HOW TO return multiple entities ? (using NLU only)

Rasa Open Source
1

Hi, How can I get multiple entities in the output? using NLU only. my pipeline is:

  • name: “tokenizer_whitespace” # splits the sentence into tokens
  • name: “ner_crf” # uses the pretrained spacy NER model
  • name: “intent_featurizer_count_vectors” # transform the sentence into a vector representation
  • name: “intent_classifier_tensorflow_embedding” # intent classifier intent_tokenization_flag: true # sets multi-intent tokenization intent_split_symbol: “+” # sets which symbol should be used for tokenization
  • name: “ner_synonyms” # trains synonyms component
2

What do you mean? You can define multiple entities in one sentence by tagging them using the following format:

intent: give_name_and_email

- I'm [Remy](name) and my e-mail address is [someone@example.com](email)

- my e-mail address is [someone@example.com](email) and my name is [Remy](name)