio by adding classes, training data and - optionally - test data; read more about Intent Classification in Teneo here.

Create

To add a new class to the solution, follow the below steps:

  • In the Class Manager window, click Add Class in the top ribbon; the new class will appear in the Class list
  • In the Class details view, write the name of the class under Class Name
  • Now, write training examples in the Enter Training Example text field
    • When done, click Add or press Enter to add the example to the list and write a new one
    • Repeat above steps to introduce the all wanted training data examples
  • Optionally, select the Test Examples tab to add Test Data Examples
    • Write test examples in the Enter Test Example test field
    • When done, click Add or press Enter to add the example to the list and write a new one
    • Repeat above steps to introduce all the wanted test data examples
  • Remember to click Save in the Class Manager to preserve the modifications.

Note that it is not possible to save changes if a new class is created but no training data entered.

Some text editors, such as Windows Notepad or Notepad++, allows to select and drag text which can then be dropped onto the training data field in the Class Manager creating one training or test data example for each line in the original editor.

Edit

To edit an existing class:

  • Double-click the class name in the Class list, or
  • Select the class and click Edit in the top ribbon
  • Now, perform any needed updates:
    • Edit the name in the Class Name field
    • Write training examples in the Enter Training Example text field
      • When done, click Add or press Enter to add the example to the list and write a new one
      • Repeat above steps to introduce the all wanted training data examples
    • Select the Test Examples tab to add Test Data Examples
      • Write test examples in the Enter Test Example test field
      • When done, click Add or press Enter to add the example to the list and write a new one
      • Repeat above steps to introduce all the wanted test data examples
  • Remember to click Save to preserve any modifications.

TIP In edit-mode, drag/drop examples between the Training Examples tab and the Test Examples tab to move examples from one tab to the other; multi-select by pressing Ctrl while clicking and drag/drop multiple examples in one

The top ribbon of the Class Manager also provides a number of buttons and options, these are described further in the below table.

Class Manager: top ribbon (Home tab)

Class Manager's top ribbon

The Class Manager's top ribbon provide a range of buttons and options for working with classes, the below table lists the different buttons and, when relevant, links to more information are provided.

SectionButtonCommentMore info
Class ManagerCloseClose the Class ManagerClose
Save ClassesSave modifications performed in one or more classes; clicking the lower part of the button allows to save with or without commentSave
Import ClassesImport various classes from a .tsv fileImport classes
ClassesAdd ClassAdd a new classCreate
EditEdit the selected class
DeleteDelete the selected classDelete
Filter ClassesText field; use to filter on the list of classesFilter
ExamplesExamples FilterText field; use to filter on the lists of training and test data examplesFilter
HistoryClassOpen the history of the selected classHistory
Stable VersionSet/UnsetSet the current version of the selected class(es) as stable or unset itVersion flag
BranchingInclude/ExcludeInclude or Exclude the selected class(es) from branching when working in a Localization setupLocalization setup

Class tab

The backstage of the Class Manager (Class tab in the top of the Class Manager window) contains the below mentioned menu items.

Menu itemComment
Save ClassesSave all classes
CloseClose the Class Manager window

Generate

The option to Generate Training and Test Examples is only available if LLM Settings are defined for theAccount

To Generate Training and/or Test Examples, follow the below steps:

  • If not already open, open the Class Manager
  • Next, open an existing class in edit mode either by double-clicking the class in the Class list or by selecting the class and clicking Edit
  • If needed, select the Test Examples tab, else leave the selection of the Training Examples and click the Generate button
  • In the pop-up, select if the data should be generated from the existing examples or a description and also how many examples should be generated
  • Click Generate; alternatively click Cancel to abort
  • When the data generation is finished, review the examples in the preview and click Apply to add them to the Class
  • Remember to Save the Class to preserve the changes.

The new examples are highlighted with a yellow border for easy recognizability.

Save

New and modified classes can be saved in two ways:

  • Individually by clicking the Save button in the Class details view, or
  • all at once, using the Save button in the top ribbon of the Class Manager.

Note that the following restrictions are bound to the save action of classes:

  • the class name cannot contain spaces or reserved characters
  • every class must contain at least one training data entry
  • classes cannot contain duplicated training data examples nor duplicated test data examples.

Close

To close the Class Manager, either:

  • Click the X in the top, right corner of the Class Manager window
  • Click the Close button available in the top ribbon
  • In the Class Manager backstage, click Close in the left-side menu

If unsaved changes are detected, Teneo Studio will prompt the user to Save Changes, Discard Changes or Cancel.

Delete

To delete a class, follow the below steps:

  • Select the class to delete in the Class list; multi-select by pressing Ctrl while clicking
  • In the top ribbon, click Delete

The selected class(es) are marked for deletion until the next Save action is performed in the Class Manager, or until the user clicks Apply in the Class details section.
If a class is marked for deletion by mistake, select the class again and click Cancel in the Class details section.

Remember to click Save in the Class Manager to perform the actual deletion of the selected class(es) and to train a new machine learning model without the deleted class(es).

For more information, please see Delete documents

Filter

In the top ribbon of the Class Manager, two text filters are available:

  • one to filter classes, i.e., on the name of the class, and
  • one to filter on the examples provided as training data or test data of a previously selected class (or selected classes).

The two filters allows the user to filter separately in the Class list and the training and test examples. Both filters operate directly over the lists and are kept while the user is working on the classes, meaning that the filter isn't cleared if a new class is selected and any current filter is applied when selected another class. The filter(s) can be cleared by manually clicking the Clear Filter icon next to the filter text.

The options and functionalities described in this section currently only apply toTeneo Studio Desktop

The information related to a class, such as the name, Id, training data examples and test data examples, is searchable in the Search tab of the main Teneo Studio window.

The Id of a class is available at the bottom of the Class details in the Class Manager when selecting the class (in read-only mode). To copy the Id, simply right-click it and select copy from the context menu.

Class Id

For more information, please visit the Search section.

Import Classes

The options and functionalities described in this section currently only apply toTeneo Studio Desktop

The Import Classes button, in the top ribbon of the Class Manager, allows to import classes from an external file (in .tsv format); requirements related to the file are explained below.

To import a .tsv file, follow the below steps:

  • In the Class Manager, click Import Classes
  • Browse to the location of the .tsv file, select it and click Open
    Alternatively drag/drop the .tsv file onto the Class list
  • Teneo Studio prompts to confirm the data import, click Yes
  • Remember to click Save in the Class Manager to preserve the modifications.

Note that the import functionality does not check if the .tsv file contains duplicated data examples; this check is performed by the Class Manager when saving and the user will have to remove any duplicated examples from the Class Manager before being able to save the newly imported classes; also see Save further above.

File Requirements

As of Teneo 7.3 it is possible to import classes with both training data examples and test data examples.
The old format, specifying class name and training data example only, is still supported while a new format is available supporting data type, class name as well as test and training data examples.
Below please find further details for the new and old formats.

To update an existing class, the class name must be written in upper case in the .tsv file

The new format allows to:

  • create new class(es) with training data examples only
  • create new class(es) with training data examples and test data examples
  • update existing class(es) with test data examples and/or training data examples.

The requirements of the file to import are as follows:

  • plain text file, saved in the tab-separated values format (.tsv)
  • one line per training or test data example
  • each line must contain three columns separated by tab with the following information:
    • the data type: either TRAINING or TEST, note that data type must be written in upper case
    • a valid class name, and
    • depending on the specified data type, either a training or a test data example.

Plain text file with tab separation

Details

Class Name Requirements

The requirements for the class names are:

  • the class name must be unique
  • the class name must be upper case
  • the class name cannot contain reserved characters nor spaces

Teneo Studio automatically suggests a new class the name CLASS, this should be customized by the user.
If the user adds more classes (without customizing the names), Teneo Studio adds an incremental number to the suggested names of the next classes, for example, CLASS, CLASS_1, CLASS_2, CLASS_3, etc.
If the Class Name field is left empty, the user will not be able to save modifications until a name is provided.

Class Name As Annotation

At runtime, Teneo Predict uses the names of the classes to create the annotations for the most probable intent class(es) and denotes the annotation with a confidence score. The name of the annotation is the same as the name of a class in the Class Manager.

Therefore, the class name is visible in any place where annotations are usually seen, for example, in Tryout or scripting, and because of this users are encouraged to give each class a unique and easily recognizable class name.

As the class names are applied within the Teneo Platform as annotations, these can also be used within TLML syntaxes using the Teneo Linguistic Modeling Language.

Training Data

To train an intent model more than one class must exist and, for optimal performance, it is recommended to provide a minimum of ten unique training data examples per class. It is compulsory to add at least one training data example to each class.

Identical training data examples are not allowed and to avoid duplicated training examples, the Class Manager prevents developers from saving if two identical examples are detected in the same class. Saving is also prevented if an empty example is detected.
In Teneo Studio Desktop, when adding training examples manually, the Class Manager also prevents developers from adding a new example to the list if the exact same example already exists.

Keep an eye to the Suggestions in the backstage of Teneo Studio Desktop as duplicated examples detected in the same class or different classes are raised here

Note that to perform a Cross Validation evaluation in the Class Performance area of Teneo Studio Desktop, each class must contain a minimum of 5 training examples.

Test Data

Test Data can be added to classes just like training data, but where the training data is used to train the intent model, the test data is only used to evaluate the intent model when running Test Data Evaluation in the Class Performance area of Teneo Studio Desktop. And, therefore, it is not compulsory to add test data examples. Test data can be defined in a solution on triggers, transitions and classes.

Similarly to the training examples, the test examples must be unique. To avoid duplicated test examples, the Class Manager prevents developers from saving if two identical examples are detected.
In Teneo Studio Desktop, when adding test examples manually, the Class Manager prevents developers from adding a new example to the list if the exact same example already exists.

Furthermore, the Class Manager, in Teneo Studio Desktop, displays Linked Test Examples for the classes. The linked test examples come from triggers and transitions which reference the selected class (as a Class Match) and cover the positive User Intent examples added to the trigger or transition in the Flow. These linked test examples cannot be edited in the Class Manager, but direct navigation is possible by double-clicking. Note that User Intent examples from triggers and transitions in disabled flows are ignored and not displayed as linked test examples.

During a Test Data Evaluation, the model is evaluated with all the test data examples added directly to the class together with the linked test examples. Duplicated test examples are removed from the test data when running Test Data Evaluations.