Train Text Classification Model (GeoAI)

Summary

Trains a single or multilabel text classification model to assign a predefined category or label to unstructured text.

Learn more about how Text Classification works

Usage

  • This tool requires deep learning frameworks be installed. To set up your machine to use deep learning frameworks in ArcGIS Pro, see Install deep learning frameworks for ArcGIS.

  • This tool can also be used to fine-tune an existing trained model.

  • To run this tool using GPU, set the Processor Type environment to GPU. If you have more than one GPU, specify the GPU ID environment instead.

  • The input to the tool is a table or a feature class containing training data, with a text field containing the input text and a label field containing the target class labels.

  • For information about requirements for running this tool and issues you may encounter, see Deep Learning frequently asked questions.

Parameters

LabelExplanationData Type
Input Table

A feature class or table containing a text field with the input text for the model and a label field containing the target class labels.

Feature Layer; Table View
Text Field

A text field in the input feature class or table that contains the text that will be classified by the model.

Field
Label Field

A text field in the input feature class or table that contains the target class labels for training the model. In the case of multilabel text classification, specify more than one text field.

Field
Output Model

The output folder location that will store the trained model.

Folder
Pretrained Model File
(Optional)

A pretrained model that will be used to fine-tune the new model. The input can be an Esri model definition file (.emd) or a deep learning package file (.dlpk).

A pretrained model with similar classes can be fine-tuned to fit the new model. The pretrained model must have been trained with the same model type and backbone model that will be used to train the new model.

File
Max Epochs
(Optional)

The maximum number of epochs for which the model will be trained. A maximum epoch value of 1 means the dataset will be passed forward and backward through the neural network one time. The default value is 5.

Long
Model Backbone
(Optional)

Specifies the preconfigured neural network that will serve as the encoder for the model and extract feature representations of the input text in the form of fixed length vectors. These vectors are then passed as input to the classification head of the model.

  • bert-base-casedThe model will be trained using the BERT neural network. BERT is pretrained using the masked language modeling objective and next sentence prediction.
  • roberta-base The model will be trained using the RoBERTa neural network. RoBERTa modifies the key hyperparameters of BERT, eliminating the pretraining objective and training of the next sentence with small batches and higher learning rates.
  • albert-base-v1The model will be trained using the ALBERT neural network. ALBERT uses a self-supervised loss that focuses on modeling intersentence coherence, resulting in better scalability than BERT.
  • xlnet-base-casedThe model will be trained using the XLNet neural network. XLNet is a generalized autoregressive pretraining method. It allows learning bidirectional contexts by maximizing the expected probability on all permutations of the factorization order, which overcomes BERT's drawbacks.
  • xlm-roberta-baseThe model will be trained using the XLM-RoBERTa neural network. XLM-RoBERTa is a multilingual model trained on 100 different languages. Unlike some XLM multilingual models, it does not require language tensors to understand which language is used and identifies the correct language from the input IDs.
  • distilroberta-baseThe model will be trained using the DistilRoBERTa neural network. DistilRoBERTa is an English language model pretrained with the supervision of roberta-base solely on OpenWebTextCorpus, a reproduction of OpenAI's WebText dataset.
  • distilbert-base-casedThe model will be trained using the DistilBERT neural network. DistilBERT is a smaller general-purpose language representation model.
String
Batch Size
(Optional)

The number of training samples that will be processed at one time. The default value is 2.

Increasing the batch size can improve tool performance; however, as the batch size increases, more memory is used. If an out of memory error occurs, use a smaller batch size.

Double
Model Arguments
(Optional)

Additional arguments for initializing the model, such as seq_len for the maximum sequence length of the training data, that will be considered for training the model.

See keyword arguments in the TextClassifier documentation for the list of supported model arguments that can be used.

Value Table
Learning Rate
(Optional)

The step size indicating how much the model weights will be adjusted during the training process. If no value is specified, an optimal learning rate will be determined automatically.

Double
Validation Percentage
(Optional)

The percentage of training samples that will be used for validating the model. The default value is 10.

Double
Stop when model stops improving
(Optional)

Specifies whether model training will stop when the model is no longer improving or until the Max Epochs parameter value is reached.

  • Checked—The model training will stop when the model is no longer improving, regardless of the Max Epochs parameter value specified. This is the default.
  • Unchecked—The model training will continue until the Max Epochs parameter value is reached.
Boolean
Make model backbone trainable
(Optional)

Specifies whether the backbone layers in the pretrained model will be frozen, so that the weights and biases remain as originally designed.

  • Checked—The backbone layers will not be frozen, and the weights and biases of the Model Backbone parameter value can be altered to fit the training samples. This takes more time to process but typically produces better results. This is the default.
  • Unchecked—The backbone layers will be frozen, and the predefined weights and biases of the Model Backbone parameter value will not be altered during training.

Boolean
Remove HTML Tags
(Optional)

Specifies whether HTML tags will be removed from the input text.

  • Checked—The HTML tags in the input text will be removed. This is the default.
  • Unchecked—The HTML tags in the input text will not be removed.

Boolean
Remove URLs
(Optional)

Specifies whether URLs will be removed from the input text.

  • Checked—The URLs in the input text will be removed. This is the default.
  • Unchecked—The URLs in the input text will not be removed.

Boolean

arcpy.geoai.TrainTextClassificationModel(in_table, text_field, label_field, out_model, {pretrained_model_file}, {max_epochs}, {model_backbone}, {batch_size}, {model_arguments}, {learning_rate}, {validation_percentage}, {stop_training}, {make_trainable}, {remove_html_tags}, {remove_urls})
NameExplanationData Type
in_table

A feature class or table containing a text field with the input text for the model and a label field containing the target class labels.

Feature Layer; Table View
text_field

A text field in the input feature class or table that contains the text that will be classified by the model.

Field
label_field
[label_field,...]

A text field in the input feature class or table that contains the target class labels for training the model. In the case of multilabel text classification, specify more than one text field.

Field
out_model

The output folder location that will store the trained model.

Folder
pretrained_model_file
(Optional)

A pretrained model that will be used to fine-tune the new model. The input can be an Esri model definition file (.emd) or a deep learning package file (.dlpk).

A pretrained model with similar classes can be fine-tuned to fit the new model. The pretrained model must have been trained with the same model type and backbone model that will be used to train the new model.

File
max_epochs
(Optional)

The maximum number of epochs for which the model will be trained. A maximum epoch value of 1 means the dataset will be passed forward and backward through the neural network one time. The default value is 5.

Long
model_backbone
(Optional)

Specifies the preconfigured neural network that will serve as the encoder for the model and extract feature representations of the input text in the form of fixed length vectors. These vectors are then passed as input to the classification head of the model.

  • bert-base-casedThe model will be trained using the BERT neural network. BERT is pretrained using the masked language modeling objective and next sentence prediction.
  • roberta-base The model will be trained using the RoBERTa neural network. RoBERTa modifies the key hyperparameters of BERT, eliminating the pretraining objective and training of the next sentence with small batches and higher learning rates.
  • albert-base-v1The model will be trained using the ALBERT neural network. ALBERT uses a self-supervised loss that focuses on modeling intersentence coherence, resulting in better scalability than BERT.
  • xlnet-base-casedThe model will be trained using the XLNet neural network. XLNet is a generalized autoregressive pretraining method. It allows learning bidirectional contexts by maximizing the expected probability on all permutations of the factorization order, which overcomes BERT's drawbacks.
  • xlm-roberta-baseThe model will be trained using the XLM-RoBERTa neural network. XLM-RoBERTa is a multilingual model trained on 100 different languages. Unlike some XLM multilingual models, it does not require language tensors to understand which language is used and identifies the correct language from the input IDs.
  • distilroberta-baseThe model will be trained using the DistilRoBERTa neural network. DistilRoBERTa is an English language model pretrained with the supervision of roberta-base solely on OpenWebTextCorpus, a reproduction of OpenAI's WebText dataset.
  • distilbert-base-casedThe model will be trained using the DistilBERT neural network. DistilBERT is a smaller general-purpose language representation model.
String
batch_size
(Optional)

The number of training samples that will be processed at one time. The default value is 2.

Increasing the batch size can improve tool performance; however, as the batch size increases, more memory is used. If an out of memory error occurs, use a smaller batch size.

Double
model_arguments
[model_arguments,...]
(Optional)

Additional arguments for initializing the model, such as seq_len for the maximum sequence length of the training data, that will be considered for training the model.

See keyword arguments in the TextClassifier documentation for the list of supported model arguments that can be used.

Value Table
learning_rate
(Optional)

The step size indicating how much the model weights will be adjusted during the training process. If no value is specified, an optimal learning rate will be determined automatically.

Double
validation_percentage
(Optional)

The percentage of training samples that will be used for validating the model. The default value is 10.

Double
stop_training
(Optional)

Specifies whether model training will stop when the model is no longer improving or until the max_epochs parameter value is reached.

  • STOP_TRAININGThe model training will stop when the model is no longer improving, regardless of the max_epochs parameter value specified. This is the default.
  • CONTINUE_TRAININGThe model training will continue until the max_epochs parameter value is reached.
Boolean
make_trainable
(Optional)

Specifies whether the backbone layers in the pretrained model will be frozen, so that the weights and biases remain as originally designed.

  • TRAIN_MODEL_BACKBONEThe backbone layers will not be frozen, and the weights and biases of the model_backbone parameter value can be altered to fit the training samples. This takes more time to process but typically produces better results. This is the default.
  • FREEZE_MODEL_BACKBONEThe backbone layers will be frozen, and the predefined weights and biases of the model_backbone parameter value will not be altered during training.
Boolean
remove_html_tags
(Optional)

Specifies whether HTML tags will be removed from the input text.

  • REMOVE_HTML_TAGSThe HTML tags in the input text will be removed. This is the default.
  • DO_NOT_REMOVE_HTML_TAGSThe HTML tags in the input text will not be removed.
Boolean
remove_urls
(Optional)

Specifies whether URLs will be removed from the input text.

  • REMOVE_URLSThe URLs in the input text will be removed. This is the default.
  • DO_NOT_REMOVE_URLSThe URLs in the input text will not be removed.
Boolean

Code sample

TrainTextClassificationModel (Python window)

The following Python window script demonstrates how to use the TrainTextClassificationModel function.

# Name: TrainTextClassification.py
# Description: Train a text classifier model to classify text in different classes.  
#
# Requirements: ArcGIS Pro Advanced license

# Import system modules
import arcpy
import os

arcpy.env.workspace = "C:/textanalysisexamples/data"

# Set local variables
in_table = "training_data_textclassifier.csv"
out_folder = "c\\textclassifier"

# Run Train Text Classification Model
arcpy.geoai.TrainTextClassificationModel(in_table, out_folder, 
            max_epochs=2, text_field="Address", label_field="Country", batch_size=16)

Environments

Licensing information

  • Basic: No
  • Standard: No
  • Advanced: Yes

Related topics