ModelsBasedOnTextEmbeddings: Base class for models using neural nets

In aifeducation: Artificial Intelligence for Education

Base class for models using neural nets

Description

Abstract class for all models that do not rely on the python library 'transformers'. All models of this class require text embeddings as input. These are provided as objects of class EmbeddedText or LargeDataSetForTextEmbeddings.

Objects of this class containing fields and methods used in several other classes in 'AI for Education'.

This class is not designed for a direct application and should only be used by developers.

Value

A new object of this class.

Super classes

aifeducation::AIFEMaster -> aifeducation::AIFEBaseModel -> ModelsBasedOnTextEmbeddings

Methods

Public methods

• ModelsBasedOnTextEmbeddings$get_text_embedding_model()

• ModelsBasedOnTextEmbeddings$get_text_embedding_model_name()

• ModelsBasedOnTextEmbeddings$check_embedding_model()

• ModelsBasedOnTextEmbeddings$save()

• ModelsBasedOnTextEmbeddings$load_from_disk()

• ModelsBasedOnTextEmbeddings$plot_training_history()

• ModelsBasedOnTextEmbeddings$clone()

Inherited methods

• aifeducation::AIFEMaster$get_all_fields()
• aifeducation::AIFEMaster$get_documentation_license()
• aifeducation::AIFEMaster$get_ml_framework()
• aifeducation::AIFEMaster$get_model_config()
• aifeducation::AIFEMaster$get_model_description()
• aifeducation::AIFEMaster$get_model_info()
• aifeducation::AIFEMaster$get_model_license()
• aifeducation::AIFEMaster$get_package_versions()
• aifeducation::AIFEMaster$get_private()
• aifeducation::AIFEMaster$get_publication_info()
• aifeducation::AIFEMaster$get_sustainability_data()
• aifeducation::AIFEMaster$is_configured()
• aifeducation::AIFEMaster$is_trained()
• aifeducation::AIFEMaster$set_documentation_license()
• aifeducation::AIFEMaster$set_model_description()
• aifeducation::AIFEMaster$set_model_license()
• aifeducation::AIFEMaster$set_publication_info()
• aifeducation::AIFEBaseModel$count_parameter()

---

Method get_text_embedding_model()

Method for requesting the text embedding model information.

Usage

ModelsBasedOnTextEmbeddings$get_text_embedding_model()

Returns

list of all relevant model information on the text embedding model underlying the model.

---

Method get_text_embedding_model_name()

Method for requesting the name (unique id) of the underlying text embedding model.

Usage

ModelsBasedOnTextEmbeddings$get_text_embedding_model_name()

Returns

Returns a string describing name of the text embedding model.

---

Method check_embedding_model()

Method for checking if the provided text embeddings are created with the same TextEmbeddingModel as the model.

Usage

ModelsBasedOnTextEmbeddings$check_embedding_model(text_embeddings)

Arguments

text_embeddings

Object of class EmbeddedText or LargeDataSetForTextEmbeddings.

Returns

TRUE if the underlying TextEmbeddingModel are the same. FALSE if the models differ.

---

Method save()

Method for saving a model.

Usage

ModelsBasedOnTextEmbeddings$save(dir_path, folder_name)

Arguments

dir_path

string Path of the directory where the model should be saved.

folder_name

string Name of the folder that should be created within the directory.

Returns

Function does not return a value. It saves the model to disk.

---

Method load_from_disk()

loads an object from disk and updates the object to the current version of the package.

Usage

ModelsBasedOnTextEmbeddings$load_from_disk(dir_path)

Arguments

dir_path

Path where the object set is stored.

Returns

Method does not return anything. It loads an object from disk.

---

Method plot_training_history()

Method for requesting a plot of the training history. This method requires the R package 'ggplot2' to work.

Usage

ModelsBasedOnTextEmbeddings$plot_training_history(
  final_training = FALSE,
  pl_step = NULL,
  measure = "loss",
  ind_best_model = TRUE,
  ind_selected_model = TRUE,
  x_min = NULL,
  x_max = NULL,
  y_min = NULL,
  y_max = NULL,
  add_min_max = TRUE,
  text_size = 10L
)

Arguments

final_training

bool If FALSE the values of the performance estimation are used. If TRUE only the epochs of the final training are used.

pl_step

int Number of the step during pseudo labeling to plot. Only relevant if the model was trained with active pseudo labeling.

measure

Measure to plot.

ind_best_model

bool If TRUE the plot indicates the best states of the model according to the chosen measure.

ind_selected_model

bool If TRUE the plot indicates the states of the model which are used after training. These are the final states of the fold or the final state of the last training loop.

x_min

int Minimal value for x-axis. Set to NULL for an automatic adjustment. Allowed values: x

x_max

int Maximal value for x-axis. Set to NULL for an automatic adjustment. Allowed values: x

y_min

int Minimal value for y-axis. Set to NULL for an automatic adjustment. Allowed values: x

y_max

int Maximal value for y-axis. Set to NULL for an automatic adjustment. Allowed values: x

add_min_max

bool If TRUE the minimal and maximal values during performance estimation are port of the plot. If FALSE only the mean values are shown. Parameter is ignored if final_training=TRUE.

text_size

int Size of text elements. Allowed values: 1 <= x

Returns

Returns a plot of class ggplot visualizing the training process. Prepare history data of objects Function for preparing the history data of a model in order to be plotted in AI for Education - Studio.

final bool If TRUE the history data of the final training is used for the data set. pl_step int If use_pl=TRUE select the step within pseudo labeling for which the data should be prepared. Returns a named list with the training history data of the model. The reported measures depend on the provided model.

Utils Studio Developers internal

---

Method clone()

The objects of this class are cloneable with this method.

Usage

ModelsBasedOnTextEmbeddings$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

See Also

Other R6 Classes for Developers: AIFEBaseModel, AIFEMaster, BaseModelCore, ClassifiersBasedOnTextEmbeddings, DataManagerClassifier, LargeDataSetBase, TEClassifiersBasedOnProtoNet, TEClassifiersBasedOnRegular, TokenizerBase

aifeducation documentation built on Nov. 19, 2025, 5:08 p.m.