Rasa NLU Components using PaddleNLP

Features

• Tokenizer and Dense featurizer using pre-trained models supported by PaddleNLP.

Usage

pip install rasa-paddlenlp

In your config.yml, use the following configuration:

language: zh

pipeline:
  - name: "rasa_paddlenlp.nlu.paddlenlp_tokenizer.PaddleNLPTokenizer"
    model_name: bert
    model_weights: bert-wwm-ext-chinese
    # Flag to check whether to split intents
    intent_tokenization_flag: false
    # Symbol on which intent should be split
    intent_split_symbol: "_"
  - name: "rasa_paddlenlp.nlu.paddlenlp_featurizer.PaddleNLPFeaturizer"
    model_name: bert
    model_weights: bert-wwm-ext-chinese
  # rest of your configurations

Currently there is code to support BERT pre-trained models, we just need to add the model definitions and default weights in order for other PaddleNLP-supported models.

Credits

This package took inspiration from the following projects:

• Rasa
• PaddleNLP

This package was created with Cookiecutter and the audreyr/cookiecutter-pypackage project template.

• Cookiecutter
• audreyr/cookiecutter-pypackage

License

MIT