Text Classification model

Text Classification is a sequence classification model based on BERT-based encoders. It can be used for a variety of tasks like text classification, sentiment analysis, domain/intent detection for dialogue systems, etc. The model takes a text input and predicts a label/class for the whole sequence. Megatron-LM and most of the BERT-based encoders supported by HuggingFace including BERT, RoBERTa, and DistilBERT.

An example script on how to train the model can be found here: NeMo/examples/nlp/text_classification/text_classification_with_bert.py. The default configuration file for the model can be found at: NeMo/examples/nlp/text_classification/conf/text_classification_config.yaml.

There is also a Jupyter notebook which explains how to work with this model. We recommend you try this model in the Jupyter notebook (can run on Google’s Colab.): NeMo/tutorials/nlp/Text_Classification_Sentiment_Analysis.ipynb. This tutorial shows an example of how run the Text Classification model on a sentiment analysis task. You may connect to an instance with a GPU (Runtime -> Change runtime type -> select GPU for the hardware accelerator) to run the notebook.

The Text Classification model uses a simple text format as the dataset. It requires the data to be stored in TAB separated files (.tsv) with two columns: sentence and label. Each line of the data file contains text sequences, where words are separated with spaces and the label is separated with [TAB], i.e.:

            

            
[WORD][SPACE][WORD][SPACE][WORD][TAB][LABEL]
        

Labels need to be integers starting from 0. Some examples taken from the SST2 dataset, which is a two-class dataset for sentiment analysis:

            

            
saw how bad this movie was  0
lend some dignity to a dumb story   0
the greatest musicians  1
        

You may need separate files for train, validation, and test with this format.

If your dataset is stored in another format, you need to convert it to NeMo’s format to use this model. There are some conversion scripts available for the following datasets:

• SST2 [NLP-TEXTCLASSIFY4]

• IMDB [NLP-TEXTCLASSIFY3]

• ChemProt [NLP-TEXTCLASSIFY2]

• THUCnews [NLP-TEXTCLASSIFY1]

You can convert them from their original format to NeMo’s format. To convert the original datasets to NeMo’s format, use the examples/text_classification/data/import_datasets.py script:

            

            
python import_datasets.py \
    --dataset_name DATASET_NAME \
    --target_data_dir TARGET_PATH \
    --source_data_dir SOURCE_PATH
        

It reads the dataset specified by DATASET_NAME from SOURCE_PATH and converts it to NeMo’s format. It then saves the new dataset at TARGET_PATH.

Arguments:

• dataset_name: name of the dataset to convert (sst-2, chemprot, imdb, and thucnews are currently supported)

• source_data_dir: directory of your dataset

• target_data_dir: directory to save the converted dataset

After the conversion, the TARGET_PATH should contain the following files:

            

            
.
|--TARGET_PATH
  |-- train.tsv
  |-- dev.tsv
  |-- test.tsv
        

Some datasets do not have the test set or their test set does not have any labels, therefore, the corresponding file may be missing.

You may find an example of a config file to be used for training of the Text Classification model at NeMo/examples/nlp/text_classification/conf/text_classification_config.yaml. You can change any of these parameters directly from the config file or update them with the command-line arguments.

The config file of the Text Classification model contains three main sections of trainer, exp_manager, and model. You can find more details about the trainer and exp_manager at Model NLP. Some sub-sections of the model section including tokenizer, language_model, and optim are shared among most of the NLP models. The details of these sections can be found at Model NLP.

Example of a command for training a Text Classification model on two GPUs for 50 epochs:

            

            
python examples/nlp/text_classification/text_classification_with_bert.py \
    model.training_ds.file_path=<TRAIN_FILE_PATH> \
    model.validation_ds.file_path=<VALIDATION_FILE_PATH> \
    trainer.max_epochs=50 \
    trainer.devices=[0,1] \
    trainer.accelerator='gpu' \
    optim.name=adam \
    optim.lr=0.0001 \
    model.nemo_path=<NEMO_FILE_PATH>
        

At the start of each training experiment, there is a printed log of the experiment specification including any parameters added or overridden via the command-line. It also shows additional information, such as which GPUs are available, where logs are saved, and some samples from the datasets with their corresponding inputs to the model. It also provides some stats on the lengths of sequences in the dataset.

After each epoch, you should see a summary table of metrics on the validation set which include the following metrics:

• Precision

• Recall

• F1

At the end of training, NeMo saves the last checkpoint at the path specified by NEMO_FILE_PATH in .nemo format.

Model Arguments

The following table lists some of the model’s parameters you can use in the config files or set them from the command-line when training a model:

After saving the model in .nemo format, you can load the model and perform evaluation or inference on the model. You can find some examples in the example script: NeMo/examples/nlp/text_classification/text_classification_with_bert.py.

[NLP-TEXTCLASSIFY1]

Jingyang Li and Maosong Sun. Scalable term selection for text categorization. In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), 774–782. 2007.

[NLP-TEXTCLASSIFY2]

Sangrak Lim and Jaewoo Kang. Chemical–gene relation extraction using recursive neural network. Database, 2018.

[NLP-TEXTCLASSIFY3]

Andrew L. Maas, Raymond E. Daly, Peter T. Pham, Dan Huang, Andrew Y. Ng, and Christopher Potts. Learning word vectors for sentiment analysis. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, 142–150. Portland, Oregon, USA, June 2011. Association for Computational Linguistics. URL: http://www.aclweb.org/anthology/P11-1015.

[NLP-TEXTCLASSIFY4]

Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D. Manning, Andrew Ng, and Christopher Potts. Recursive deep models for semantic compositionality over a sentiment treebank. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, 1631–1642. Seattle, Washington, USA, October 2013. Association for Computational Linguistics. URL: https://www.aclweb.org/anthology/D13-1170.