Problem while storing the slot value

Rasa Open Source
1

Hi,

Premise: I have created a slot where I ask for users name and in my nlu file while writing intents for name I’ve also defined entities.

Problem: when user types something like call me “name” or my name is “name” the bot stores the whole sentence instead of name.

I only want to store the name so, how should I do it ?

any help would be appreciated!

2

There’s a blog post on this subject here. The flowchart there gives a good overview of how to approach entity extraction and the following paragraph address extracting names:

The spaCy library offers pretrained entity extractors. As with the word embeddings, only certain languages are supported. If your language is supported, the component ner_spacy is the recommended option to recognise entities like organization names, people’s names, or places. You can try out the recognition in the interactive demo of spaCy.

3

Thanks for the help:)

4

hi stephens, I have created a bot thats asks user information (using forms) and stores in database. I want to extract name from the user. so Im using spacy entity extractor and added dimension [‘PERSON’]. I have some doubts in nlu and domain. should I add the entities PERSON for name in nlu and add the entities in domain.

version: “2.0”

nlu:

  • intent: Names

    examples: |

    • My name is [shanthosh] (PERSON)
    • I am [Virat] (PERSON)
    • [vijay] (PERSON)

version: “2.0”

intents:

  • greet

  • goodbye

  • mobile_number

  • Names:

    use_entities:

    - PERSON

entities:

  • PERSON

slots:

name:

type: text

influence_conversation: false

forms:

user_details_form:

required_slots:

  name:

    - type: from_text

      entity: PERSON