Auto spelling correct the words before interpreter in rasa core

how can i use the auto word spelling correcter library on input text on user in rasa core.

You can try adding it to the message preprocessor

I would like to know how you did that if you are successful!

@datistiquo nope, the spelling corrector libraries performance is not good.

Yeahh I tested the one week free bing corrector and this perforsm not very well too! What librariers did you try?

1- SpellChecker 2- textblob 3- autocorrector

which library you have tested?

The Bing API!

I’d suggest just adding common spelling errors to your training data tbh (if you’re using the tensorflow embedding pipeline)

@akelad here is pipline. There could be many errors during the typing, so should I put all the possible errors ? is not be duplication ?

eg: 1- i am hapy for being alone. 2- i am happyfor being alone. 3- i am thapy being a lone .

should I insert all of them in my training files ??

language: "en"

- name: "nlp_spacy"
  model: "en"
- name: "tokenizer_spacy"
- name: "ner_spacy"
- name: "ner_duckling"
  - "number"
- name: "ner_crf"
  BILOU_flag: true
    # features for word before token
    - ["low", "title", "upper", "pos", "pos2"]
    # features of token itself
    - ["bias", "low", "upper","prefix5", "prefix2", "suffix3", "suffix2", "digit", "title", "digit", "pos", "pos2", "pattern"]
    # features for word after the token we want to tag
    - ["low", "title", "upper", "pos", "pos2"]
  max_iterations: 50
  L1_c: 1
  L2_c: 1e-3
- name: "ner_synonyms"
- name: "intent_featurizer_count_vectors"
- name: "intent_classifier_tensorflow_embedding"

How? Can you show any example?